File size: 5,997 Bytes
5a04e59 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 |
'''
* 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
|