Spaces:
Runtime error
Runtime error
File size: 2,268 Bytes
f0e9666 |
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 |
# Copyright (c) Alibaba, Inc. and its affiliates.
import os
import numpy as np
import open_clip
import torch
import torch.nn as nn
import torchvision.transforms as T
class FrozenOpenCLIPEmbedder(nn.Module):
"""
Uses the OpenCLIP transformer encoder for text
"""
LAYERS = ['last', 'penultimate']
def __init__(self,
pretrained='laion2b_s32b_b79k',
arch='ViT-H-14',
device='cuda',
max_length=77,
freeze=True,
layer='penultimate'):
super().__init__()
assert layer in self.LAYERS
model, _, _ = open_clip.create_model_and_transforms(arch, device=torch.device('cpu'), pretrained=pretrained)
del model.visual
self.model = model
self.device = device
self.max_length = max_length
if freeze:
self.freeze()
self.layer = layer
if self.layer == 'last':
self.layer_idx = 0
elif self.layer == 'penultimate':
self.layer_idx = 1
else:
raise NotImplementedError()
def freeze(self):
self.model = self.model.eval()
for param in self.parameters():
param.requires_grad = False
def forward(self, text):
tokens = open_clip.tokenize(text)
z = self.encode_with_transformer(tokens.to(self.device))
return z
def encode_with_transformer(self, text):
x = self.model.token_embedding(text)
x = x + self.model.positional_embedding
x = x.permute(1, 0, 2)
x = self.text_transformer_forward(x, attn_mask=self.model.attn_mask)
x = x.permute(1, 0, 2)
x = self.model.ln_final(x)
return x
def text_transformer_forward(self, x: torch.Tensor, attn_mask=None):
for i, r in enumerate(self.model.transformer.resblocks):
if i == len(self.model.transformer.resblocks) - self.layer_idx:
break
if self.model.transformer.grad_checkpointing and not torch.jit.is_scripting(
):
x = checkpoint(r, x, attn_mask)
else:
x = r(x, attn_mask=attn_mask)
return x
def encode(self, text):
return self(text) |