File size: 12,554 Bytes
65fb4ac | 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 | import csv
import math
import os
from functools import partial
import numpy as np
import torch
import torch.nn.functional as F
import transformers
from torch.utils.data import DataLoader
from configs import args
from datasets import REFAVS
from decoder_invariance_check import build_model, set_seed
from load_model import collate_fn, dict_to_cuda
def make_loader(tokenizer):
dataset = REFAVS(args.eval_split, args, tokenizer, input_type="refer")
return DataLoader(
dataset,
batch_size=1,
shuffle=False,
num_workers=0,
collate_fn=partial(collate_fn, tokenizer=tokenizer),
)
def build_tokenizer():
tokenizer = transformers.AutoTokenizer.from_pretrained(
args.mllm,
cache_dir=None,
model_max_length=2048,
padding_side="right",
use_fast=False,
)
tokenizer.pad_token = tokenizer.unk_token
tokenizer.add_tokens("[SEG]")
seg_token_idx = tokenizer("[SEG]", add_special_tokens=False).input_ids[0]
return tokenizer, seg_token_idx
def get_q(model, batch):
with torch.cuda.amp.autocast(dtype=torch.bfloat16):
output = model.forward(
images=batch["images"],
images_clip=batch["images_clip"],
audio_features=batch["audio_feats"],
image_features=batch["image_feats"],
input_ids=batch["input_ids"],
labels=batch["labels"],
attention_masks=batch["attention_masks"],
masks_list=batch["masks"],
resize_list=batch["resizes"],
orgsize_list=batch["orgsizes"],
conversation_list=batch["convs"],
refs_num=batch["refs_num"],
fids=batch["fids"],
vids=batch["vids"],
contrast=args.ct_weight,
ref_ids=batch["ref_ids"],
inference=True,
)
return output["seg_embeddings"][0][0].float()
def decode_low_res(model, batch, q):
visual_model = model.get_model().visual_model
sparse, dense = visual_model.prompt_encoder(
points=None,
boxes=None,
masks=None,
text_embeds=q.view(1, 1, -1).to(next(visual_model.parameters()).dtype),
)
sparse = sparse.to(q.dtype)
dense = dense.to(q.dtype)
with torch.cuda.amp.autocast(dtype=torch.bfloat16):
low_res_masks, iou_predictions = visual_model.mask_decoder(
image_embeddings=batch["image_feats"][0],
image_pe=visual_model.prompt_encoder.get_dense_pe(),
sparse_prompt_embeddings=sparse,
dense_prompt_embeddings=dense,
multimask_output=False,
)
return low_res_masks.float(), iou_predictions.float().squeeze(-1)
def masks_to_64(mask_logits_or_binary):
if mask_logits_or_binary.ndim == 3:
mask_logits_or_binary = mask_logits_or_binary.unsqueeze(1)
return F.interpolate(
mask_logits_or_binary.float(),
size=(64, 64),
mode="bilinear",
align_corners=False,
).clamp(0.0, 1.0)
def d2_scores(image_embeddings, mask64, q, beta):
feats = image_embeddings.float()
if mask64.shape[0] != feats.shape[0]:
raise ValueError(f"Mask/frame mismatch: {mask64.shape} vs {feats.shape}")
q = F.normalize(q.float().view(1, -1), dim=-1)
mask = mask64.float()
comp = 1.0 - mask
z_in = (feats * mask).sum(dim=(2, 3)) / mask.sum(dim=(2, 3)).clamp_min(1e-6)
z_out = (feats * comp).sum(dim=(2, 3)) / comp.sum(dim=(2, 3)).clamp_min(1e-6)
z_in = F.normalize(z_in, dim=-1)
z_out = F.normalize(z_out, dim=-1)
return (z_in @ q.T).squeeze(-1) - beta * (z_out @ q.T).squeeze(-1)
def frame_iou(pred_logits, gt_masks):
pred = (torch.sigmoid(pred_logits.float()) > 0.4).float()
gt = gt_masks.float()
if pred.ndim == 4:
pred = pred.squeeze(1)
inter = (pred * gt).sum(dim=(1, 2))
union = torch.maximum(pred, gt).sum(dim=(1, 2))
num_pixels = pred.shape[-1] * pred.shape[-2]
no_obj = gt.sum(dim=(1, 2)) == 0
inter_no_obj = ((1.0 - pred) * (1.0 - gt)).sum(dim=(1, 2))
inter = torch.where(no_obj, inter_no_obj, inter)
union = torch.where(no_obj, torch.full_like(union, float(num_pixels)), union)
return inter / union.clamp_min(1e-7)
def frame_fscore_proxy(pred_logits, gt_masks):
pred = (torch.sigmoid(pred_logits.float()) > 0.4).float()
gt = gt_masks.float()
if pred.ndim == 4:
pred = pred.squeeze(1)
tp = (pred * gt).sum(dim=(1, 2))
precision = tp / pred.sum(dim=(1, 2)).clamp_min(1e-7)
recall = tp / gt.sum(dim=(1, 2)).clamp_min(1e-7)
beta2 = 0.3
fscore = (1 + beta2) * precision * recall / (beta2 * precision + recall).clamp_min(1e-7)
no_obj = gt.sum(dim=(1, 2)) == 0
return torch.where(no_obj, torch.zeros_like(fscore), fscore)
def parse_betas():
raw = os.environ.get("D2_BETAS", "0.5")
return [float(x.strip()) for x in raw.split(",") if x.strip()]
def collect_q_pool(model, tokenizer, limit):
q_pool = []
loader = make_loader(tokenizer)
for sample_idx, batch in enumerate(loader):
if sample_idx >= limit:
break
batch = dict_to_cuda(batch)
q = get_q(model, batch)
q_pool.append(
{
"sample_idx": sample_idx,
"vid": batch["vids"][0],
"ref": batch["refs"][0][0],
"fid": int(batch["fids"][0][0]),
"q": q.cpu(),
}
)
print(f"Collected q {sample_idx}: vid={q_pool[-1]['vid']} ref={q_pool[-1]['ref']}")
if not q_pool:
raise RuntimeError("No q vectors collected. Is the selected split empty?")
return q_pool
def choose_shuffled_idx(sample_idx, q_pool):
if len(q_pool) <= 1:
return None
return (sample_idx + 1) % len(q_pool)
def choose_wrong_ref_idx(sample_idx, q_pool):
current = q_pool[sample_idx]
for item in q_pool:
if item["sample_idx"] == sample_idx:
continue
if item["vid"] == current["vid"] and item["fid"] != current["fid"]:
return item["sample_idx"]
for item in q_pool:
if item["sample_idx"] == sample_idx:
continue
if item["vid"] == current["vid"] and item["ref"] != current["ref"]:
return item["sample_idx"]
return None
def run_d2(model, tokenizer, q_pool, betas, limit):
rows = []
loader = make_loader(tokenizer)
q_lookup = {item["sample_idx"]: item for item in q_pool}
generator = torch.Generator(device="cuda")
generator.manual_seed(1234)
for sample_idx, batch in enumerate(loader):
if sample_idx >= limit:
break
batch = dict_to_cuda(batch)
item = q_lookup[sample_idx]
real_q = item["q"].cuda()
low_res_masks, iou_predictions = decode_low_res(model, batch, real_q)
pred_mask64 = masks_to_64(torch.sigmoid(low_res_masks))
gt_masks = batch["masks"][0][0].float()
gt_mask64 = masks_to_64(gt_masks)
image_embeddings = batch["image_feats"][0].float()
pred_logits_hr = model.get_model().visual_model.postprocess_masks(
low_res_masks.to(batch["image_feats"][0].dtype),
input_size=batch["resizes"][0],
original_size=batch["orgsizes"][0],
).squeeze(1)
frame_ious = frame_iou(pred_logits_hr, gt_masks)
frame_fscores = frame_fscore_proxy(pred_logits_hr, gt_masks)
pred_area = (torch.sigmoid(pred_logits_hr.float()) > 0.4).float().mean(dim=(1, 2))
gt_area = gt_masks.float().mean(dim=(1, 2))
shuffled_idx = choose_shuffled_idx(sample_idx, q_pool)
wrong_ref_idx = choose_wrong_ref_idx(sample_idx, q_pool)
q_controls = [
("real", real_q, sample_idx),
("random", torch.randn(real_q.shape, device=real_q.device, generator=generator), None),
]
if shuffled_idx is not None:
q_controls.append(("shuffled", q_lookup[shuffled_idx]["q"].cuda(), shuffled_idx))
if wrong_ref_idx is not None:
q_controls.append(("wrong_ref", q_lookup[wrong_ref_idx]["q"].cuda(), wrong_ref_idx))
for beta in betas:
for q_type, q, q_source_idx in q_controls:
pred_scores = d2_scores(image_embeddings, pred_mask64, q, beta)
gt_scores = d2_scores(image_embeddings, gt_mask64, q, beta)
base_info = {
"sample_idx": sample_idx,
"vid": item["vid"],
"ref": item["ref"],
"fid": item["fid"],
"split": args.eval_split,
"frame_iou": math.nan,
"frame_fscore_proxy": math.nan,
"iou_pred": math.nan,
"pred_area": math.nan,
"gt_area": math.nan,
}
for frame_idx in range(pred_scores.shape[0]):
base_info_frame = dict(base_info)
base_info_frame.update(
{
"frame_iou": frame_ious[frame_idx].item(),
"frame_fscore_proxy": frame_fscores[frame_idx].item(),
"iou_pred": iou_predictions[frame_idx].item(),
"pred_area": pred_area[frame_idx].item(),
"gt_area": gt_area[frame_idx].item(),
}
)
row = dict(base_info_frame)
row.update(
{
"frame": frame_idx,
"q_type": q_type,
"beta": beta,
"s_pred": pred_scores[frame_idx].item(),
"s_gt": gt_scores[frame_idx].item(),
"q_source_idx": q_source_idx if q_source_idx is not None else "",
}
)
rows.append(row)
real_rows = [
r for r in rows if r["sample_idx"] == sample_idx and r["q_type"] == "real" and r["beta"] == betas[0]
]
s_pred_values = [r["s_pred"] for r in real_rows]
print(
f"D2 {sample_idx}: vid={item['vid']} ref={item['ref']} "
f"mean_s_pred={np.mean(s_pred_values):.4f} min_s_pred={np.min(s_pred_values):.4f} "
f"mean_iou={frame_ious.mean().item():.4f}"
)
return rows
def print_summary(rows):
real_rows = [r for r in rows if r["q_type"] == "real"]
if not real_rows:
return
by_beta = sorted(set(r["beta"] for r in real_rows))
print("\nSummary")
print(f"rows: {len(rows)}")
for beta in by_beta:
beta_rows = [r for r in rows if r["beta"] == beta]
print(f"\nbeta={beta}")
for q_type in sorted(set(r["q_type"] for r in beta_rows)):
qr = [r for r in beta_rows if r["q_type"] == q_type]
print(
f"{q_type:10s} "
f"mean_s_pred={np.mean([r['s_pred'] for r in qr]):+.4f} "
f"mean_s_gt={np.mean([r['s_gt'] for r in qr]):+.4f}"
)
real_beta = [r for r in beta_rows if r["q_type"] == "real"]
s_pred = np.array([r["s_pred"] for r in real_beta])
frame_iou_values = np.array([r["frame_iou"] for r in real_beta])
if len(s_pred) > 1 and np.std(s_pred) > 1e-8 and np.std(frame_iou_values) > 1e-8:
corr = np.corrcoef(s_pred, frame_iou_values)[0, 1]
print(f"corr(real s_pred, frame_iou)={corr:+.4f}")
else:
print("corr(real s_pred, frame_iou)=nan")
def main():
set_seed(42)
torch.set_grad_enabled(False)
betas = parse_betas()
tokenizer, seg_token_idx = build_tokenizer()
limit = args.max_eval_rows if args.max_eval_rows > 0 else 30
print(f"Split: {args.eval_split} | samples: {limit} | betas: {betas}")
model = build_model(tokenizer, seg_token_idx)
q_pool = collect_q_pool(model, tokenizer, limit)
rows = run_d2(model, tokenizer, q_pool, betas, limit)
print_summary(rows)
csv_path = os.environ.get("D2_BASIC_CSV", f"/workspace/SimToken/d2_basic_{args.eval_split}_{limit}.csv")
os.makedirs(os.path.dirname(os.path.abspath(csv_path)), exist_ok=True)
with open(csv_path, "w", newline="") as f:
writer = csv.DictWriter(f, fieldnames=list(rows[0].keys()))
writer.writeheader()
writer.writerows(rows)
print(f"\nSaved CSV: {csv_path}")
if __name__ == "__main__":
main()
|