File size: 17,047 Bytes
a43ef32 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 |
"""
Copyright (c) 2023, salesforce.com, inc.
All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
For full license text, see the LICENSE file in the repo root or https://opensource.org/licenses/BSD-3-Clause
"""
import contextlib
import logging
import os
import time
import datetime
import torch
import torch.nn as nn
import torch.distributed as dist
import torch.nn.functional as F
import lavis.common.dist_utils as dist_utils
from lavis.common.dist_utils import download_cached_file
from lavis.common.utils import is_url
from lavis.common.logger import MetricLogger
from lavis.models.base_model import BaseModel
from lavis.models.blip2_models.Qformer import BertConfig, BertLMHeadModel
from lavis.models.eva_vit import create_eva_vit_g
from lavis.models.clip_vit import create_clip_vit_L
from transformers import BertTokenizer
class Blip2Base(BaseModel):
@classmethod
def init_tokenizer(cls, truncation_side="right"):
tokenizer = BertTokenizer.from_pretrained("bert-base-uncased", truncation_side=truncation_side)
tokenizer.add_special_tokens({"bos_token": "[DEC]"})
return tokenizer
def maybe_autocast(self, dtype=torch.float16):
# if on cpu, don't use autocast
# if on gpu, use autocast with dtype if provided, otherwise use torch.float16
enable_autocast = self.device != torch.device("cpu")
if enable_autocast:
return torch.cuda.amp.autocast(dtype=dtype)
else:
return contextlib.nullcontext()
@classmethod
def init_Qformer(cls, num_query_token, vision_width, cross_attention_freq=2):
encoder_config = BertConfig.from_pretrained("bert-base-uncased")
encoder_config.encoder_width = vision_width
# insert cross-attention layer every other block
encoder_config.add_cross_attention = True
encoder_config.cross_attention_freq = cross_attention_freq
encoder_config.query_length = num_query_token
Qformer = BertLMHeadModel.from_pretrained(
"bert-base-uncased", config=encoder_config
)
query_tokens = nn.Parameter(
torch.zeros(1, num_query_token, encoder_config.hidden_size)
)
query_tokens.data.normal_(mean=0.0, std=encoder_config.initializer_range)
return Qformer, query_tokens
def init_vision_encoder(
self, model_name, img_size, drop_path_rate, use_grad_checkpoint, precision
):
assert model_name in [
"eva_clip_g",
"eva2_clip_L",
"clip_L",
], "vit model must be eva_clip_g, eva2_clip_L or clip_L"
if model_name == "eva_clip_g":
visual_encoder = create_eva_vit_g(
img_size, drop_path_rate, use_grad_checkpoint, precision
)
# elif model_name == "eva2_clip_L":
# visual_encoder = create_eva2_vit_L(
# img_size, drop_path_rate, use_grad_checkpoint, precision
# )
elif model_name == "clip_L":
visual_encoder = create_clip_vit_L(img_size, use_grad_checkpoint, precision)
ln_vision = LayerNorm(visual_encoder.num_features)
self.vit_name = model_name
return visual_encoder, ln_vision
def load_from_pretrained(self, 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"]
msg = self.load_state_dict(state_dict, strict=False)
# logging.info("Missing keys {}".format(msg.missing_keys))
logging.info("load checkpoint from %s" % url_or_filename)
return msg
def get_optimizer_params(self, weight_decay, lr_scale=1):
vit_num_layers = self.visual_encoder.get_num_layer()
lr_scales = list(lr_scale ** (vit_num_layers + 1 - i) for i in range(vit_num_layers + 2))
parameter_group_names = {}
parameter_group_vars = {}
for name, param in self.named_parameters():
if not param.requires_grad:
continue # frozen weights
if len(param.shape) == 1 or name.endswith(".bias"):
group_name = "no_decay"
this_weight_decay = 0.
else:
group_name = "decay"
this_weight_decay = weight_decay
if 'visual_encoder' in name:
layer_id = self.visual_encoder.get_num_layer(name.replace('visual_encoder.',''))
group_name = "vit_layer_%d_%s" % (layer_id, group_name)
else:
layer_id = None
if group_name not in parameter_group_names:
if layer_id is not None:
scale = lr_scales[layer_id]
else:
scale = 1
parameter_group_names[group_name] = {
"weight_decay": this_weight_decay,
"params": [],
"lr_scale": scale
}
parameter_group_vars[group_name] = {
"weight_decay": this_weight_decay,
"params": [],
"lr_scale": scale
}
parameter_group_vars[group_name]["params"].append(param)
parameter_group_names[group_name]["params"].append(name)
# import json
# print("Param groups = %s" % json.dumps(parameter_group_names, indent=2))
optim_params = list(parameter_group_vars.values())
return optim_params
def _lemmatize(self, answers):
def apply(answer):
doc = self.lemmatizer(answer)
words = []
for token in doc:
if token.pos_ in ["NOUN", "VERB"]:
words.append(token.lemma_)
else:
words.append(token.text)
answer = " ".join(words)
return answer
return [apply(answer) for answer in answers]
@property
def lemmatizer(self):
if self._lemmatizer is None:
try:
import spacy
self._lemmatizer = spacy.load("en_core_web_sm")
except ImportError:
logging.error(
"""
Please install spacy and en_core_web_sm model to apply lemmatization.
python -m spacy download en_core_web_sm
OR
import spacy.cli
spacy.cli.download("en_core_web_sm")
"""
)
exit(1)
return self._lemmatizer
class Blip2ProteinBase(BaseModel):
@classmethod
def init_tokenizer(cls, truncation_side="right"):
tokenizer = BertTokenizer.from_pretrained("bert-base-uncased", truncation_side=truncation_side)
tokenizer.add_special_tokens({"bos_token": "[DEC]"})
return tokenizer
def maybe_autocast(self, dtype=torch.float16):
# if on cpu, don't use autocast
# if on gpu, use autocast with dtype if provided, otherwise use torch.float16
enable_autocast = self.device != torch.device("cpu")
if enable_autocast:
return torch.cuda.amp.autocast(dtype=dtype)
else:
return contextlib.nullcontext()
@classmethod
def init_Qformer(cls, num_query_token, vision_width, cross_attention_freq=2):
encoder_config = BertConfig.from_pretrained("bert-base-uncased")
encoder_config.encoder_width = vision_width
# insert cross-attention layer every other block
encoder_config.add_cross_attention = True
encoder_config.cross_attention_freq = cross_attention_freq
encoder_config.query_length = num_query_token
Qformer = BertLMHeadModel.from_pretrained("bert-base-uncased", config=encoder_config)
query_tokens = nn.Parameter(
torch.zeros(1, num_query_token, encoder_config.hidden_size)
)
query_tokens.data.normal_(mean=0.0, std=encoder_config.initializer_range)
return Qformer, query_tokens
def load_from_pretrained(self, 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"]
msg = self.load_state_dict(state_dict, strict=False)
# logging.info("Missing keys {}".format(msg.missing_keys))
logging.info("load checkpoint from %s" % url_or_filename)
return msg
def get_optimizer_params(self, weight_decay, lr_scale=1):
try:
vit_num_layers = self.ln_vision.num_layers
except:
print('Use pre computing embedding instead of ln_vision model')
vit_num_layers = 33
lr_scales = list(lr_scale ** (vit_num_layers + 1 - i) for i in range(vit_num_layers + 2))
parameter_group_names = {}
parameter_group_vars = {}
for name, param in self.named_parameters():
if not param.requires_grad:
continue # frozen weights
if len(param.shape) == 1 or name.endswith(".bias"):
group_name = "no_decay"
this_weight_decay = 0.
else:
group_name = "decay"
this_weight_decay = weight_decay
# if 'visual_encoder' in name:
# layer_id = self.visual_encoder.get_num_layer(name.replace('visual_encoder.',''))
# group_name = "vit_layer_%d_%s" % (layer_id, group_name)
# else:
# layer_id = None
if group_name not in parameter_group_names:
# if layer_id is not None:
# scale = lr_scales[layer_id]
# else:
# scale = 1
scale = 1
parameter_group_names[group_name] = {
"weight_decay": this_weight_decay,
"params": [],
"lr_scale": scale
}
parameter_group_vars[group_name] = {
"weight_decay": this_weight_decay,
"params": [],
"lr_scale": scale
}
parameter_group_vars[group_name]["params"].append(param)
parameter_group_names[group_name]["params"].append(name)
# import json
# print("Param groups = %s" % json.dumps(parameter_group_names, indent=2))
optim_params = list(parameter_group_vars.values())
return optim_params
def _lemmatize(self, answers):
def apply(answer):
doc = self.lemmatizer(answer)
words = []
for token in doc:
if token.pos_ in ["NOUN", "VERB"]:
words.append(token.lemma_)
else:
words.append(token.text)
answer = " ".join(words)
return answer
return [apply(answer) for answer in answers]
@property
def lemmatizer(self):
if self._lemmatizer is None:
try:
import spacy
self._lemmatizer = spacy.load("en_core_web_sm")
except ImportError:
logging.error(
"""
Please install spacy and en_core_web_sm model to apply lemmatization.
python -m spacy download en_core_web_sm
OR
import spacy.cli
spacy.cli.download("en_core_web_sm")
"""
)
exit(1)
return self._lemmatizer
def disabled_train(self, mode=True):
"""Overwrite model.train with this function to make sure train/eval mode
does not change anymore."""
return self
class LayerNorm(nn.LayerNorm):
"""Subclass torch's LayerNorm to handle fp16."""
def forward(self, x: torch.Tensor):
orig_type = x.dtype
ret = super().forward(x.type(torch.float32))
return ret.type(orig_type)
def compute_sim_matrix(model, data_loader, **kwargs):
k_test = kwargs.pop("k_test")
metric_logger = MetricLogger(delimiter=" ")
header = "Evaluation:"
logging.info("Computing features for evaluation...")
start_time = time.time()
texts = data_loader.dataset.text
num_text = len(texts)
text_bs = 256
text_ids = []
text_embeds = []
text_atts = []
for i in range(0, num_text, text_bs):
text = texts[i : min(num_text, i + text_bs)]
text_input = model.tokenizer(
text,
padding="max_length",
truncation=True,
max_length=35,
return_tensors="pt",
).to(model.device)
text_feat = model.forward_text(text_input)
text_embed = F.normalize(model.text_proj(text_feat))
text_embeds.append(text_embed)
text_ids.append(text_input.input_ids)
text_atts.append(text_input.attention_mask)
text_embeds = torch.cat(text_embeds, dim=0)
text_ids = torch.cat(text_ids, dim=0)
text_atts = torch.cat(text_atts, dim=0)
vit_feats = []
image_embeds = []
for samples in data_loader:
image = samples["image"]
image = image.to(model.device)
image_feat, vit_feat = model.forward_image(image)
image_embed = model.vision_proj(image_feat)
image_embed = F.normalize(image_embed, dim=-1)
vit_feats.append(vit_feat.cpu())
image_embeds.append(image_embed)
vit_feats = torch.cat(vit_feats, dim=0)
image_embeds = torch.cat(image_embeds, dim=0)
sims_matrix = []
for image_embed in image_embeds:
sim_q2t = image_embed @ text_embeds.t()
sim_i2t, _ = sim_q2t.max(0)
sims_matrix.append(sim_i2t)
sims_matrix = torch.stack(sims_matrix, dim=0)
score_matrix_i2t = torch.full(
(len(data_loader.dataset.image), len(texts)), -100.0
).to(model.device)
num_tasks = dist_utils.get_world_size()
rank = dist_utils.get_rank()
step = sims_matrix.size(0) // num_tasks + 1
start = rank * step
end = min(sims_matrix.size(0), start + step)
for i, sims in enumerate(
metric_logger.log_every(sims_matrix[start:end], 50, header)
):
topk_sim, topk_idx = sims.topk(k=k_test, dim=0)
image_inputs = vit_feats[start + i].repeat(k_test, 1, 1).to(model.device)
score = model.compute_itm(
image_inputs=image_inputs,
text_ids=text_ids[topk_idx],
text_atts=text_atts[topk_idx],
).float()
score_matrix_i2t[start + i, topk_idx] = score + topk_sim
sims_matrix = sims_matrix.t()
score_matrix_t2i = torch.full(
(len(texts), len(data_loader.dataset.image)), -100.0
).to(model.device)
step = sims_matrix.size(0) // num_tasks + 1
start = rank * step
end = min(sims_matrix.size(0), start + step)
for i, sims in enumerate(
metric_logger.log_every(sims_matrix[start:end], 50, header)
):
topk_sim, topk_idx = sims.topk(k=k_test, dim=0)
image_inputs = vit_feats[topk_idx.cpu()].to(model.device)
score = model.compute_itm(
image_inputs=image_inputs,
text_ids=text_ids[start + i].repeat(k_test, 1),
text_atts=text_atts[start + i].repeat(k_test, 1),
).float()
score_matrix_t2i[start + i, topk_idx] = score + topk_sim
if dist_utils.is_dist_avail_and_initialized():
dist.barrier()
torch.distributed.all_reduce(
score_matrix_i2t, op=torch.distributed.ReduceOp.SUM
)
torch.distributed.all_reduce(
score_matrix_t2i, op=torch.distributed.ReduceOp.SUM
)
total_time = time.time() - start_time
total_time_str = str(datetime.timedelta(seconds=int(total_time)))
logging.info("Evaluation time {}".format(total_time_str))
return score_matrix_i2t.cpu().numpy(), score_matrix_t2i.cpu().numpy()
|