Spaces:
Runtime error
Runtime error
File size: 6,738 Bytes
50d1ff1 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 |
import os
import warnings
from PIL import Image
from torchvision import transforms
from torchvision.transforms import InterpolationMode
warnings.filterwarnings("ignore")
from models.vit import VisionTransformer, interpolate_pos_embed
from models.med import BertConfig, BertModel, BertLMHeadModel
from transformers import BertTokenizer, CLIPConfig
from models.modeling_clip import CLIPModel, CLIPVisionModel, CLIPVisionConfig
import torch
from torch import nn
import torch.nn.functional as F
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='[DEC]',
):
super().__init__()
self.visual_encoder, vision_width = create_vit(vit, image_size, vit_grad_ckpt, vit_ckpt_layer, 0)
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=False)
captions.append(caption[len(self.prompt):])
return captions
def init_tokenizer():
tokenizer = BertTokenizer.from_pretrained('resources/bert-large-chinese', do_lower_case=True)
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', 'large_v2'], "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
)
elif vit == 'large_v2':
vision_width = 1024
clip_config = CLIPConfig.from_pretrained('resources/clip_vit_large_patch14')
visual_encoder = CLIPVisionModel(clip_config)
return visual_encoder, vision_width
def load_image(image, image_size, device):
raw_image = Image.open(str(image)).convert('RGB')
w, h = raw_image.size
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))
])
image = transform(raw_image).unsqueeze(0).to(device)
return image
|