def ctdet_decode(hmap, regs, w_h_, K=100):
batch, cat, height, width = hmap.shape
hmap = torch.sigmoid(hmap)
# if flip test
if batch > 1:
hmap = (hmap[0:1] + flip_tensor(hmap[1:2])) / 2
w_h_ = (w_h_[0:1] + flip_tensor(w_h_[1:2])) / 2
regs = regs[0:1]
batch = 1
hmap = _nms(hmap) # perform nms on heatmaps
scores, inds, clses, ys, xs = _topk(hmap, K=K)
regs = _tranpose_and_gather_feature(regs, inds)
regs = regs.view(batch, K, 2)
xs = xs.view(batch, K, 1) + regs[:, :, 0:1]
ys = ys.view(batch, K, 1) + regs[:, :, 1:2]
w_h_ = _tranpose_and_gather_feature(w_h_, inds)
w_h_ = w_h_.view(batch, K, 2)
clses = clses.view(batch, K, 1).float()
scores = scores.view(batch, K, 1)
bboxes = torch.cat([xs - w_h_[..., 0:1] / 2,
ys - w_h_[..., 1:2] / 2,
xs + w_h_[..., 0:1] / 2,
ys + w_h_[..., 1:2] / 2], dim=2)
detections = torch.cat([bboxes, scores, clses], dim=2)
return detections
def compute_embeddings_lfw(args,
dataset,
model,
batch_size,
dump_embeddings=False,
pdist=lambda x, y: 1. - F.cosine_similarity(x, y),
flipped_embeddings=False):
"""Computes embeddings of all images from the LFW dataset using PyTorch"""
val_loader = DataLoader(dataset,
batch_size=batch_size,
num_workers=4,
shuffle=False)
scores_with_gt = []
embeddings = []
ids = []
for batch_idx, data in enumerate(tqdm(val_loader, 'Computing embeddings')):
images_1 = data['img1']
images_2 = data['img2']
is_same = data['is_same']
if torch.cuda.is_available() and args.devices[0] != -1:
images_1 = images_1.cuda()
images_2 = images_2.cuda()
emb_1 = model(images_1)
emb_2 = model(images_2)
if flipped_embeddings:
images_1_flipped = flip_tensor(images_1, 3)
images_2_flipped = flip_tensor(images_2, 3)
emb_1_flipped = model(images_1_flipped)
emb_2_flipped = model(images_2_flipped)
emb_1 = (emb_1 + emb_1_flipped) * .5
emb_2 = (emb_2 + emb_2_flipped) * .5
scores = pdist(emb_1, emb_2).data.cpu().numpy()
for i, _ in enumerate(scores):
scores_with_gt.append({
'score': scores[i],
'is_same': is_same[i],
'idx': batch_idx * batch_size + i
})
if dump_embeddings:
id0 = data['id0']
id1 = data['id1']
ids.append(id0)
ids.append(id1)
to_dump_1 = emb_1.data.cpu()
to_dump_2 = emb_2.data.cpu()
embeddings.append(to_dump_1)
embeddings.append(to_dump_2)
if dump_embeddings:
total_emb = np.concatenate(embeddings, axis=0)
total_ids = np.concatenate(ids, axis=0)
log_path = './logs/{:%Y_%m_%d_%H_%M}'.format(datetime.datetime.now())
writer = SummaryWriter(log_path)
writer.add_embedding(torch.from_numpy(total_emb), total_ids)
return scores_with_gt
def ctdet_decode(hmap, regs, w_h_, K=100):
'''
hmap提取中心点位置为xs,ys
regs保存的是偏置，需要加在xs,ys上，代表精确的中心位置
w_h_保存的是对应目标的宽和高
'''
# dets = ctdet_decode(*output, K=cfg.test_topk)
batch, cat, height, width = hmap.shape
hmap = torch.sigmoid(hmap) # 归一化到0-1
# if flip test
if batch > 1: # batch > 1代表使用了翻转
# img = np.concatenate((img, img[:, :, :, ::-1].copy()), axis=0)
hmap = (hmap[0:1] + flip_tensor(hmap[1:2])) / 2
w_h_ = (w_h_[0:1] + flip_tensor(w_h_[1:2])) / 2
regs = regs[0:1]
batch = 1
# 这里的nms和带anchor的目标检测方法中的不一样，这里使用的是3x3的maxpool筛选
hmap = _nms(hmap) # perform nms on heatmaps
# 找到前K个极大值点代表存在目标
scores, inds, clses, ys, xs = _topk(hmap, K=K)
# from [bs c h w] to [bs, h, w, c]
regs = _tranpose_and_gather_feature(regs, inds)
regs = regs.view(batch, K, 2)
xs = xs.view(batch, K, 1) + regs[:, :, 0:1]
ys = ys.view(batch, K, 1) + regs[:, :, 1:2]
w_h_ = _tranpose_and_gather_feature(w_h_, inds)
w_h_ = w_h_.view(batch, K, 2)
clses = clses.view(batch, K, 1).float()
scores = scores.view(batch, K, 1)
# xs,ys是中心坐标，w_h_[...,0:1]是w,1:2是h
bboxes = torch.cat([
xs - w_h_[..., 0:1] / 2, ys - w_h_[..., 1:2] / 2,
xs + w_h_[..., 0:1] / 2, ys + w_h_[..., 1:2] / 2
],
dim=2)
detections = torch.cat([bboxes, scores, clses], dim=2)
return detections
def ctsegm_inmodal_norm_code_decode(hmap, regs, w_h_, codes_, offsets_, contour_std, dictionary, K=100):
batch, cat, height, width = hmap.shape
hmap = torch.sigmoid(hmap)
# if flip test
if batch > 1:
hmap = (hmap[0:1] + flip_tensor(hmap[1:2])) / 2
w_h_ = (w_h_[0:1] + flip_tensor(w_h_[1:2])) / 2
regs = regs[0:1]
codes_ = codes_[0:1]
offsets_ = offsets_[0:1]
contour_std = contour_std[0:1]
batch = 1
hmap = _nms(hmap) # perform nms on heatmaps
scores, inds, clses, ys, xs = _topk(hmap, K=K)
regs = _tranpose_and_gather_feature(regs, inds)
regs = regs.view(batch, K, 2)
xs = xs.view(batch, K, 1) + regs[:, :, 0:1]
ys = ys.view(batch, K, 1) + regs[:, :, 1:2]
w_h_ = _tranpose_and_gather_feature(w_h_, inds)
w_h_ = w_h_.view(batch, K, 2)
contour_std = _tranpose_and_gather_feature(contour_std, inds)
contour_std = contour_std.view(batch, K, 1)
codes_ = _tranpose_and_gather_feature(codes_, inds)
codes_ = codes_.view(batch, K, 64)
clses = clses.view(batch, K, 1).float()
scores = scores.view(batch, K, 1)
bboxes = torch.cat([xs - w_h_[..., 0:1] / 2,
ys - w_h_[..., 1:2] / 2,
xs + w_h_[..., 0:1] / 2,
ys + w_h_[..., 1:2] / 2], dim=2)
offsets_ = _tranpose_and_gather_feature(offsets_, inds)
segms = torch.matmul(codes_, dictionary) * contour_std
segms = segms.view(batch, K, 32, 2) + offsets_.view(batch, K, 1, 2) + \
torch.cat([xs, ys], dim=2).view(batch, K, 1, 2)
segmentations = torch.cat([segms.view(batch, K, -1), bboxes, scores, clses], dim=2)
return segmentations
def ctsegm_fourier_decode(hmap, regs, w_h_, real_, imaginary_, K=100):
batch, cat, height, width = hmap.shape
hmap = torch.sigmoid(hmap)
# if flip test
if batch > 1:
hmap = (hmap[0:1] + flip_tensor(hmap[1:2])) / 2
w_h_ = (w_h_[0:1] + flip_tensor(w_h_[1:2])) / 2
regs = regs[0:1]
real_ = real_[0:1]
imaginary_ = imaginary_[0:1]
batch = 1
hmap = _nms(hmap) # perform nms on heatmaps
scores, inds, clses, ys, xs = _topk(hmap, K=K)
regs = _tranpose_and_gather_feature(regs, inds)
regs = regs.view(batch, K, 2)
xs = xs.view(batch, K, 1) + regs[:, :, 0:1]
ys = ys.view(batch, K, 1) + regs[:, :, 1:2]
w_h_ = _tranpose_and_gather_feature(w_h_, inds)
w_h_ = w_h_.view(batch, K, 4)
real_ = _tranpose_and_gather_feature(real_, inds)
real_ = real_.view(batch, K, 32, 1)
imaginary_ = _tranpose_and_gather_feature(imaginary_, inds)
imaginary_ = imaginary_.view(batch, K, 32, 1)
clses = clses.view(batch, K, 1).float()
scores = scores.view(batch, K, 1)
bboxes = torch.cat([xs - w_h_[..., 2:3],
ys - w_h_[..., 0:1],
xs + w_h_[..., 3:4],
ys + w_h_[..., 1:2]], dim=2)
complex_codes = torch.cat([real_, imaginary_], dim=3) * 32.
segms = torch.ifft(complex_codes, signal_ndim=1)
segms = segms + torch.cat([xs, ys], dim=2).view(batch, K, 1, 2)
segmentations = torch.cat([segms.view(batch, K, -1), bboxes, scores, clses], dim=2)
return segmentations
def ctsegm_amodal_cmm_whiten_decode(hmap, regs, w_h_, codes_, offsets_, dictionary, code_range, K=100):
batch, cat, height, width = hmap.shape
hmap = torch.sigmoid(hmap)
# if flip test
if batch > 1:
hmap = (hmap[0:1] + flip_tensor(hmap[1:2])) / 2
w_h_ = (w_h_[0:1] + flip_tensor(w_h_[1:2])) / 2
regs = regs[0:1]
codes_ = codes_[0:1]
offsets_ = offsets_[0:1]
batch = 1
hmap = _nms(hmap) # perform nms on heatmaps
scores, inds, clses, ys, xs = _topk(hmap, K=K)
regs = _tranpose_and_gather_feature(regs, inds)
regs = regs.view(batch, K, 2)
xs = xs.view(batch, K, 1) + regs[:, :, 0:1]
ys = ys.view(batch, K, 1) + regs[:, :, 1:2]
w_h_ = _tranpose_and_gather_feature(w_h_, inds)
w_h_ = w_h_.view(batch, K, 2)
codes_ = _tranpose_and_gather_feature(codes_, inds)
codes_ = codes_.view(batch, K, 64)
clses = clses.view(batch, K, 1).float()
scores = scores.view(batch, K, 1)
bboxes = torch.cat([xs - w_h_[..., 0:1] / 2,
ys - w_h_[..., 1:2] / 2,
xs + w_h_[..., 0:1] / 2,
ys + w_h_[..., 1:2] / 2], dim=2)
offsets_ = _tranpose_and_gather_feature(offsets_, inds)
# codes_ = codes_ * code_stat[1].view(1, 1, -1) + code_stat[0].view(1, 1, -1) # recover the original unnormalized codes
codes_ = (codes_ + 1) / 2. * (code_range[1] - code_range[0]) + code_range[0]
segms = torch.matmul(codes_, dictionary)
segms = segms.view(batch, K, 32, 2) + offsets_.view(batch, K, 1, 2) + \
torch.cat([xs, ys], dim=2).view(batch, K, 1, 2)
segmentations = torch.cat([segms.view(batch, K, -1), bboxes, scores, clses], dim=2)
return segmentations
def ctdet_decode(hmap, regs, w_h_, pxpy, K=100):
batch, cat, height, width = hmap.shape # C,W和H
# height , width = 128
hmap = torch.sigmoid(hmap)
# 这里，test的batch是 1
# if flip test
if batch > 1:
hmap = (hmap[0:1] + flip_tensor(hmap[1:2])) / 2
w_h_ = (w_h_[0:1] + flip_tensor(w_h_[1:2])) / 2 # w_h_ 第一列是宽度，第二列是高度。
regs = regs[0:1]
batch = 1
hmap = _nms(hmap) # perform nms on heatmaps
scores, inds, clses, ys, xs = _topk(hmap, K=K)
regs = _tranpose_and_gather_feature(regs, inds)
regs = regs.view(batch, K, 2)
xs = xs.view(batch, K, 1) + regs[:, :, 0:1]
ys = ys.view(batch, K, 1) + regs[:, :, 1:2]
w_h_ = _tranpose_and_gather_feature(w_h_, inds)
w_h_ = w_h_.view(batch, K, 2)
pxpy = _tranpose_and_gather_feature(pxpy, inds)
pxpy = pxpy.view(batch, K, 2)
clses = clses.view(batch, K, 1).float()
scores = scores.view(batch, K, 1)
width1 = torch.abs(torch.mul(pxpy[..., 0:1], torch.cos(pxpy[...,
1:2]))) # 半宽度
height1 = torch.abs(torch.mul(pxpy[..., 0:1], torch.sin(pxpy[...,
1:2]))) # 半高度
width1 = 0.1 * width1 + 0.9 * w_h_[..., 0:1] / 2
height1 = 0.1 * height1 + 0.9 * w_h_[..., 1:2] / 2
bboxes = torch.cat([xs - width1, ys - height1, xs + width1, ys + height1],
dim=2)
detections = torch.cat([bboxes, scores, clses], dim=2)
return detections
def ctsegm_shift_code_decode(hmap, regs, w_h_, codes_, dictionary, K=100):
batch, cat, height, width = hmap.shape
hmap = torch.sigmoid(hmap)
# if flip test
if batch > 1:
hmap = (hmap[0:1] + flip_tensor(hmap[1:2])) / 2
w_h_ = (w_h_[0:1] + flip_tensor(w_h_[1:2])) / 2
regs = regs[0:1]
codes_ = codes_[0:1]
batch = 1
hmap = _nms(hmap) # perform nms on heatmaps
scores, inds, clses, ys, xs = _topk(hmap, K=K)
regs = _tranpose_and_gather_feature(regs, inds)
regs = regs.view(batch, K, 2)
xs = xs.view(batch, K, 1) + regs[:, :, 0:1]
ys = ys.view(batch, K, 1) + regs[:, :, 1:2]
w_h_ = _tranpose_and_gather_feature(w_h_, inds)
w_h_ = w_h_.view(batch, K, 4)
codes_ = _tranpose_and_gather_feature(codes_, inds)
codes_ = codes_.view(batch, K, 64)
# codes_ = torch.log(codes_).view(batch, K, 64)
clses = clses.view(batch, K, 1).float()
scores = scores.view(batch, K, 1)
bboxes = torch.cat([xs - w_h_[..., 2:3],
ys - w_h_[..., 0:1],
xs + w_h_[..., 3:4],
ys + w_h_[..., 1:2]], dim=2)
segms = torch.matmul(codes_, dictionary)
segms = segms.view(batch, K, 32, 2) + torch.cat([xs, ys], dim=2).view(batch, K, 1, 2)
segmentations = torch.cat([segms.view(batch, K, -1), bboxes, scores, clses], dim=2)
return segmentations
def ctsegm_decode(hmap, regs, w_h_, codes_, dictionary, K=100):
batch, cat, height, width = hmap.shape
hmap = torch.sigmoid(hmap)
# if flip test
if batch > 1:
hmap = (hmap[0:1] + flip_tensor(hmap[1:2])) / 2
w_h_ = (w_h_[0:1] + flip_tensor(w_h_[1:2])) / 2
regs = regs[0:1]
codes_ = codes_[0:1]
batch = 1
hmap = _nms(hmap) # perform nms on heatmaps
scores, inds, clses, ys, xs = _topk(hmap, K=K)
regs = _tranpose_and_gather_feature(regs, inds)
regs = regs.view(batch, K, 2)
xs = xs.view(batch, K, 1) + regs[:, :, 0:1]
ys = ys.view(batch, K, 1) + regs[:, :, 1:2]
w_h_ = _tranpose_and_gather_feature(w_h_, inds)
w_h_ = w_h_.view(batch, K, 2)
std_ = torch.sqrt(torch.sum(w_h_ ** 2., dim=2, keepdim=True))
codes_ = _tranpose_and_gather_feature(codes_, inds)
# codes_ = codes_.view(batch, K, 64)
codes_ = torch.log(codes_).view(batch, K, 64)
clses = clses.view(batch, K, 1).float()
scores = scores.view(batch, K, 1)
segms = torch.matmul(codes_, dictionary)
# print('Sizes:', segms.size(), std_.size(), xs.size())
segms = (segms * std_).view(batch, K, 32, 2) + torch.cat([xs, ys], dim=2).view(batch, K, 1, 2)
segmentations = torch.cat([segms.view(batch, K, -1), scores, clses], dim=2)
return segmentations
