Duplicate from florentgbelidji/blip_image_embeddings

Co-authored-by: Florent Gbelidji <florentgbelidji@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,31 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,53 @@
+---
+tags:
+- feature-extraction
+- endpoints-template
+license: bsd-3-clause
+library_name: generic
+duplicated_from: florentgbelidji/blip_image_embeddings
+---
+# Fork of [salesforce/BLIP](https://github.com/salesforce/BLIP) for a `feature-extraction` task on 🤗Inference endpoint.
+This repository implements a `custom` task for `feature-extraction` for 🤗 Inference Endpoints. The code for the customized pipeline is in the [pipeline.py](https://huggingface.co/florentgbelidji/blip-embeddings/blob/main/pipeline.py).
+To use deploy this model a an Inference Endpoint you have to select `Custom` as task to use the `pipeline.py` file. -> _double check if it is selected_
+### expected Request payload
+```json
+{
+  "image": "/9j/4AAQSkZJRgABAQEBLAEsAAD/2wBDAAMCAgICAgMC....", // base64 image as bytes
+}
+```
+below is an example on how to run a request using Python and `requests`.
+## Run Request 
+1. prepare an image. 
+```bash
+!wget https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
+```
+2.run request
+```python
+import json
+from typing import List
+import requests as r
+import base64
+ENDPOINT_URL = ""
+HF_TOKEN = ""
+def predict(path_to_image: str = None):
+    with open(path_to_image, "rb") as i:
+        b64 = base64.b64encode(i.read())
+    payload = {"inputs": {"image": b64.decode("utf-8")}}
+    response = r.post(
+        ENDPOINT_URL, headers={"Authorization": f"Bearer {HF_TOKEN}"}, json=payload
+    )
+    return response.json()
+prediction = predict(
+    path_to_image="palace.jpg"
+)
+```
+expected output
+```python
+{'feature_vector': [0.016450975090265274,
+  -0.5551009774208069,
+  0.39800673723220825,
+  -0.6809228658676147,
+  2.053842782974243,
+  -0.4712907075881958,...]
+ }
+```

configs/med_config.json

@@ -0,0 +1,21 @@
+{
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "type_vocab_size": 2,
+  "vocab_size": 30524,
+  "encoder_width": 768,
+  "add_cross_attention": true   
+}

model_large_retrieval_coco.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e10e32c7a152f087afbb72ee6ddc817ca18e10641607b9fb72e20f9b4a5f63
+size 3687945348

models/.ipynb_checkpoints/blip_decoder-checkpoint.py

@@ -0,0 +1,175 @@
+'''
+ * Copyright (c) 2022, salesforce.com, inc.
+ * All rights reserved.
+ * SPDX-License-Identifier: BSD-3-Clause
+ * For full license text, see LICENSE.txt file in the repo root or https://opensource.org/licenses/BSD-3-Clause
+ * By Junnan Li
+'''
+import warnings
+warnings.filterwarnings("ignore")
+
+from models.vit import VisionTransformer, interpolate_pos_embed
+from models.med import BertConfig, BertModel, BertLMHeadModel
+from transformers import BertTokenizer
+
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+import os
+from urllib.parse import urlparse
+from timm.models.hub import download_cached_file
+
+class BLIP_Decoder(nn.Module):
+    def __init__(self,                 
+                 med_config = 'configs/med_config.json',  
+                 image_size = 384,
+                 vit = 'base',
+                 vit_grad_ckpt = False,
+                 vit_ckpt_layer = 0,
+                 prompt = 'a picture of ',
+                 ):
+        """
+        Args:
+            med_config (str): path for the mixture of encoder-decoder model's configuration file
+            image_size (int): input image size
+            vit (str): model size of vision transformer
+        """            
+        super().__init__()
+        
+        self.visual_encoder, vision_width = create_vit(vit,image_size, vit_grad_ckpt, vit_ckpt_layer)
+        self.tokenizer = init_tokenizer()   
+        med_config = BertConfig.from_json_file(med_config)
+        med_config.encoder_width = vision_width
+        self.text_decoder = BertLMHeadModel(config=med_config)    
+        
+        self.prompt = prompt
+        self.prompt_length = len(self.tokenizer(self.prompt).input_ids)-1
+
+        
+    def forward(self, image, caption):
+        
+        image_embeds = self.visual_encoder(image) 
+        image_atts = torch.ones(image_embeds.size()[:-1],dtype=torch.long).to(image.device)
+        
+        text = self.tokenizer(caption, padding='longest', truncation=True, max_length=40, return_tensors="pt").to(image.device) 
+        
+        text.input_ids[:,0] = self.tokenizer.bos_token_id
+        
+        decoder_targets = text.input_ids.masked_fill(text.input_ids == self.tokenizer.pad_token_id, -100)         
+        decoder_targets[:,:self.prompt_length] = -100
+     
+        decoder_output = self.text_decoder(text.input_ids, 
+                                           attention_mask = text.attention_mask, 
+                                           encoder_hidden_states = image_embeds,
+                                           encoder_attention_mask = image_atts,                  
+                                           labels = decoder_targets,
+                                           return_dict = True,   
+                                          )   
+        loss_lm = decoder_output.loss
+        
+        return loss_lm
+        
+    def generate(self, image, sample=False, num_beams=3, max_length=30, min_length=10, top_p=0.9, repetition_penalty=1.0):
+        image_embeds = self.visual_encoder(image)
+
+        if not sample:
+            image_embeds = image_embeds.repeat_interleave(num_beams,dim=0)
+            
+        image_atts = torch.ones(image_embeds.size()[:-1],dtype=torch.long).to(image.device)
+        model_kwargs = {"encoder_hidden_states": image_embeds, "encoder_attention_mask":image_atts}
+        
+        prompt = [self.prompt] * image.size(0)
+        input_ids = self.tokenizer(prompt, return_tensors="pt").input_ids.to(image.device) 
+        input_ids[:,0] = self.tokenizer.bos_token_id
+        input_ids = input_ids[:, :-1] 
+
+        if sample:
+            #nucleus sampling
+            outputs = self.text_decoder.generate(input_ids=input_ids,
+                                                  max_length=max_length,
+                                                  min_length=min_length,
+                                                  do_sample=True,
+                                                  top_p=top_p,
+                                                  num_return_sequences=1,
+                                                  eos_token_id=self.tokenizer.sep_token_id,
+                                                  pad_token_id=self.tokenizer.pad_token_id, 
+                                                  repetition_penalty=1.1,                                            
+                                                  **model_kwargs)
+        else:
+            #beam search
+            outputs = self.text_decoder.generate(input_ids=input_ids,
+                                                  max_length=max_length,
+                                                  min_length=min_length,
+                                                  num_beams=num_beams,
+                                                  eos_token_id=self.tokenizer.sep_token_id,
+                                                  pad_token_id=self.tokenizer.pad_token_id,     
+                                                  repetition_penalty=repetition_penalty,
+                                                  **model_kwargs)            
+            
+        captions = []    
+        for output in outputs:
+            caption = self.tokenizer.decode(output, skip_special_tokens=True)    
+            captions.append(caption[len(self.prompt):])
+        return captions
+
+
+def blip_decoder(pretrained='',**kwargs):
+    model = BLIP_Decoder(**kwargs)
+    if pretrained:
+        model,msg = load_checkpoint(model,pretrained)
+        assert(len(msg.missing_keys)==0)
+    return model    
+
+def init_tokenizer():
+    tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+    tokenizer.add_special_tokens({'bos_token':'[DEC]'})
+    tokenizer.add_special_tokens({'additional_special_tokens':['[ENC]']})       
+    tokenizer.enc_token_id = tokenizer.additional_special_tokens_ids[0]  
+    return tokenizer
+
+
+def create_vit(vit, image_size, use_grad_checkpointing=False, ckpt_layer=0, drop_path_rate=0):
+        
+    assert vit in ['base', 'large'], "vit parameter must be base or large"
+    if vit=='base':
+        vision_width = 768
+        visual_encoder = VisionTransformer(img_size=image_size, patch_size=16, embed_dim=vision_width, depth=12, 
+                                           num_heads=12, use_grad_checkpointing=use_grad_checkpointing, ckpt_layer=ckpt_layer,
+                                           drop_path_rate=0 or drop_path_rate
+                                          )   
+    elif vit=='large':
+        vision_width = 1024
+        visual_encoder = VisionTransformer(img_size=image_size, patch_size=16, embed_dim=vision_width, depth=24, 
+                                           num_heads=16, use_grad_checkpointing=use_grad_checkpointing, ckpt_layer=ckpt_layer,
+                                           drop_path_rate=0.1 or drop_path_rate
+                                          )   
+    return visual_encoder, vision_width
+
+def is_url(url_or_filename):
+    parsed = urlparse(url_or_filename)
+    return parsed.scheme in ("http", "https")
+
+def load_checkpoint(model,url_or_filename):
+    if is_url(url_or_filename):
+        cached_file = download_cached_file(url_or_filename, check_hash=False, progress=True)
+        checkpoint = torch.load(cached_file, map_location='cpu') 
+    elif os.path.isfile(url_or_filename):        
+        checkpoint = torch.load(url_or_filename, map_location='cpu') 
+    else:
+        raise RuntimeError('checkpoint url or path is invalid')
+        
+    state_dict = checkpoint['model']
+    
+    state_dict['visual_encoder.pos_embed'] = interpolate_pos_embed(state_dict['visual_encoder.pos_embed'],model.visual_encoder) 
+    if 'visual_encoder_m.pos_embed' in model.state_dict().keys():
+        state_dict['visual_encoder_m.pos_embed'] = interpolate_pos_embed(state_dict['visual_encoder_m.pos_embed'],
+                                                                         model.visual_encoder_m)    
+    for key in model.state_dict().keys():
+        if key in state_dict.keys():
+            if state_dict[key].shape!=model.state_dict()[key].shape:
+                del state_dict[key]
+    
+    msg = model.load_state_dict(state_dict,strict=False)
+    print('load checkpoint from %s'%url_or_filename)  
+    return model,msg

models/.ipynb_checkpoints/blip_feature_extractor-checkpoint.py

@@ -0,0 +1,135 @@
+'''
+ * Copyright (c) 2022, salesforce.com, inc.
+ * All rights reserved.
+ * SPDX-License-Identifier: BSD-3-Clause
+ * For full license text, see LICENSE.txt file in the repo root or https://opensource.org/licenses/BSD-3-Clause
+ * By Junnan Li
+'''
+import warnings
+warnings.filterwarnings("ignore")
+
+from models.vit import VisionTransformer, interpolate_pos_embed
+from models.med import BertConfig, BertModel, BertLMHeadModel
+from transformers import BertTokenizer
+
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+import os
+from urllib.parse import urlparse
+from timm.models.hub import download_cached_file
+
+class BLIP_Base(nn.Module):
+    def __init__(self,                 
+                 med_config = 'configs/med_config.json',  
+                 image_size = 224,
+                 vit = 'base',
+                 vit_grad_ckpt = False,
+                 vit_ckpt_layer = 0,                 
+                 ):
+        """
+        Args:
+            med_config (str): path for the mixture of encoder-decoder model's configuration file
+            image_size (int): input image size
+            vit (str): model size of vision transformer
+        """               
+        super().__init__()
+        
+        self.visual_encoder, vision_width = create_vit(vit,image_size, vit_grad_ckpt, vit_ckpt_layer)
+        self.tokenizer = init_tokenizer()   
+        med_config = BertConfig.from_json_file(med_config)
+        med_config.encoder_width = vision_width
+        self.text_encoder = BertModel(config=med_config, add_pooling_layer=False)  
+
+        
+    def forward(self, image, caption, mode):
+        
+        assert mode in ['image', 'text', 'multimodal'], "mode parameter must be image, text, or multimodal"
+        text = self.tokenizer(caption, return_tensors="pt").to(image.device) 
+        
+        if mode=='image':    
+            # return image features
+            image_embeds = self.visual_encoder(image)             
+            return image_embeds
+        
+        elif mode=='text':
+            # return text features
+            text_output = self.text_encoder(text.input_ids, attention_mask = text.attention_mask,                      
+                                            return_dict = True, mode = 'text')  
+            return text_output.last_hidden_state
+        
+        elif mode=='multimodal':
+            # return multimodel features
+            image_embeds = self.visual_encoder(image)    
+            image_atts = torch.ones(image_embeds.size()[:-1],dtype=torch.long).to(image.device)      
+            
+            text.input_ids[:,0] = self.tokenizer.enc_token_id
+            output = self.text_encoder(text.input_ids,
+                                       attention_mask = text.attention_mask,
+                                       encoder_hidden_states = image_embeds,
+                                       encoder_attention_mask = image_atts,      
+                                       return_dict = True,
+                                      )              
+            return output.last_hidden_state
+
+
+def blip_feature_extractor(pretrained='',**kwargs):
+    model = BLIP_Base(**kwargs)
+    if pretrained:
+        model,msg = load_checkpoint(model,pretrained)
+        assert(len(msg.missing_keys)==0)
+    return model        
+
+def init_tokenizer():
+    tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+    tokenizer.add_special_tokens({'bos_token':'[DEC]'})
+    tokenizer.add_special_tokens({'additional_special_tokens':['[ENC]']})       
+    tokenizer.enc_token_id = tokenizer.additional_special_tokens_ids[0]  
+    return tokenizer
+
+
+def create_vit(vit, image_size, use_grad_checkpointing=False, ckpt_layer=0, drop_path_rate=0):
+        
+    assert vit in ['base', 'large'], "vit parameter must be base or large"
+    if vit=='base':
+        vision_width = 768
+        visual_encoder = VisionTransformer(img_size=image_size, patch_size=16, embed_dim=vision_width, depth=12, 
+                                           num_heads=12, use_grad_checkpointing=use_grad_checkpointing, ckpt_layer=ckpt_layer,
+                                           drop_path_rate=0 or drop_path_rate
+                                          )   
+    elif vit=='large':
+        vision_width = 1024
+        visual_encoder = VisionTransformer(img_size=image_size, patch_size=16, embed_dim=vision_width, depth=24, 
+                                           num_heads=16, use_grad_checkpointing=use_grad_checkpointing, ckpt_layer=ckpt_layer,
+                                           drop_path_rate=0.1 or drop_path_rate
+                                          )   
+    return visual_encoder, vision_width
+
+def is_url(url_or_filename):
+    parsed = urlparse(url_or_filename)
+    return parsed.scheme in ("http", "https")
+
+def load_checkpoint(model,url_or_filename):
+    if is_url(url_or_filename):
+        cached_file = download_cached_file(url_or_filename, check_hash=False, progress=True)
+        checkpoint = torch.load(cached_file, map_location='cpu') 
+    elif os.path.isfile(url_or_filename):        
+        checkpoint = torch.load(url_or_filename, map_location='cpu') 
+    else:
+        raise RuntimeError('checkpoint url or path is invalid')
+        
+    state_dict = checkpoint['model']
+    
+    state_dict['visual_encoder.pos_embed'] = interpolate_pos_embed(state_dict['visual_encoder.pos_embed'],model.visual_encoder) 
+    if 'visual_encoder_m.pos_embed' in model.state_dict().keys():
+        state_dict['visual_encoder_m.pos_embed'] = interpolate_pos_embed(state_dict['visual_encoder_m.pos_embed'],
+                                                                         model.visual_encoder_m)    
+    for key in model.state_dict().keys():
+        if key in state_dict.keys():
+            if state_dict[key].shape!=model.state_dict()[key].shape:
+                del state_dict[key]
+    
+    msg = model.load_state_dict(state_dict,strict=False)
+    print('load checkpoint from %s'%url_or_filename)  
+    return model,msg

models/blip_decoder.py

@@ -0,0 +1,175 @@
+'''
+ * Copyright (c) 2022, salesforce.com, inc.
+ * All rights reserved.
+ * SPDX-License-Identifier: BSD-3-Clause
+ * For full license text, see LICENSE.txt file in the repo root or https://opensource.org/licenses/BSD-3-Clause
+ * By Junnan Li
+'''
+import warnings
+warnings.filterwarnings("ignore")
+
+from models.vit import VisionTransformer, interpolate_pos_embed
+from models.med import BertConfig, BertModel, BertLMHeadModel
+from transformers import BertTokenizer
+
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+import os
+from urllib.parse import urlparse
+from timm.models.hub import download_cached_file
+
+class BLIP_Decoder(nn.Module):
+    def __init__(self,                 
+                 med_config = 'configs/med_config.json',  
+                 image_size = 384,
+                 vit = 'base',
+                 vit_grad_ckpt = False,
+                 vit_ckpt_layer = 0,
+                 prompt = 'a picture of ',
+                 ):
+        """
+        Args:
+            med_config (str): path for the mixture of encoder-decoder model's configuration file
+            image_size (int): input image size
+            vit (str): model size of vision transformer
+        """            
+        super().__init__()
+        
+        self.visual_encoder, vision_width = create_vit(vit,image_size, vit_grad_ckpt, vit_ckpt_layer)
+        self.tokenizer = init_tokenizer()   
+        med_config = BertConfig.from_json_file(med_config)
+        med_config.encoder_width = vision_width
+        self.text_decoder = BertLMHeadModel(config=med_config)    
+        
+        self.prompt = prompt
+        self.prompt_length = len(self.tokenizer(self.prompt).input_ids)-1
+
+        
+    def forward(self, image, caption):
+        
+        image_embeds = self.visual_encoder(image) 
+        image_atts = torch.ones(image_embeds.size()[:-1],dtype=torch.long).to(image.device)
+        
+        text = self.tokenizer(caption, padding='longest', truncation=True, max_length=40, return_tensors="pt").to(image.device) 
+        
+        text.input_ids[:,0] = self.tokenizer.bos_token_id
+        
+        decoder_targets = text.input_ids.masked_fill(text.input_ids == self.tokenizer.pad_token_id, -100)         
+        decoder_targets[:,:self.prompt_length] = -100
+     
+        decoder_output = self.text_decoder(text.input_ids, 
+                                           attention_mask = text.attention_mask, 
+                                           encoder_hidden_states = image_embeds,
+                                           encoder_attention_mask = image_atts,                  
+                                           labels = decoder_targets,
+                                           return_dict = True,   
+                                          )   
+        loss_lm = decoder_output.loss
+        
+        return loss_lm
+        
+    def generate(self, image, sample=False, num_beams=3, max_length=30, min_length=10, top_p=0.9, repetition_penalty=1.0):
+        image_embeds = self.visual_encoder(image)
+
+        if not sample:
+            image_embeds = image_embeds.repeat_interleave(num_beams,dim=0)
+            
+        image_atts = torch.ones(image_embeds.size()[:-1],dtype=torch.long).to(image.device)
+        model_kwargs = {"encoder_hidden_states": image_embeds, "encoder_attention_mask":image_atts}
+        
+        prompt = [self.prompt] * image.size(0)
+        input_ids = self.tokenizer(prompt, return_tensors="pt").input_ids.to(image.device) 
+        input_ids[:,0] = self.tokenizer.bos_token_id
+        input_ids = input_ids[:, :-1] 
+
+        if sample:
+            #nucleus sampling
+            outputs = self.text_decoder.generate(input_ids=input_ids,
+                                                  max_length=max_length,
+                                                  min_length=min_length,
+                                                  do_sample=True,
+                                                  top_p=top_p,
+                                                  num_return_sequences=1,
+                                                  eos_token_id=self.tokenizer.sep_token_id,
+                                                  pad_token_id=self.tokenizer.pad_token_id, 
+                                                  repetition_penalty=1.1,                                            
+                                                  **model_kwargs)
+        else:
+            #beam search
+            outputs = self.text_decoder.generate(input_ids=input_ids,
+                                                  max_length=max_length,
+                                                  min_length=min_length,
+                                                  num_beams=num_beams,
+                                                  eos_token_id=self.tokenizer.sep_token_id,
+                                                  pad_token_id=self.tokenizer.pad_token_id,     
+                                                  repetition_penalty=repetition_penalty,
+                                                  **model_kwargs)            
+            
+        captions = []    
+        for output in outputs:
+            caption = self.tokenizer.decode(output, skip_special_tokens=True)    
+            captions.append(caption[len(self.prompt):])
+        return captions
+
+
+def blip_decoder(pretrained='',**kwargs):
+    model = BLIP_Decoder(**kwargs)
+    if pretrained:
+        model,msg = load_checkpoint(model,pretrained)
+        assert(len(msg.missing_keys)==0)
+    return model    
+
+def init_tokenizer():
+    tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+    tokenizer.add_special_tokens({'bos_token':'[DEC]'})
+    tokenizer.add_special_tokens({'additional_special_tokens':['[ENC]']})       
+    tokenizer.enc_token_id = tokenizer.additional_special_tokens_ids[0]  
+    return tokenizer
+
+
+def create_vit(vit, image_size, use_grad_checkpointing=False, ckpt_layer=0, drop_path_rate=0):
+        
+    assert vit in ['base', 'large'], "vit parameter must be base or large"
+    if vit=='base':
+        vision_width = 768
+        visual_encoder = VisionTransformer(img_size=image_size, patch_size=16, embed_dim=vision_width, depth=12, 
+                                           num_heads=12, use_grad_checkpointing=use_grad_checkpointing, ckpt_layer=ckpt_layer,
+                                           drop_path_rate=0 or drop_path_rate
+                                          )   
+    elif vit=='large':
+        vision_width = 1024
+        visual_encoder = VisionTransformer(img_size=image_size, patch_size=16, embed_dim=vision_width, depth=24, 
+                                           num_heads=16, use_grad_checkpointing=use_grad_checkpointing, ckpt_layer=ckpt_layer,
+                                           drop_path_rate=0.1 or drop_path_rate
+                                          )   
+    return visual_encoder, vision_width
+
+def is_url(url_or_filename):
+    parsed = urlparse(url_or_filename)
+    return parsed.scheme in ("http", "https")
+
+def load_checkpoint(model,url_or_filename):
+    if is_url(url_or_filename):
+        cached_file = download_cached_file(url_or_filename, check_hash=False, progress=True)
+        checkpoint = torch.load(cached_file, map_location='cpu') 
+    elif os.path.isfile(url_or_filename):        
+        checkpoint = torch.load(url_or_filename, map_location='cpu') 
+    else:
+        raise RuntimeError('checkpoint url or path is invalid')
+        
+    state_dict = checkpoint['model']
+    
+    state_dict['visual_encoder.pos_embed'] = interpolate_pos_embed(state_dict['visual_encoder.pos_embed'],model.visual_encoder) 
+    if 'visual_encoder_m.pos_embed' in model.state_dict().keys():
+        state_dict['visual_encoder_m.pos_embed'] = interpolate_pos_embed(state_dict['visual_encoder_m.pos_embed'],
+                                                                         model.visual_encoder_m)    
+    for key in model.state_dict().keys():
+        if key in state_dict.keys():
+            if state_dict[key].shape!=model.state_dict()[key].shape:
+                del state_dict[key]
+    
+    msg = model.load_state_dict(state_dict,strict=False)
+    print('load checkpoint from %s'%url_or_filename)  
+    return model,msg

models/blip_feature_extractor.py

@@ -0,0 +1,135 @@
+'''
+ * Copyright (c) 2022, salesforce.com, inc.
+ * All rights reserved.
+ * SPDX-License-Identifier: BSD-3-Clause
+ * For full license text, see LICENSE.txt file in the repo root or https://opensource.org/licenses/BSD-3-Clause
+ * By Junnan Li
+'''
+import warnings
+warnings.filterwarnings("ignore")
+
+from models.vit import VisionTransformer, interpolate_pos_embed
+from models.med import BertConfig, BertModel, BertLMHeadModel
+from transformers import BertTokenizer
+
+import torch
+from torch import nn
+import torch.nn.functional as F
+
+import os
+from urllib.parse import urlparse
+from timm.models.hub import download_cached_file
+
+class BLIP_Base(nn.Module):
+    def __init__(self,                 
+                 med_config = 'configs/med_config.json',  
+                 image_size = 224,
+                 vit = 'base',
+                 vit_grad_ckpt = False,
+                 vit_ckpt_layer = 0,                 
+                 ):
+        """
+        Args:
+            med_config (str): path for the mixture of encoder-decoder model's configuration file
+            image_size (int): input image size
+            vit (str): model size of vision transformer
+        """               
+        super().__init__()
+        
+        self.visual_encoder, vision_width = create_vit(vit,image_size, vit_grad_ckpt, vit_ckpt_layer)
+        self.tokenizer = init_tokenizer()   
+        med_config = BertConfig.from_json_file(med_config)
+        med_config.encoder_width = vision_width
+        self.text_encoder = BertModel(config=med_config, add_pooling_layer=False)  
+
+        
+    def forward(self, image, caption, mode):
+        
+        assert mode in ['image', 'text', 'multimodal'], "mode parameter must be image, text, or multimodal"
+        text = self.tokenizer(caption, return_tensors="pt").to(image.device) 
+        
+        if mode=='image':    
+            # return image features
+            image_embeds = self.visual_encoder(image)             
+            return image_embeds
+        
+        elif mode=='text':
+            # return text features
+            text_output = self.text_encoder(text.input_ids, attention_mask = text.attention_mask,                      
+                                            return_dict = True, mode = 'text')  
+            return text_output.last_hidden_state
+        
+        elif mode=='multimodal':
+            # return multimodel features
+            image_embeds = self.visual_encoder(image)    
+            image_atts = torch.ones(image_embeds.size()[:-1],dtype=torch.long).to(image.device)      
+            
+            text.input_ids[:,0] = self.tokenizer.enc_token_id
+            output = self.text_encoder(text.input_ids,
+                                       attention_mask = text.attention_mask,
+                                       encoder_hidden_states = image_embeds,
+                                       encoder_attention_mask = image_atts,      
+                                       return_dict = True,
+                                      )              
+            return output.last_hidden_state
+
+
+def blip_feature_extractor(pretrained='',**kwargs):
+    model = BLIP_Base(**kwargs)
+    if pretrained:
+        model,msg = load_checkpoint(model,pretrained)
+        assert(len(msg.missing_keys)==0)
+    return model        
+
+def init_tokenizer():
+    tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+    tokenizer.add_special_tokens({'bos_token':'[DEC]'})
+    tokenizer.add_special_tokens({'additional_special_tokens':['[ENC]']})       
+    tokenizer.enc_token_id = tokenizer.additional_special_tokens_ids[0]  
+    return tokenizer
+
+
+def create_vit(vit, image_size, use_grad_checkpointing=False, ckpt_layer=0, drop_path_rate=0):
+        
+    assert vit in ['base', 'large'], "vit parameter must be base or large"
+    if vit=='base':
+        vision_width = 768
+        visual_encoder = VisionTransformer(img_size=image_size, patch_size=16, embed_dim=vision_width, depth=12, 
+                                           num_heads=12, use_grad_checkpointing=use_grad_checkpointing, ckpt_layer=ckpt_layer,
+                                           drop_path_rate=0 or drop_path_rate
+                                          )   
+    elif vit=='large':
+        vision_width = 1024
+        visual_encoder = VisionTransformer(img_size=image_size, patch_size=16, embed_dim=vision_width, depth=24, 
+                                           num_heads=16, use_grad_checkpointing=use_grad_checkpointing, ckpt_layer=ckpt_layer,
+                                           drop_path_rate=0.1 or drop_path_rate
+                                          )   
+    return visual_encoder, vision_width
+
+def is_url(url_or_filename):
+    parsed = urlparse(url_or_filename)
+    return parsed.scheme in ("http", "https")
+
+def load_checkpoint(model,url_or_filename):
+    if is_url(url_or_filename):
+        cached_file = download_cached_file(url_or_filename, check_hash=False, progress=True)
+        checkpoint = torch.load(cached_file, map_location='cpu') 
+    elif os.path.isfile(url_or_filename):        
+        checkpoint = torch.load(url_or_filename, map_location='cpu') 
+    else:
+        raise RuntimeError('checkpoint url or path is invalid')
+        
+    state_dict = checkpoint['model']
+    
+    state_dict['visual_encoder.pos_embed'] = interpolate_pos_embed(state_dict['visual_encoder.pos_embed'],model.visual_encoder) 
+    if 'visual_encoder_m.pos_embed' in model.state_dict().keys():
+        state_dict['visual_encoder_m.pos_embed'] = interpolate_pos_embed(state_dict['visual_encoder_m.pos_embed'],
+                                                                         model.visual_encoder_m)    
+    for key in model.state_dict().keys():
+        if key in state_dict.keys():
+            if state_dict[key].shape!=model.state_dict()[key].shape:
+                del state_dict[key]
+    
+    msg = model.load_state_dict(state_dict,strict=False)
+    print('load checkpoint from %s'%url_or_filename)  
+    return model,msg

models/med.py

@@ -0,0 +1,953 @@
+'''
+ * Copyright (c) 2022, salesforce.com, inc.
+ * All rights reserved.
+ * SPDX-License-Identifier: BSD-3-Clause
+ * For full license text, see LICENSE.txt file in the repo root or https://opensource.org/licenses/BSD-3-Clause
+ * By Junnan Li
+ * Based on huggingface code base
+ * https://github.com/huggingface/transformers/blob/v4.15.0/src/transformers/models/bert
+'''
+
+import math
+import os
+import warnings
+from dataclasses import dataclass
+from typing import Optional, Tuple
+
+import torch
+from torch import Tensor, device, dtype, nn
+import torch.utils.checkpoint
+from torch import nn
+from torch.nn import CrossEntropyLoss
+import torch.nn.functional as F
+
+from transformers.activations import ACT2FN
+from transformers.file_utils import (
+    ModelOutput,
+)
+from transformers.modeling_outputs import (
+    BaseModelOutputWithPastAndCrossAttentions,
+    BaseModelOutputWithPoolingAndCrossAttentions,
+    CausalLMOutputWithCrossAttentions,
+    MaskedLMOutput,
+    MultipleChoiceModelOutput,
+    NextSentencePredictorOutput,
+    QuestionAnsweringModelOutput,
+    SequenceClassifierOutput,
+    TokenClassifierOutput,
+)
+from transformers.modeling_utils import (
+    PreTrainedModel,
+    apply_chunking_to_forward,
+    find_pruneable_heads_and_indices,
+    prune_linear_layer,
+)
+from transformers.utils import logging
+from transformers.models.bert.configuration_bert import BertConfig
+
+
+logger = logging.get_logger(__name__)
+
+
+class BertEmbeddings(nn.Module):
+    """Construct the embeddings from word and position embeddings."""
+
+    def __init__(self, config):
+        super().__init__()
+        self.word_embeddings = nn.Embedding(config.vocab_size, config.hidden_size, padding_idx=config.pad_token_id)
+        self.position_embeddings = nn.Embedding(config.max_position_embeddings, config.hidden_size)
+
+        # self.LayerNorm is not snake-cased to stick with TensorFlow model variable name and be able to load
+        # any TensorFlow checkpoint file
+        self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
+        self.dropout = nn.Dropout(config.hidden_dropout_prob)
+
+        # position_ids (1, len position emb) is contiguous in memory and exported when serialized
+        self.register_buffer("position_ids", torch.arange(config.max_position_embeddings).expand((1, -1)))
+        self.position_embedding_type = getattr(config, "position_embedding_type", "absolute")
+        
+        self.config = config
+
+    def forward(
+        self, input_ids=None, position_ids=None, inputs_embeds=None, past_key_values_length=0
+    ):
+        if input_ids is not None:
+            input_shape = input_ids.size()
+        else:
+            input_shape = inputs_embeds.size()[:-1]
+
+        seq_length = input_shape[1]
+
+        if position_ids is None:
+            position_ids = self.position_ids[:, past_key_values_length : seq_length + past_key_values_length]
+
+        if inputs_embeds is None:
+            inputs_embeds = self.word_embeddings(input_ids)
+
+        embeddings = inputs_embeds
+
+        if self.position_embedding_type == "absolute":
+            position_embeddings = self.position_embeddings(position_ids)
+            embeddings += position_embeddings
+        embeddings = self.LayerNorm(embeddings)
+        embeddings = self.dropout(embeddings)
+        return embeddings
+
+
+class BertSelfAttention(nn.Module):
+    def __init__(self, config, is_cross_attention):
+        super().__init__()
+        self.config = config
+        if config.hidden_size % config.num_attention_heads != 0 and not hasattr(config, "embedding_size"):
+            raise ValueError(
+                "The hidden size (%d) is not a multiple of the number of attention "
+                "heads (%d)" % (config.hidden_size, config.num_attention_heads)
+            )
+        
+        self.num_attention_heads = config.num_attention_heads
+        self.attention_head_size = int(config.hidden_size / config.num_attention_heads)
+        self.all_head_size = self.num_attention_heads * self.attention_head_size
+
+        self.query = nn.Linear(config.hidden_size, self.all_head_size)
+        if is_cross_attention:
+            self.key = nn.Linear(config.encoder_width, self.all_head_size)
+            self.value = nn.Linear(config.encoder_width, self.all_head_size)
+        else:
+            self.key = nn.Linear(config.hidden_size, self.all_head_size)
+            self.value = nn.Linear(config.hidden_size, self.all_head_size)
+
+        self.dropout = nn.Dropout(config.attention_probs_dropout_prob)
+        self.position_embedding_type = getattr(config, "position_embedding_type", "absolute")
+        if self.position_embedding_type == "relative_key" or self.position_embedding_type == "relative_key_query":
+            self.max_position_embeddings = config.max_position_embeddings
+            self.distance_embedding = nn.Embedding(2 * config.max_position_embeddings - 1, self.attention_head_size)
+        self.save_attention = False   
+            
+    def save_attn_gradients(self, attn_gradients):
+        self.attn_gradients = attn_gradients
+        
+    def get_attn_gradients(self):
+        return self.attn_gradients
+    
+    def save_attention_map(self, attention_map):
+        self.attention_map = attention_map
+        
+    def get_attention_map(self):
+        return self.attention_map
+    
+    def transpose_for_scores(self, x):
+        new_x_shape = x.size()[:-1] + (self.num_attention_heads, self.attention_head_size)
+        x = x.view(*new_x_shape)
+        return x.permute(0, 2, 1, 3)
+
+    def forward(
+        self,
+        hidden_states,
+        attention_mask=None,
+        head_mask=None,
+        encoder_hidden_states=None,
+        encoder_attention_mask=None,
+        past_key_value=None,
+        output_attentions=False,
+    ):
+        mixed_query_layer = self.query(hidden_states)
+
+        # If this is instantiated as a cross-attention module, the keys
+        # and values come from an encoder; the attention mask needs to be
+        # such that the encoder's padding tokens are not attended to.
+        is_cross_attention = encoder_hidden_states is not None
+
+        if is_cross_attention:
+            key_layer = self.transpose_for_scores(self.key(encoder_hidden_states))
+            value_layer = self.transpose_for_scores(self.value(encoder_hidden_states))
+            attention_mask = encoder_attention_mask
+        elif past_key_value is not None:
+            key_layer = self.transpose_for_scores(self.key(hidden_states))
+            value_layer = self.transpose_for_scores(self.value(hidden_states))
+            key_layer = torch.cat([past_key_value[0], key_layer], dim=2)
+            value_layer = torch.cat([past_key_value[1], value_layer], dim=2)
+        else:
+            key_layer = self.transpose_for_scores(self.key(hidden_states))
+            value_layer = self.transpose_for_scores(self.value(hidden_states))
+
+        query_layer = self.transpose_for_scores(mixed_query_layer)
+
+        past_key_value = (key_layer, value_layer)
+
+        # Take the dot product between "query" and "key" to get the raw attention scores.
+        attention_scores = torch.matmul(query_layer, key_layer.transpose(-1, -2))
+
+        if self.position_embedding_type == "relative_key" or self.position_embedding_type == "relative_key_query":
+            seq_length = hidden_states.size()[1]
+            position_ids_l = torch.arange(seq_length, dtype=torch.long, device=hidden_states.device).view(-1, 1)
+            position_ids_r = torch.arange(seq_length, dtype=torch.long, device=hidden_states.device).view(1, -1)
+            distance = position_ids_l - position_ids_r
+            positional_embedding = self.distance_embedding(distance + self.max_position_embeddings - 1)
+            positional_embedding = positional_embedding.to(dtype=query_layer.dtype)  # fp16 compatibility
+
+            if self.position_embedding_type == "relative_key":
+                relative_position_scores = torch.einsum("bhld,lrd->bhlr", query_layer, positional_embedding)
+                attention_scores = attention_scores + relative_position_scores
+            elif self.position_embedding_type == "relative_key_query":
+                relative_position_scores_query = torch.einsum("bhld,lrd->bhlr", query_layer, positional_embedding)
+                relative_position_scores_key = torch.einsum("bhrd,lrd->bhlr", key_layer, positional_embedding)
+                attention_scores = attention_scores + relative_position_scores_query + relative_position_scores_key
+
+        attention_scores = attention_scores / math.sqrt(self.attention_head_size)
+        if attention_mask is not None:
+            # Apply the attention mask is (precomputed for all layers in BertModel forward() function)
+            attention_scores = attention_scores + attention_mask
+
+        # Normalize the attention scores to probabilities.
+        attention_probs = nn.Softmax(dim=-1)(attention_scores)
+        
+        if is_cross_attention and self.save_attention:
+            self.save_attention_map(attention_probs)
+            attention_probs.register_hook(self.save_attn_gradients)         
+
+        # This is actually dropping out entire tokens to attend to, which might
+        # seem a bit unusual, but is taken from the original Transformer paper.
+        attention_probs_dropped = self.dropout(attention_probs)
+
+        # Mask heads if we want to
+        if head_mask is not None:
+            attention_probs_dropped = attention_probs_dropped * head_mask
+
+        context_layer = torch.matmul(attention_probs_dropped, value_layer)
+
+        context_layer = context_layer.permute(0, 2, 1, 3).contiguous()
+        new_context_layer_shape = context_layer.size()[:-2] + (self.all_head_size,)
+        context_layer = context_layer.view(*new_context_layer_shape)
+
+        outputs = (context_layer, attention_probs) if output_attentions else (context_layer,)
+
+        outputs = outputs + (past_key_value,)
+        return outputs
+
+
+class BertSelfOutput(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.dense = nn.Linear(config.hidden_size, config.hidden_size)
+        self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
+        self.dropout = nn.Dropout(config.hidden_dropout_prob)
+
+    def forward(self, hidden_states, input_tensor):
+        hidden_states = self.dense(hidden_states)
+        hidden_states = self.dropout(hidden_states)
+        hidden_states = self.LayerNorm(hidden_states + input_tensor)
+        return hidden_states
+
+
+class BertAttention(nn.Module):
+    def __init__(self, config, is_cross_attention=False):
+        super().__init__()
+        self.self = BertSelfAttention(config, is_cross_attention)
+        self.output = BertSelfOutput(config)
+        self.pruned_heads = set()
+
+    def prune_heads(self, heads):
+        if len(heads) == 0:
+            return
+        heads, index = find_pruneable_heads_and_indices(
+            heads, self.self.num_attention_heads, self.self.attention_head_size, self.pruned_heads
+        )
+
+        # Prune linear layers
+        self.self.query = prune_linear_layer(self.self.query, index)
+        self.self.key = prune_linear_layer(self.self.key, index)
+        self.self.value = prune_linear_layer(self.self.value, index)
+        self.output.dense = prune_linear_layer(self.output.dense, index, dim=1)
+
+        # Update hyper params and store pruned heads
+        self.self.num_attention_heads = self.self.num_attention_heads - len(heads)
+        self.self.all_head_size = self.self.attention_head_size * self.self.num_attention_heads
+        self.pruned_heads = self.pruned_heads.union(heads)
+
+    def forward(
+        self,
+        hidden_states,
+        attention_mask=None,
+        head_mask=None,
+        encoder_hidden_states=None,
+        encoder_attention_mask=None,
+        past_key_value=None,
+        output_attentions=False,
+    ):
+        self_outputs = self.self(
+            hidden_states,
+            attention_mask,
+            head_mask,
+            encoder_hidden_states,
+            encoder_attention_mask,
+            past_key_value,
+            output_attentions,
+        )
+        attention_output = self.output(self_outputs[0], hidden_states)
+        outputs = (attention_output,) + self_outputs[1:]  # add attentions if we output them
+        return outputs
+
+
+class BertIntermediate(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.dense = nn.Linear(config.hidden_size, config.intermediate_size)
+        if isinstance(config.hidden_act, str):
+            self.intermediate_act_fn = ACT2FN[config.hidden_act]
+        else:
+            self.intermediate_act_fn = config.hidden_act
+
+    def forward(self, hidden_states):
+        hidden_states = self.dense(hidden_states)
+        hidden_states = self.intermediate_act_fn(hidden_states)
+        return hidden_states
+
+
+class BertOutput(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.dense = nn.Linear(config.intermediate_size, config.hidden_size)
+        self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
+        self.dropout = nn.Dropout(config.hidden_dropout_prob)
+
+    def forward(self, hidden_states, input_tensor):
+        hidden_states = self.dense(hidden_states)
+        hidden_states = self.dropout(hidden_states)
+        hidden_states = self.LayerNorm(hidden_states + input_tensor)
+        return hidden_states
+
+
+class BertLayer(nn.Module):
+    def __init__(self, config, layer_num):
+        super().__init__()
+        self.config = config
+        self.chunk_size_feed_forward = config.chunk_size_feed_forward
+        self.seq_len_dim = 1
+        self.attention = BertAttention(config)      
+        self.layer_num = layer_num          
+        if self.config.add_cross_attention:
+            self.crossattention = BertAttention(config, is_cross_attention=self.config.add_cross_attention)
+        self.intermediate = BertIntermediate(config)
+        self.output = BertOutput(config)
+
+    def forward(
+        self,
+        hidden_states,
+        attention_mask=None,
+        head_mask=None,
+        encoder_hidden_states=None,
+        encoder_attention_mask=None,
+        past_key_value=None,
+        output_attentions=False,
+        mode=None,
+    ):
+        # decoder uni-directional self-attention cached key/values tuple is at positions 1,2
+        self_attn_past_key_value = past_key_value[:2] if past_key_value is not None else None
+        self_attention_outputs = self.attention(
+            hidden_states,
+            attention_mask,
+            head_mask,
+            output_attentions=output_attentions,
+            past_key_value=self_attn_past_key_value,
+        )
+        attention_output = self_attention_outputs[0]
+
+        outputs = self_attention_outputs[1:-1]
+        present_key_value = self_attention_outputs[-1]
+
+        if mode=='multimodal':
+            assert encoder_hidden_states is not None, "encoder_hidden_states must be given for cross-attention layers"
+
+            cross_attention_outputs = self.crossattention(
+                attention_output,
+                attention_mask,
+                head_mask,
+                encoder_hidden_states,
+                encoder_attention_mask,
+                output_attentions=output_attentions,
+            )
+            attention_output = cross_attention_outputs[0]
+            outputs = outputs + cross_attention_outputs[1:-1]  # add cross attentions if we output attention weights                               
+        layer_output = apply_chunking_to_forward(
+            self.feed_forward_chunk, self.chunk_size_feed_forward, self.seq_len_dim, attention_output
+        )
+        outputs = (layer_output,) + outputs
+
+        outputs = outputs + (present_key_value,)
+
+        return outputs
+
+    def feed_forward_chunk(self, attention_output):
+        intermediate_output = self.intermediate(attention_output)
+        layer_output = self.output(intermediate_output, attention_output)
+        return layer_output
+
+
+class BertEncoder(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.config = config
+        self.layer = nn.ModuleList([BertLayer(config,i) for i in range(config.num_hidden_layers)])
+        self.gradient_checkpointing = False
+
+    def forward(
+        self,
+        hidden_states,
+        attention_mask=None,
+        head_mask=None,
+        encoder_hidden_states=None,
+        encoder_attention_mask=None,
+        past_key_values=None,
+        use_cache=None,
+        output_attentions=False,
+        output_hidden_states=False,
+        return_dict=True,
+        mode='multimodal',
+    ):
+        all_hidden_states = () if output_hidden_states else None
+        all_self_attentions = () if output_attentions else None
+        all_cross_attentions = () if output_attentions and self.config.add_cross_attention else None
+
+        next_decoder_cache = () if use_cache else None
+               
+        for i in range(self.config.num_hidden_layers):
+            layer_module = self.layer[i]
+            if output_hidden_states:
+                all_hidden_states = all_hidden_states + (hidden_states,)
+
+            layer_head_mask = head_mask[i] if head_mask is not None else None
+            past_key_value = past_key_values[i] if past_key_values is not None else None
+
+            if self.gradient_checkpointing and self.training:
+
+                if use_cache:
+                    logger.warn(
+                        "`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`..."
+                    )
+                    use_cache = False
+
+                def create_custom_forward(module):
+                    def custom_forward(*inputs):
+                        return module(*inputs, past_key_value, output_attentions)
+
+                    return custom_forward
+
+                layer_outputs = torch.utils.checkpoint.checkpoint(
+                    create_custom_forward(layer_module),
+                    hidden_states,
+                    attention_mask,
+                    layer_head_mask,
+                    encoder_hidden_states,
+                    encoder_attention_mask,
+                    mode=mode,
+                )
+            else:
+                layer_outputs = layer_module(
+                    hidden_states,
+                    attention_mask,
+                    layer_head_mask,
+                    encoder_hidden_states,
+                    encoder_attention_mask,
+                    past_key_value,
+                    output_attentions,
+                    mode=mode,
+                )
+
+            hidden_states = layer_outputs[0]
+            if use_cache:
+                next_decoder_cache += (layer_outputs[-1],)
+            if output_attentions:
+                all_self_attentions = all_self_attentions + (layer_outputs[1],)
+
+        if output_hidden_states:
+            all_hidden_states = all_hidden_states + (hidden_states,)
+
+        if not return_dict:
+            return tuple(
+                v
+                for v in [
+                    hidden_states,
+                    next_decoder_cache,
+                    all_hidden_states,
+                    all_self_attentions,
+                    all_cross_attentions,
+                ]
+                if v is not None
+            )
+        return BaseModelOutputWithPastAndCrossAttentions(
+            last_hidden_state=hidden_states,
+            past_key_values=next_decoder_cache,
+            hidden_states=all_hidden_states,
+            attentions=all_self_attentions,
+            cross_attentions=all_cross_attentions,
+        )
+
+
+class BertPooler(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.dense = nn.Linear(config.hidden_size, config.hidden_size)
+        self.activation = nn.Tanh()
+
+    def forward(self, hidden_states):
+        # We "pool" the model by simply taking the hidden state corresponding
+        # to the first token.
+        first_token_tensor = hidden_states[:, 0]
+        pooled_output = self.dense(first_token_tensor)
+        pooled_output = self.activation(pooled_output)
+        return pooled_output
+
+
+class BertPredictionHeadTransform(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.dense = nn.Linear(config.hidden_size, config.hidden_size)
+        if isinstance(config.hidden_act, str):
+            self.transform_act_fn = ACT2FN[config.hidden_act]
+        else:
+            self.transform_act_fn = config.hidden_act
+        self.LayerNorm = nn.LayerNorm(config.hidden_size, eps=config.layer_norm_eps)
+
+    def forward(self, hidden_states):
+        hidden_states = self.dense(hidden_states)
+        hidden_states = self.transform_act_fn(hidden_states)
+        hidden_states = self.LayerNorm(hidden_states)
+        return hidden_states
+
+
+class BertLMPredictionHead(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.transform = BertPredictionHeadTransform(config)
+
+        # The output weights are the same as the input embeddings, but there is
+        # an output-only bias for each token.
+        self.decoder = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
+
+        self.bias = nn.Parameter(torch.zeros(config.vocab_size))
+
+        # Need a link between the two variables so that the bias is correctly resized with `resize_token_embeddings`
+        self.decoder.bias = self.bias
+
+    def forward(self, hidden_states):
+        hidden_states = self.transform(hidden_states)
+        hidden_states = self.decoder(hidden_states)
+        return hidden_states
+
+
+class BertOnlyMLMHead(nn.Module):
+    def __init__(self, config):
+        super().__init__()
+        self.predictions = BertLMPredictionHead(config)
+
+    def forward(self, sequence_output):
+        prediction_scores = self.predictions(sequence_output)
+        return prediction_scores
+
+
+class BertPreTrainedModel(PreTrainedModel):
+    """
+    An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained
+    models.
+    """
+
+    config_class = BertConfig
+    base_model_prefix = "bert"
+    _keys_to_ignore_on_load_missing = [r"position_ids"]
+
+    def _init_weights(self, module):
+        """ Initialize the weights """
+        if isinstance(module, (nn.Linear, nn.Embedding)):
+            # Slightly different from the TF version which uses truncated_normal for initialization
+            # cf https://github.com/pytorch/pytorch/pull/5617
+            module.weight.data.normal_(mean=0.0, std=self.config.initializer_range)
+        elif isinstance(module, nn.LayerNorm):
+            module.bias.data.zero_()
+            module.weight.data.fill_(1.0)
+        if isinstance(module, nn.Linear) and module.bias is not None:
+            module.bias.data.zero_()
+
+
+class BertModel(BertPreTrainedModel):
+    """
+    The model can behave as an encoder (with only self-attention) as well as a decoder, in which case a layer of
+    cross-attention is added between the self-attention layers, following the architecture described in `Attention is
+    all you need <https://arxiv.org/abs/1706.03762>`__ by Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit,
+    Llion Jones, Aidan N. Gomez, Lukasz Kaiser and Illia Polosukhin.
+    argument and :obj:`add_cross_attention` set to :obj:`True`; an :obj:`encoder_hidden_states` is then expected as an
+    input to the forward pass.
+    """
+
+    def __init__(self, config, add_pooling_layer=True):
+        super().__init__(config)
+        self.config = config
+
+        self.embeddings = BertEmbeddings(config)
+        
+        self.encoder = BertEncoder(config)
+
+        self.pooler = BertPooler(config) if add_pooling_layer else None
+
+        self.init_weights()
+ 
+
+    def get_input_embeddings(self):
+        return self.embeddings.word_embeddings
+
+    def set_input_embeddings(self, value):
+        self.embeddings.word_embeddings = value
+
+    def _prune_heads(self, heads_to_prune):
+        """
+        Prunes heads of the model. heads_to_prune: dict of {layer_num: list of heads to prune in this layer} See base
+        class PreTrainedModel
+        """
+        for layer, heads in heads_to_prune.items():
+            self.encoder.layer[layer].attention.prune_heads(heads)
+
+    
+    def get_extended_attention_mask(self, attention_mask: Tensor, input_shape: Tuple[int], device: device, is_decoder: bool) -> Tensor:
+        """
+        Makes broadcastable attention and causal masks so that future and masked tokens are ignored.
+        Arguments:
+            attention_mask (:obj:`torch.Tensor`):
+                Mask with ones indicating tokens to attend to, zeros for tokens to ignore.
+            input_shape (:obj:`Tuple[int]`):
+                The shape of the input to the model.
+            device: (:obj:`torch.device`):
+                The device of the input to the model.
+        Returns:
+            :obj:`torch.Tensor` The extended attention mask, with a the same dtype as :obj:`attention_mask.dtype`.
+        """
+        # We can provide a self-attention mask of dimensions [batch_size, from_seq_length, to_seq_length]
+        # ourselves in which case we just need to make it broadcastable to all heads.
+        if attention_mask.dim() == 3:
+            extended_attention_mask = attention_mask[:, None, :, :]
+        elif attention_mask.dim() == 2:
+            # Provided a padding mask of dimensions [batch_size, seq_length]
+            # - if the model is a decoder, apply a causal mask in addition to the padding mask
+            # - if the model is an encoder, make the mask broadcastable to [batch_size, num_heads, seq_length, seq_length]
+            if is_decoder:
+                batch_size, seq_length = input_shape
+
+                seq_ids = torch.arange(seq_length, device=device)
+                causal_mask = seq_ids[None, None, :].repeat(batch_size, seq_length, 1) <= seq_ids[None, :, None]
+                # in case past_key_values are used we need to add a prefix ones mask to the causal mask
+                # causal and attention masks must have same type with pytorch version < 1.3
+                causal_mask = causal_mask.to(attention_mask.dtype)
+   
+                if causal_mask.shape[1] < attention_mask.shape[1]:
+                    prefix_seq_len = attention_mask.shape[1] - causal_mask.shape[1]
+                    causal_mask = torch.cat(
+                        [
+                            torch.ones((batch_size, seq_length, prefix_seq_len), device=device, dtype=causal_mask.dtype),
+                            causal_mask,
+                        ],
+                        axis=-1,
+                    )                     
+
+                extended_attention_mask = causal_mask[:, None, :, :] * attention_mask[:, None, None, :]
+            else:
+                extended_attention_mask = attention_mask[:, None, None, :]
+        else:
+            raise ValueError(
+                "Wrong shape for input_ids (shape {}) or attention_mask (shape {})".format(
+                    input_shape, attention_mask.shape
+                )
+            )
+
+        # Since attention_mask is 1.0 for positions we want to attend and 0.0 for
+        # masked positions, this operation will create a tensor which is 0.0 for
+        # positions we want to attend and -10000.0 for masked positions.
+        # Since we are adding it to the raw scores before the softmax, this is
+        # effectively the same as removing these entirely.
+        extended_attention_mask = extended_attention_mask.to(dtype=self.dtype)  # fp16 compatibility
+        extended_attention_mask = (1.0 - extended_attention_mask) * -10000.0
+        return extended_attention_mask
+    
+    def forward(
+        self,
+        input_ids=None,
+        attention_mask=None,
+        position_ids=None,
+        head_mask=None,
+        inputs_embeds=None,
+        encoder_embeds=None,
+        encoder_hidden_states=None,
+        encoder_attention_mask=None,
+        past_key_values=None,
+        use_cache=None,
+        output_attentions=None,
+        output_hidden_states=None,
+        return_dict=None,
+        is_decoder=False,
+        mode='multimodal',
+    ):
+        r"""
+        encoder_hidden_states  (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
+            Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if
+            the model is configured as a decoder.
+        encoder_attention_mask (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
+            Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
+            the cross-attention if the model is configured as a decoder. Mask values selected in ``[0, 1]``:
+            - 1 for tokens that are **not masked**,
+            - 0 for tokens that are **masked**.
+        past_key_values (:obj:`tuple(tuple(torch.FloatTensor))` of length :obj:`config.n_layers` with each tuple having 4 tensors of shape :obj:`(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):
+            Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.
+            If :obj:`past_key_values` are used, the user can optionally input only the last :obj:`decoder_input_ids`
+            (those that don't have their past key value states given to this model) of shape :obj:`(batch_size, 1)`
+            instead of all :obj:`decoder_input_ids` of shape :obj:`(batch_size, sequence_length)`.
+        use_cache (:obj:`bool`, `optional`):
+            If set to :obj:`True`, :obj:`past_key_values` key value states are returned and can be used to speed up
+            decoding (see :obj:`past_key_values`).
+        """
+        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
+        output_hidden_states = (
+            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
+        )
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        if is_decoder:
+            use_cache = use_cache if use_cache is not None else self.config.use_cache
+        else:
+            use_cache = False
+
+        if input_ids is not None and inputs_embeds is not None:
+            raise ValueError("You cannot specify both input_ids and inputs_embeds at the same time")
+        elif input_ids is not None:
+            input_shape = input_ids.size()
+            batch_size, seq_length = input_shape
+            device = input_ids.device
+        elif inputs_embeds is not None:
+            input_shape = inputs_embeds.size()[:-1]
+            batch_size, seq_length = input_shape
+            device = inputs_embeds.device
+        elif encoder_embeds is not None:    
+            input_shape = encoder_embeds.size()[:-1]
+            batch_size, seq_length = input_shape 
+            device = encoder_embeds.device
+        else:
+            raise ValueError("You have to specify either input_ids or inputs_embeds or encoder_embeds")
+
+        # past_key_values_length
+        past_key_values_length = past_key_values[0][0].shape[2] if past_key_values is not None else 0
+
+        if attention_mask is None:
+            attention_mask = torch.ones(((batch_size, seq_length + past_key_values_length)), device=device)
+            
+        # We can provide a self-attention mask of dimensions [batch_size, from_seq_length, to_seq_length]
+        # ourselves in which case we just need to make it broadcastable to all heads.
+        extended_attention_mask: torch.Tensor = self.get_extended_attention_mask(attention_mask, input_shape, 
+                                                                                 device, is_decoder)
+
+        # If a 2D or 3D attention mask is provided for the cross-attention
+        # we need to make broadcastable to [batch_size, num_heads, seq_length, seq_length]
+        if encoder_hidden_states is not None:
+            if type(encoder_hidden_states) == list:
+                encoder_batch_size, encoder_sequence_length, _ = encoder_hidden_states[0].size()
+            else:
+                encoder_batch_size, encoder_sequence_length, _ = encoder_hidden_states.size()
+            encoder_hidden_shape = (encoder_batch_size, encoder_sequence_length)
+            
+            if type(encoder_attention_mask) == list:
+                encoder_extended_attention_mask = [self.invert_attention_mask(mask) for mask in encoder_attention_mask]
+            elif encoder_attention_mask is None:
+                encoder_attention_mask = torch.ones(encoder_hidden_shape, device=device)
+                encoder_extended_attention_mask = self.invert_attention_mask(encoder_attention_mask)
+            else:    
+                encoder_extended_attention_mask = self.invert_attention_mask(encoder_attention_mask)
+        else:
+            encoder_extended_attention_mask = None
+
+        # Prepare head mask if needed
+        # 1.0 in head_mask indicate we keep the head
+        # attention_probs has shape bsz x n_heads x N x N
+        # input head_mask has shape [num_heads] or [num_hidden_layers x num_heads]
+        # and head_mask is converted to shape [num_hidden_layers x batch x num_heads x seq_length x seq_length]
+        head_mask = self.get_head_mask(head_mask, self.config.num_hidden_layers)
+        
+        if encoder_embeds is None:
+            embedding_output = self.embeddings(
+                input_ids=input_ids,
+                position_ids=position_ids,
+                inputs_embeds=inputs_embeds,
+                past_key_values_length=past_key_values_length,
+            )
+        else:
+            embedding_output = encoder_embeds
+            
+        encoder_outputs = self.encoder(
+            embedding_output,
+            attention_mask=extended_attention_mask,
+            head_mask=head_mask,
+            encoder_hidden_states=encoder_hidden_states,
+            encoder_attention_mask=encoder_extended_attention_mask,
+            past_key_values=past_key_values,
+            use_cache=use_cache,
+            output_attentions=output_attentions,
+            output_hidden_states=output_hidden_states,
+            return_dict=return_dict,
+            mode=mode,
+        )
+        sequence_output = encoder_outputs[0]
+        pooled_output = self.pooler(sequence_output) if self.pooler is not None else None
+
+        if not return_dict:
+            return (sequence_output, pooled_output) + encoder_outputs[1:]
+
+        return BaseModelOutputWithPoolingAndCrossAttentions(
+            last_hidden_state=sequence_output,
+            pooler_output=pooled_output,
+            past_key_values=encoder_outputs.past_key_values,
+            hidden_states=encoder_outputs.hidden_states,
+            attentions=encoder_outputs.attentions,
+            cross_attentions=encoder_outputs.cross_attentions,
+        )
+
+
+
+class BertLMHeadModel(BertPreTrainedModel):
+
+    _keys_to_ignore_on_load_unexpected = [r"pooler"]
+    _keys_to_ignore_on_load_missing = [r"position_ids", r"predictions.decoder.bias"]
+
+    def __init__(self, config):
+        super().__init__(config)
+
+        self.bert = BertModel(config, add_pooling_layer=False)
+        self.cls = BertOnlyMLMHead(config)
+
+        self.init_weights()
+
+    def get_output_embeddings(self):
+        return self.cls.predictions.decoder
+
+    def set_output_embeddings(self, new_embeddings):
+        self.cls.predictions.decoder = new_embeddings
+
+    def forward(
+        self,
+        input_ids=None,
+        attention_mask=None,
+        position_ids=None,
+        head_mask=None,
+        inputs_embeds=None,
+        encoder_hidden_states=None,
+        encoder_attention_mask=None,
+        labels=None,
+        past_key_values=None,
+        use_cache=None,
+        output_attentions=None,
+        output_hidden_states=None,
+        return_dict=None,
+        return_logits=False,            
+        is_decoder=True,
+        reduction='mean',
+        mode='multimodal', 
+    ):
+        r"""
+        encoder_hidden_states  (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length, hidden_size)`, `optional`):
+            Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if
+            the model is configured as a decoder.
+        encoder_attention_mask (:obj:`torch.FloatTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
+            Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in
+            the cross-attention if the model is configured as a decoder. Mask values selected in ``[0, 1]``:
+            - 1 for tokens that are **not masked**,
+            - 0 for tokens that are **masked**.
+        labels (:obj:`torch.LongTensor` of shape :obj:`(batch_size, sequence_length)`, `optional`):
+            Labels for computing the left-to-right language modeling loss (next word prediction). Indices should be in
+            ``[-100, 0, ..., config.vocab_size]`` (see ``input_ids`` docstring) Tokens with indices set to ``-100`` are
+            ignored (masked), the loss is only computed for the tokens with labels n ``[0, ..., config.vocab_size]``
+        past_key_values (:obj:`tuple(tuple(torch.FloatTensor))` of length :obj:`config.n_layers` with each tuple having 4 tensors of shape :obj:`(batch_size, num_heads, sequence_length - 1, embed_size_per_head)`):
+            Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.
+            If :obj:`past_key_values` are used, the user can optionally input only the last :obj:`decoder_input_ids`
+            (those that don't have their past key value states given to this model) of shape :obj:`(batch_size, 1)`
+            instead of all :obj:`decoder_input_ids` of shape :obj:`(batch_size, sequence_length)`.
+        use_cache (:obj:`bool`, `optional`):
+            If set to :obj:`True`, :obj:`past_key_values` key value states are returned and can be used to speed up
+            decoding (see :obj:`past_key_values`).
+        Returns:
+        Example::
+            >>> from transformers import BertTokenizer, BertLMHeadModel, BertConfig
+            >>> import torch
+            >>> tokenizer = BertTokenizer.from_pretrained('bert-base-cased')
+            >>> config = BertConfig.from_pretrained("bert-base-cased")
+            >>> model = BertLMHeadModel.from_pretrained('bert-base-cased', config=config)
+            >>> inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
+            >>> outputs = model(**inputs)
+            >>> prediction_logits = outputs.logits
+        """
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+        if labels is not None:
+            use_cache = False
+
+        outputs = self.bert(
+            input_ids,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            head_mask=head_mask,
+            inputs_embeds=inputs_embeds,
+            encoder_hidden_states=encoder_hidden_states,
+            encoder_attention_mask=encoder_attention_mask,
+            past_key_values=past_key_values,
+            use_cache=use_cache,
+            output_attentions=output_attentions,
+            output_hidden_states=output_hidden_states,
+            return_dict=return_dict,
+            is_decoder=is_decoder,
+            mode=mode,
+        )
+        
+        sequence_output = outputs[0]
+        prediction_scores = self.cls(sequence_output)
+        
+        if return_logits:
+            return prediction_scores[:, :-1, :].contiguous()  
+
+        lm_loss = None
+        if labels is not None:
+            # we are doing next-token prediction; shift prediction scores and input ids by one
+            shifted_prediction_scores = prediction_scores[:, :-1, :].contiguous()
+            labels = labels[:, 1:].contiguous()
+            loss_fct = CrossEntropyLoss(reduction=reduction, label_smoothing=0.1) 
+            lm_loss = loss_fct(shifted_prediction_scores.view(-1, self.config.vocab_size), labels.view(-1))
+            if reduction=='none':
+                lm_loss = lm_loss.view(prediction_scores.size(0),-1).sum(1)               
+
+        if not return_dict:
+            output = (prediction_scores,) + outputs[2:]
+            return ((lm_loss,) + output) if lm_loss is not None else output
+
+        return CausalLMOutputWithCrossAttentions(
+            loss=lm_loss,
+            logits=prediction_scores,
+            past_key_values=outputs.past_key_values,
+            hidden_states=outputs.hidden_states,
+            attentions=outputs.attentions,
+            cross_attentions=outputs.cross_attentions,
+        )
+
+    def prepare_inputs_for_generation(self, input_ids, past=None, attention_mask=None, **model_kwargs):
+        input_shape = input_ids.shape
+        # if model is used as a decoder in encoder-decoder model, the decoder attention mask is created on the fly
+        if attention_mask is None:
+            attention_mask = input_ids.new_ones(input_shape)
+
+        # cut decoder_input_ids if past is used
+        if past is not None:
+            input_ids = input_ids[:, -1:]
+
+        return {
+            "input_ids": input_ids, 
+            "attention_mask": attention_mask, 
+            "past_key_values": past,
+            "encoder_hidden_states": model_kwargs.get("encoder_hidden_states", None),
+            "encoder_attention_mask": model_kwargs.get("encoder_attention_mask", None),
+            "is_decoder": True,
+        }
+
+    def _reorder_cache(self, past, beam_idx):
+        reordered_past = ()
+        for layer_past in past:
+            reordered_past += (tuple(past_state.index_select(0, beam_idx) for past_state in layer_past),)
+        return reordered_past

models/vit.py

@@ -0,0 +1,305 @@
+'''
+ * Copyright (c) 2022, salesforce.com, inc.
+ * All rights reserved.
+ * SPDX-License-Identifier: BSD-3-Clause
+ * For full license text, see LICENSE.txt file in the repo root or https://opensource.org/licenses/BSD-3-Clause
+ * By Junnan Li
+ * Based on timm code base
+ * https://github.com/rwightman/pytorch-image-models/tree/master/timm
+'''
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from functools import partial
+
+from timm.models.vision_transformer import _cfg, PatchEmbed
+from timm.models.registry import register_model
+from timm.models.layers import trunc_normal_, DropPath
+from timm.models.helpers import named_apply, adapt_input_conv
+
+from fairscale.nn.checkpoint.checkpoint_activations import checkpoint_wrapper
+
+class Mlp(nn.Module):
+    """ MLP as used in Vision Transformer, MLP-Mixer and related networks
+    """
+    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
+        super().__init__()
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        self.fc1 = nn.Linear(in_features, hidden_features)
+        self.act = act_layer()
+        self.fc2 = nn.Linear(hidden_features, out_features)
+        self.drop = nn.Dropout(drop)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        x = self.act(x)
+        x = self.drop(x)
+        x = self.fc2(x)
+        x = self.drop(x)
+        return x
+
+
+class Attention(nn.Module):
+    def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0.):
+        super().__init__()
+        self.num_heads = num_heads
+        head_dim = dim // num_heads
+        # NOTE scale factor was wrong in my original version, can set manually to be compat with prev weights
+        self.scale = qk_scale or head_dim ** -0.5
+        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
+        self.attn_drop = nn.Dropout(attn_drop)
+        self.proj = nn.Linear(dim, dim)
+        self.proj_drop = nn.Dropout(proj_drop)
+        self.attn_gradients = None
+        self.attention_map = None
+        
+    def save_attn_gradients(self, attn_gradients):
+        self.attn_gradients = attn_gradients
+        
+    def get_attn_gradients(self):
+        return self.attn_gradients
+    
+    def save_attention_map(self, attention_map):
+        self.attention_map = attention_map
+        
+    def get_attention_map(self):
+        return self.attention_map
+    
+    def forward(self, x, register_hook=False):
+        B, N, C = x.shape
+        qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
+        q, k, v = qkv[0], qkv[1], qkv[2]   # make torchscript happy (cannot use tensor as tuple)
+
+        attn = (q @ k.transpose(-2, -1)) * self.scale
+        attn = attn.softmax(dim=-1)
+        attn = self.attn_drop(attn)
+                
+        if register_hook:
+            self.save_attention_map(attn)
+            attn.register_hook(self.save_attn_gradients)        
+
+        x = (attn @ v).transpose(1, 2).reshape(B, N, C)
+        x = self.proj(x)
+        x = self.proj_drop(x)
+        return x
+
+
+class Block(nn.Module):
+
+    def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0.,
+                 drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm, use_grad_checkpointing=False):
+        super().__init__()
+        self.norm1 = norm_layer(dim)
+        self.attn = Attention(
+            dim, num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)
+        # NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
+        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
+        self.norm2 = norm_layer(dim)
+        mlp_hidden_dim = int(dim * mlp_ratio)
+        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
+
+        if use_grad_checkpointing:
+            self.attn = checkpoint_wrapper(self.attn)
+            self.mlp = checkpoint_wrapper(self.mlp)
+
+    def forward(self, x, register_hook=False):
+        x = x + self.drop_path(self.attn(self.norm1(x), register_hook=register_hook))
+        x = x + self.drop_path(self.mlp(self.norm2(x)))
+        return x
+
+
+class VisionTransformer(nn.Module):
+    """ Vision Transformer
+    A PyTorch impl of : `An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale`  -
+        https://arxiv.org/abs/2010.11929
+    """
+    def __init__(self, img_size=224, patch_size=16, in_chans=3, num_classes=1000, embed_dim=768, depth=12,
+                 num_heads=12, mlp_ratio=4., qkv_bias=True, qk_scale=None, representation_size=None,
+                 drop_rate=0., attn_drop_rate=0., drop_path_rate=0., norm_layer=None, 
+                 use_grad_checkpointing=False, ckpt_layer=0):
+        """
+        Args:
+            img_size (int, tuple): input image size
+            patch_size (int, tuple): patch size
+            in_chans (int): number of input channels
+            num_classes (int): number of classes for classification head
+            embed_dim (int): embedding dimension
+            depth (int): depth of transformer
+            num_heads (int): number of attention heads
+            mlp_ratio (int): ratio of mlp hidden dim to embedding dim
+            qkv_bias (bool): enable bias for qkv if True
+            qk_scale (float): override default qk scale of head_dim ** -0.5 if set
+            representation_size (Optional[int]): enable and set representation layer (pre-logits) to this value if set
+            drop_rate (float): dropout rate
+            attn_drop_rate (float): attention dropout rate
+            drop_path_rate (float): stochastic depth rate
+            norm_layer: (nn.Module): normalization layer
+        """
+        super().__init__()
+        self.num_features = self.embed_dim = embed_dim  # num_features for consistency with other models
+        norm_layer = norm_layer or partial(nn.LayerNorm, eps=1e-6)
+
+        self.patch_embed = PatchEmbed(
+            img_size=img_size, patch_size=patch_size, in_chans=in_chans, embed_dim=embed_dim)
+
+        num_patches = self.patch_embed.num_patches
+
+        self.cls_token = nn.Parameter(torch.zeros(1, 1, embed_dim))
+        self.pos_embed = nn.Parameter(torch.zeros(1, num_patches + 1, embed_dim))
+        self.pos_drop = nn.Dropout(p=drop_rate)
+
+        dpr = [x.item() for x in torch.linspace(0, drop_path_rate, depth)]  # stochastic depth decay rule
+        self.blocks = nn.ModuleList([
+            Block(
+                dim=embed_dim, num_heads=num_heads, mlp_ratio=mlp_ratio, qkv_bias=qkv_bias, qk_scale=qk_scale,
+                drop=drop_rate, attn_drop=attn_drop_rate, drop_path=dpr[i], norm_layer=norm_layer,
+                use_grad_checkpointing=(use_grad_checkpointing and i>=depth-ckpt_layer)
+            )
+            for i in range(depth)])
+        self.norm = norm_layer(embed_dim)
+
+        trunc_normal_(self.pos_embed, std=.02)
+        trunc_normal_(self.cls_token, std=.02)
+        self.apply(self._init_weights)
+
+    def _init_weights(self, m):
+        if isinstance(m, nn.Linear):
+            trunc_normal_(m.weight, std=.02)
+            if isinstance(m, nn.Linear) and m.bias is not None:
+                nn.init.constant_(m.bias, 0)
+        elif isinstance(m, nn.LayerNorm):
+            nn.init.constant_(m.bias, 0)
+            nn.init.constant_(m.weight, 1.0)
+
+    @torch.jit.ignore
+    def no_weight_decay(self):
+        return {'pos_embed', 'cls_token'}
+
+    def forward(self, x, register_blk=-1):
+        B = x.shape[0]
+        x = self.patch_embed(x)
+
+        cls_tokens = self.cls_token.expand(B, -1, -1)  # stole cls_tokens impl from Phil Wang, thanks
+        x = torch.cat((cls_tokens, x), dim=1)
+  
+        x = x + self.pos_embed[:,:x.size(1),:]
+        x = self.pos_drop(x)
+
+        for i,blk in enumerate(self.blocks):
+            x = blk(x, register_blk==i)
+        x = self.norm(x)
+        
+        return x
+
+    @torch.jit.ignore()
+    def load_pretrained(self, checkpoint_path, prefix=''):
+        _load_weights(self, checkpoint_path, prefix)
+
+
+@torch.no_grad()
+def _load_weights(model: VisionTransformer, checkpoint_path: str, prefix: str = ''):
+    """ Load weights from .npz checkpoints for official Google Brain Flax implementation
+    """
+    import numpy as np
+
+    def _n2p(w, t=True):
+        if w.ndim == 4 and w.shape[0] == w.shape[1] == w.shape[2] == 1:
+            w = w.flatten()
+        if t:
+            if w.ndim == 4:
+                w = w.transpose([3, 2, 0, 1])
+            elif w.ndim == 3:
+                w = w.transpose([2, 0, 1])
+            elif w.ndim == 2:
+                w = w.transpose([1, 0])
+        return torch.from_numpy(w)
+
+    w = np.load(checkpoint_path)
+    if not prefix and 'opt/target/embedding/kernel' in w:
+        prefix = 'opt/target/'
+
+    if hasattr(model.patch_embed, 'backbone'):
+        # hybrid
+        backbone = model.patch_embed.backbone
+        stem_only = not hasattr(backbone, 'stem')
+        stem = backbone if stem_only else backbone.stem
+        stem.conv.weight.copy_(adapt_input_conv(stem.conv.weight.shape[1], _n2p(w[f'{prefix}conv_root/kernel'])))
+        stem.norm.weight.copy_(_n2p(w[f'{prefix}gn_root/scale']))
+        stem.norm.bias.copy_(_n2p(w[f'{prefix}gn_root/bias']))
+        if not stem_only:
+            for i, stage in enumerate(backbone.stages):
+                for j, block in enumerate(stage.blocks):
+                    bp = f'{prefix}block{i + 1}/unit{j + 1}/'
+                    for r in range(3):
+                        getattr(block, f'conv{r + 1}').weight.copy_(_n2p(w[f'{bp}conv{r + 1}/kernel']))
+                        getattr(block, f'norm{r + 1}').weight.copy_(_n2p(w[f'{bp}gn{r + 1}/scale']))
+                        getattr(block, f'norm{r + 1}').bias.copy_(_n2p(w[f'{bp}gn{r + 1}/bias']))
+                    if block.downsample is not None:
+                        block.downsample.conv.weight.copy_(_n2p(w[f'{bp}conv_proj/kernel']))
+                        block.downsample.norm.weight.copy_(_n2p(w[f'{bp}gn_proj/scale']))
+                        block.downsample.norm.bias.copy_(_n2p(w[f'{bp}gn_proj/bias']))
+        embed_conv_w = _n2p(w[f'{prefix}embedding/kernel'])
+    else:
+        embed_conv_w = adapt_input_conv(
+            model.patch_embed.proj.weight.shape[1], _n2p(w[f'{prefix}embedding/kernel']))
+    model.patch_embed.proj.weight.copy_(embed_conv_w)
+    model.patch_embed.proj.bias.copy_(_n2p(w[f'{prefix}embedding/bias']))
+    model.cls_token.copy_(_n2p(w[f'{prefix}cls'], t=False))
+    pos_embed_w = _n2p(w[f'{prefix}Transformer/posembed_input/pos_embedding'], t=False)
+    if pos_embed_w.shape != model.pos_embed.shape:
+        pos_embed_w = resize_pos_embed(  # resize pos embedding when different size from pretrained weights
+            pos_embed_w, model.pos_embed, getattr(model, 'num_tokens', 1), model.patch_embed.grid_size)
+    model.pos_embed.copy_(pos_embed_w)
+    model.norm.weight.copy_(_n2p(w[f'{prefix}Transformer/encoder_norm/scale']))
+    model.norm.bias.copy_(_n2p(w[f'{prefix}Transformer/encoder_norm/bias']))
+#     if isinstance(model.head, nn.Linear) and model.head.bias.shape[0] == w[f'{prefix}head/bias'].shape[-1]:
+#         model.head.weight.copy_(_n2p(w[f'{prefix}head/kernel']))
+#         model.head.bias.copy_(_n2p(w[f'{prefix}head/bias']))
+#     if isinstance(getattr(model.pre_logits, 'fc', None), nn.Linear) and f'{prefix}pre_logits/bias' in w:
+#         model.pre_logits.fc.weight.copy_(_n2p(w[f'{prefix}pre_logits/kernel']))
+#         model.pre_logits.fc.bias.copy_(_n2p(w[f'{prefix}pre_logits/bias']))
+    for i, block in enumerate(model.blocks.children()):
+        block_prefix = f'{prefix}Transformer/encoderblock_{i}/'
+        mha_prefix = block_prefix + 'MultiHeadDotProductAttention_1/'
+        block.norm1.weight.copy_(_n2p(w[f'{block_prefix}LayerNorm_0/scale']))
+        block.norm1.bias.copy_(_n2p(w[f'{block_prefix}LayerNorm_0/bias']))
+        block.attn.qkv.weight.copy_(torch.cat([
+            _n2p(w[f'{mha_prefix}{n}/kernel'], t=False).flatten(1).T for n in ('query', 'key', 'value')]))
+        block.attn.qkv.bias.copy_(torch.cat([
+            _n2p(w[f'{mha_prefix}{n}/bias'], t=False).reshape(-1) for n in ('query', 'key', 'value')]))
+        block.attn.proj.weight.copy_(_n2p(w[f'{mha_prefix}out/kernel']).flatten(1))
+        block.attn.proj.bias.copy_(_n2p(w[f'{mha_prefix}out/bias']))
+        for r in range(2):
+            getattr(block.mlp, f'fc{r + 1}').weight.copy_(_n2p(w[f'{block_prefix}MlpBlock_3/Dense_{r}/kernel']))
+            getattr(block.mlp, f'fc{r + 1}').bias.copy_(_n2p(w[f'{block_prefix}MlpBlock_3/Dense_{r}/bias']))
+        block.norm2.weight.copy_(_n2p(w[f'{block_prefix}LayerNorm_2/scale']))
+        block.norm2.bias.copy_(_n2p(w[f'{block_prefix}LayerNorm_2/bias']))
+
+
+def interpolate_pos_embed(pos_embed_checkpoint, visual_encoder):        
+    # interpolate position embedding
+    embedding_size = pos_embed_checkpoint.shape[-1]
+    num_patches = visual_encoder.patch_embed.num_patches
+    num_extra_tokens = visual_encoder.pos_embed.shape[-2] - num_patches
+    # height (== width) for the checkpoint position embedding
+    orig_size = int((pos_embed_checkpoint.shape[-2] - num_extra_tokens) ** 0.5)
+    # height (== width) for the new position embedding
+    new_size = int(num_patches ** 0.5)
+
+    if orig_size!=new_size:
+        # class_token and dist_token are kept unchanged
+        extra_tokens = pos_embed_checkpoint[:, :num_extra_tokens]
+        # only the position tokens are interpolated
+        pos_tokens = pos_embed_checkpoint[:, num_extra_tokens:]
+        pos_tokens = pos_tokens.reshape(-1, orig_size, orig_size, embedding_size).permute(0, 3, 1, 2)
+        pos_tokens = torch.nn.functional.interpolate(
+            pos_tokens, size=(new_size, new_size), mode='bicubic', align_corners=False)
+        pos_tokens = pos_tokens.permute(0, 2, 3, 1).flatten(1, 2)
+        new_pos_embed = torch.cat((extra_tokens, pos_tokens), dim=1)
+        print('reshape position embedding from %d to %d'%(orig_size ** 2,new_size ** 2))
+        
+        return new_pos_embed    
+    else:
+        return pos_embed_checkpoint

pipeline.py

@@ -0,0 +1,55 @@
+from typing import  Dict, List, Any
+from PIL import Image
+import requests
+import torch
+import base64
+import os
+from io import BytesIO
+from models.blip_feature_extractor import blip_feature_extractor
+from torchvision import transforms
+from torchvision.transforms.functional import InterpolationMode
+
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+class PreTrainedPipeline():
+    def __init__(self, path=""):
+        # load the optimized model
+        self.model_path = os.path.join(path,'model_large_retrieval_coco.pth') 
+        self.model = blip_feature_extractor(
+            pretrained=self.model_path, 
+            image_size=384, 
+            vit='large',
+            med_config=os.path.join(path, 'configs/med_config.json')
+        )
+        self.model.eval()
+        self.model = self.model.to(device)
+        
+        image_size = 384
+        self.transform = transforms.Compose([
+            transforms.Resize((image_size,image_size),interpolation=InterpolationMode.BICUBIC),
+            transforms.ToTensor(),
+            transforms.Normalize((0.48145466, 0.4578275, 0.40821073), (0.26862954, 0.26130258, 0.27577711))
+            ]) 
+     
+
+
+    def __call__(self, data: Any) -> Dict[str, List[float]]:
+        """
+        Args:
+            data (:obj:):
+                includes the input data and the parameters for the inference.
+        Return:
+            A :obj:`dict`:. The object returned should be a dict like {"feature_vector": [0.6331314444541931,0.8802216053009033,...,-0.7866355180740356,]} containing :
+                - "feature_vector": A list of floats corresponding to the image embedding.
+        """
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", {"mode": "image"})
+        
+        # decode base64 image to PIL
+        image = Image.open(BytesIO(base64.b64decode(inputs['image'])))
+        image = self.transform(image).unsqueeze(0).to(device)   
+        text=""
+        with torch.no_grad():
+            feature_vector = self.model(image, text, mode=parameters["mode"])[0,0].tolist()
+        # postprocess the prediction
+        return {"feature_vector": feature_vector}

requirements.txt

@@ -0,0 +1,4 @@
+timm
+fairscale
+requests
+Pillow