def detect_pose(self, im, bbox): im_in = im cords = bbox[0:4] center, scale = self.x1y1x2y2_to_cs(cords) r=0 trans = get_affine_transform(center[0], scale[0], r, self.image_size) input_image = cv2.warpAffine(im_in, trans, (int(self.image_width), int(self.image_height)), flags=cv2.INTER_LINEAR) with torch.no_grad(): input = self.transform(input_image) input = input.unsqueeze(0) with torch.cuda.device(self.gpu_id): input = input.cuda() output = self.model(input) if cfg.TEST.FLIP_TEST: input_flipped = np.flip(input.cpu().numpy(),3).copy() input_flipped = torch.from_numpy(input_flipped).cuda() output_flipped = self.model(input_flipped) output_flipped = flip_back(output_flipped.cpu().numpy(), self.flip_pairs) output_flipped = torch.from_numpy(output_flipped.copy()).cuda() if cfg.TEST.SHIFT_HEATMAP: output_flipped[:, :, :, 1:] = output_flipped.clone()[:, :, :, 0:-1] output = (output + output_flipped) *0.5 output = output.cpu().numpy() preds, maxvals = self.get_final_preds(output, center, scale) preds, maxvals = preds.squeeze(), maxvals.squeeze() heatmaps = output.squeeze() #For posetrack dataset, the 3th and 4th channel is None preds = np.delete(preds, [3,4], axis=0) maxvals = np.delete(maxvals, [3,4], axis=0) heatmaps = np.delete(heatmaps, [3,4], axis=0) #print(heatmaps.shape,preds,maxvals) return preds, maxvals, heatmaps
def detect_pose_secway(self, im, bbox):
cords = bbox[0:4]
H, W, C = im.shape
xmin, ymin, xmax, ymax = [int(i) for i in cords]
xmax = min(xmax, W)
ymax = min(ymax, H)
xmin = max(xmin, 0)
ymin = max(ymin, 0)
w, h = xmax - xmin, ymax - ymin
if w < 0 or h < 0:
return np.zeros([17, 2]), np.zeros([17]), np.zeros([17, 64, 64])
im_in = im[ymin:ymax, xmin:xmax, :]
scale_factor = [self.image_width / w, self.image_height / h]
im_resize = cv2.resize(im_in,
(int(self.image_width), int(self.image_height)),
interpolation=cv2.INTER_LINEAR)
with torch.no_grad():
input = self.transform(im_resize)
input = input.unsqueeze(0)
with torch.cuda.device(self.gpu_id):
adj = self.reset_adj_no1()
adj = adj.unsqueeze(0)
adj = adj.type(torch.cuda.FloatTensor)
input = input.cuda()
output = self.model(input, adj)
if cfg.TEST.FLIP_TEST:
input_flipped = np.flip(input.cpu().numpy(), 3).copy()
input_flipped = torch.from_numpy(input_flipped).cuda()
output_flipped = self.model(input_flipped, adj)
output_flipped = flip_back(output_flipped.cpu().numpy(),
self.flip_pairs)
output_flipped = torch.from_numpy(
output_flipped.copy()).cuda()
if cfg.TEST.SHIFT_HEATMAP:
output_flipped[:, :, :,
1:] = output_flipped.clone()[:, :, :,
0:-1]
output = (output + output_flipped) * 0.5
preds, maxvals = get_max_preds(output.clone().cpu().numpy())
preds, maxvals = preds.squeeze() * 4, maxvals.squeeze()
heatmaps = output.cpu().numpy().squeeze()
#For posetrack dataset, the 3th and 4th channel is None
preds = np.delete(preds, [3, 4], axis=0)
preds[:, 0] = preds[:, 0] / scale_factor[0] + bbox[0]
preds[:, 1] = preds[:, 1] / scale_factor[1] + bbox[1]
maxvals = np.delete(maxvals, [3, 4], axis=0)
heatmaps = np.delete(heatmaps, [3, 4], axis=0)
return preds, maxvals, heatmaps
def validate(val_loader,
model,
criterion,
num_classes,
debug=False,
flip=True):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
# predictions
predictions = torch.Tensor(val_loader.dataset.__len__(), num_classes, 2)
# switch to evaluate mode
model.eval()
gt_win, pred_win = None, None
end = time.time()
bar = Bar('Eval ', max=len(val_loader))
with torch.no_grad():
for i, (input, target, meta) in enumerate(val_loader):
# measure data loading time
data_time.update(time.time() - end)
input = input.to(device, non_blocking=True)
target = target.to(device, non_blocking=True)
target_weight = meta['target_weight'].to(device, non_blocking=True)
# compute output
output = model(input)
score_map = output[-1].cpu() if type(
output) == list else output.cpu()
if flip:
flip_input = torch.from_numpy(fliplr(
input.clone().numpy())).float().to(device)
flip_output = model(flip_input)
flip_output = flip_output[-1].cpu() if type(
flip_output) == list else flip_output.cpu()
flip_output = flip_back(flip_output)
score_map += flip_output
if type(output) == list: # multiple output
loss = 0
for o in output:
loss += criterion(o, target, target_weight)
output = output[-1]
else: # single output
loss = criterion(output, target, target_weight)
acc = accuracy(score_map, target.cpu(), idx)
# generate predictions
preds = final_preds(score_map, meta['center'], meta['scale'],
[64, 64])
for n in range(score_map.size(0)):
predictions[meta['index'][n], :, :] = preds[n, :, :]
if debug:
gt_batch_img = batch_with_heatmap(input, target)
pred_batch_img = batch_with_heatmap(input, score_map)
if not gt_win or not pred_win:
plt.subplot(121)
gt_win = plt.imshow(gt_batch_img)
plt.subplot(122)
pred_win = plt.imshow(pred_batch_img)
else:
gt_win.set_data(gt_batch_img)
pred_win.set_data(pred_batch_img)
plt.pause(.05)
plt.draw()
# measure accuracy and record loss
losses.update(loss.item(), input.size(0))
acces.update(acc[0], input.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
# plot progress
bar.suffix = '({batch}/{size}) Data: {data:.6f}s | Batch: {bt:.3f}s | Total: {total:} | ETA: {eta:} | Loss: {loss:.4f} | Acc: {acc: .4f}'.format(
batch=i + 1,
size=len(val_loader),
data=data_time.val,
bt=batch_time.avg,
total=bar.elapsed_td,
eta=bar.eta_td,
loss=losses.avg,
acc=acces.avg)
bar.next()
bar.finish()
return losses.avg, acces.avg, predictions
def validate(val_loader, model, criterion, num_classes, debug=False, flip=True, _logger=None):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
# predictions
predictions = torch.Tensor(val_loader.dataset.__len__(), num_classes, 2)
autoloss = models.loss.UniLoss(valid=True)
# switch to evaluate mode
model.eval()
#model.train()
gt_win, pred_win = None, None
end = time.time()
bar = Bar('Processing', max=len(val_loader))
for i, (inputs, target, meta) in enumerate(val_loader):
# measure data loading time
data_time.update(time.time() - end)
target = target.cuda(async=True)
input_var = torch.autograd.Variable(inputs.cuda(), volatile=True)
target_var = torch.autograd.Variable(target, volatile=True)
# compute output
output = model(input_var)
score_map = output[-1].data.cpu()
if flip:
flip_input_var = torch.autograd.Variable(
torch.from_numpy(fliplr(inputs.clone().numpy())).float().cuda(),
volatile=True
)
flip_output_var = model(flip_input_var)
flip_output = flip_back(flip_output_var[-1].data.cpu())
score_map += flip_output
loss = 0
for o in output:
loss += criterion(o, target_var)
#acc = accuracy(score_map, target.cpu(), idx)
_, acc, _ = autoloss(output[-1], meta)
# generate predictions
preds = final_preds(score_map, meta['center'], meta['scale'], [64, 64])
for n in range(score_map.size(0)):
predictions[meta['index'][n], :, :] = preds[n, :, :]
if debug:
gt_batch_img = batch_with_heatmap(inputs, target)
pred_batch_img = batch_with_heatmap(inputs, score_map)
if not gt_win or not pred_win:
plt.subplot(121)
gt_win = plt.imshow(gt_batch_img)
plt.subplot(122)
pred_win = plt.imshow(pred_batch_img)
else:
gt_win.set_data(gt_batch_img)
pred_win.set_data(pred_batch_img)
plt.pause(.05)
plt.draw()
# measure accuracy and record loss
losses.update(loss.item(), inputs.size(0))
acces.update(acc.item(), inputs.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
# plot progress
bar.suffix = '({batch}/{size}) Data: {data:.6f}s | Batch: {bt:.3f}s | Total: {total:} | Loss: {loss:.4f} | Acc: {acc: .4f}'.format(
batch=i + 1,
size=len(val_loader),
data=data_time.val,
bt=batch_time.avg,
total=bar.elapsed_td,
loss=losses.avg*100,
acc=acces.avg*100
)
_logger.info(bar.suffix)
bar.finish()
return losses.avg*100, acces.avg*100, predictions
def validate(val_loader,
model,
criterion,
num_classes,
idx,
save_result_dir,
meta_dir,
anno_type,
flip=True,
evaluate=False,
scales=[0.7, 0.8, 0.9, 1, 1.2, 1.4, 1.6],
multi_scale=False,
save_heatmap=False):
anno_type = anno_type[0].lower()
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
num_scales = len(scales)
# switch to evaluate mode
model.eval()
meanstd_file = '../datasets/arm/mean.pth.tar'
meanstd = torch.load(meanstd_file)
mean = meanstd['mean']
gt_win, pred_win = None, None
end = time.time()
bar = Bar('Processing', max=len(val_loader))
for i, (inputs, target, meta) in enumerate(val_loader):
#print(inputs.shape)
# measure data loading time
data_time.update(time.time() - end)
if anno_type != 'none':
target = target.cuda(async=True)
target_var = torch.autograd.Variable(target)
input_var = torch.autograd.Variable(inputs.cuda())
with torch.no_grad():
# compute output
output = model(input_var)
score_map = output[-1].data.cpu()
if flip:
flip_input_var = torch.autograd.Variable(
torch.from_numpy(fliplr(
inputs.clone().numpy())).float().cuda(), )
flip_output_var = model(flip_input_var)
flip_output = flip_back(flip_output_var[-1].data.cpu(),
meta_dir=meta_dir[0])
score_map += flip_output
score_map /= 2
if anno_type != 'none':
loss = 0
for o in output:
loss += criterion(o, target_var)
acc = accuracy(score_map, target.cpu(), idx, pck_threshold)
if multi_scale:
new_scales = []
new_res = []
new_score_map = []
new_inp = []
new_meta = []
img_name = []
confidence = []
new_center = []
num_imgs = score_map.size(0) // num_scales
for n in range(num_imgs):
score_map_merged, res, conf = multi_scale_merge(
score_map[num_scales * n:num_scales * (n + 1)].numpy(),
meta['scale'][num_scales * n:num_scales * (n + 1)])
inp_merged, _, _ = multi_scale_merge(
inputs[num_scales * n:num_scales * (n + 1)].numpy(),
meta['scale'][num_scales * n:num_scales * (n + 1)])
new_score_map.append(score_map_merged)
new_scales.append(meta['scale'][num_scales * (n + 1) - 1])
new_center.append(meta['center'][num_scales * n])
new_res.append(res)
new_inp.append(inp_merged)
img_name.append(meta['img_name'][num_scales * n])
confidence.append(conf)
if len(new_score_map) > 1:
score_map = torch.tensor(
np.stack(new_score_map)) #stack back to 4-dim
inputs = torch.tensor(np.stack(new_inp))
else:
score_map = torch.tensor(
np.expand_dims(new_score_map[0], axis=0))
inputs = torch.tensor(np.expand_dims(new_inp[0], axis=0))
else:
img_name = []
confidence = []
for n in range(score_map.size(0)):
img_name.append(meta['img_name'][n])
confidence.append(
np.amax(score_map[n].numpy(), axis=(1, 2)).tolist())
# generate predictions
if multi_scale:
preds = final_preds(score_map, new_center, new_scales, new_res[0])
else:
preds = final_preds(score_map, meta['center'], meta['scale'],
[64, 64])
for n in range(score_map.size(0)):
if evaluate:
with open(
os.path.join(save_result_dir, 'preds',
img_name[n] + '.json'), 'w') as f:
obj = {
'd2_key': preds[n].numpy().tolist(),
'score': confidence[n]
}
json.dump(obj, f)
if evaluate:
for n in range(score_map.size(0)):
inp = inputs[n]
pred = score_map[n]
for t, m in zip(inp, mean):
t.add_(m)
scipy.misc.imsave(
os.path.join(save_result_dir, 'visualization',
'{}.jpg'.format(img_name[n])),
sample_with_heatmap(inp, pred))
if save_heatmap:
score_map_original_size = align_back(
score_map[n], meta['center'][n],
meta['scale'][len(scales) * n - 1],
meta['original_size'][n])
np.save(
os.path.join(save_result_dir, 'heatmaps',
'{}.npy'.format(img_name[n])),
score_map_original_size)
if anno_type != 'none':
# measure accuracy and record loss
losses.update(loss.item(), inputs.size(0))
acces.update(acc[0], inputs.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
# plot progress
bar.suffix = '({batch}/{size}) Data: {data:.6f}s | Batch: {bt:.3f}s | Total: {total:} | ETA: {eta:} | Loss: {loss:.4f} | Acc: {acc: .4f}'.format(
batch=i + 1,
size=len(val_loader),
data=data_time.val,
bt=batch_time.avg,
total=bar.elapsed_td,
eta=bar.eta_td,
loss=losses.avg,
acc=acces.avg)
bar.next()
bar.finish()
if anno_type != 'none':
return losses.avg, acces.avg
else:
return 0, 0
def validate(val_loader,
model,
criterion,
num_classes,
args,
flip=False,
test_batch=6):
batch_time = AverageMeter()
data_time = AverageMeter()
acces = AverageMeter()
pck_score = np.zeros(num_classes)
pck_count = np.zeros(num_classes)
# predictions
predictions = torch.Tensor(val_loader.dataset.__len__(), num_classes, 2)
# switch to evaluate mode
model.eval()
gt_win, pred_win = None, None
end = time.time()
bar = Bar('Eval ', max=len(val_loader))
with torch.no_grad():
for i, (input, target, meta) in enumerate(val_loader):
# measure data loading time
data_time.update(time.time() - end)
input = input.to(device, non_blocking=True)
target = target.to(device, non_blocking=True)
target_weight = meta['target_weight'].to(device, non_blocking=True)
# compute output
if args.arch == 'hg':
output = model(input)
elif args.arch == 'hg_multitask':
output, _ = model(input)
else:
raise Exception("unspecified arch")
score_map = output[-1].cpu() if type(
output) == list else output.cpu()
if flip:
flip_input = torch.from_numpy(
fliplr(input.clone().cpu().numpy())).float().to(device)
flip_output = model(flip_input)
flip_output = flip_output[-1].cpu() if type(
flip_output) == list else flip_output.cpu()
flip_output = flip_back(flip_output)
score_map += flip_output
acc, _ = accuracy_2animal(score_map, target.cpu(), idx1, idx2)
# cal per joint [email protected]
for j in range(num_classes):
if acc[j + 1] > -1:
pck_score[j] += acc[j + 1].numpy()
pck_count[j] += 1
# generate predictions
preds = final_preds(score_map, meta['center'], meta['scale'],
[64, 64])
for n in range(score_map.size(0)):
predictions[meta['index'][n], :, :] = preds[n, :, :]
# measure accuracy and record loss
acces.update(acc[0], input.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
# plot progress
bar.suffix = '({batch}/{size}) Data: {data:.3f}s | Batch: {bt:.3f}s | Total: {total:} | ETA: {eta:} | Acc: {acc: .8f}'.format(
batch=i + 1,
size=len(val_loader),
data=data_time.val,
bt=batch_time.avg,
total=bar.elapsed_td,
eta=bar.eta_td,
acc=acces.avg)
bar.next()
bar.finish()
for j in range(num_classes):
pck_score[j] /= float(pck_count[j])
print("\nper joint [email protected]:")
print(list(pck_score))
return _, acces.avg, predictions
def validate(val_loader,
model,
criterion,
num_classes,
debug=False,
flip=True):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
# predictions
predictions = torch.Tensor(val_loader.dataset.__len__(), num_classes, 2)
# switch to evaluate mode
model.eval()
gt_win, pred_win = None, None
end = time.time()
bar = Bar('Eval ', max=len(val_loader))
with torch.no_grad():
for i, (input, target, meta, img_path) in enumerate(val_loader):
# measure data loading time
data_time.update(time.time() - end)
indexes = []
input = input.to(device, non_blocking=True)
#print (input.shape)
#image = input.cpu().permute(0,2,3,1).numpy()
#image = np.squeeze(image)
path = str(img_path)
path = path[3:len(path) - 2]
image = cv2.imread(path)
# cv2.imshow("image", image)
# cv2.waitKey(10)
# time.sleep(1)
target = target.to(device, non_blocking=True)
target_weight = meta['target_weight'].to(device, non_blocking=True)
# compute output
#print (input.shape)
output = model(input)
score_map = output[-1].cpu() if type(
output) == list else output.cpu()
if flip:
flip_input = torch.from_numpy(fliplr(
input.clone().numpy())).float().to(device)
flip_output = model(flip_input)
flip_output = flip_output[-1].cpu() if type(
flip_output) == list else flip_output.cpu()
flip_output = flip_back(flip_output)
score_map += flip_output
if type(output) == list: # multiple output
loss = 0
for o in output:
loss += criterion(o, target, target_weight)
output = output[-1]
else: # single output
loss = criterion(output, target, target_weight)
#print (acc)
# generate predictions
preds, vals = final_preds(score_map, meta['center'], meta['scale'],
[64, 64])
# for z in range(target.shape[1]):
# for j in range(target.shape[2]):
# for k in range(target.shape[3]):
# if target[0,z,j,k]==1.0:
# indexes.append(z)
# coords = np.squeeze(preds)
# for m in range(0,len(coords)):
# val = vals[0][m].numpy()
# if val>0.6: #threshold for confidence score
# x,y = coords[m][0].cpu().numpy(), coords[m][1].cpu().numpy()
# cv2.circle(image, (x,y), 1, (0,0,255), -1)
# #indexes.append(m)
acc = accuracy(score_map, target.cpu(), indexes)
#print ((target.cpu()).shape[1])
for n in range(score_map.size(0)):
predictions[meta['index'][n], :, :] = preds[n, :, :]
#print ("scored", score_map.shape)
if debug:
gt_batch_img = batch_with_heatmap(input, target)
pred_batch_img = batch_with_heatmap(input, score_map)
if not gt_win or not pred_win:
plt.subplot(121)
gt_win = plt.imshow(gt_batch_img)
plt.subplot(122)
pred_win = plt.imshow(pred_batch_img)
else:
gt_win.set_data(gt_batch_img)
pred_win.set_data(pred_batch_img)
plt.pause(.05)
plt.draw()
cv2.imwrite(
'/home/shantam/Documents/Programs/pytorch-pose/example/predictions/pred'
+ str(i) + '.png', image)
#time.sleep(5)
# measure accuracy and record loss
losses.update(loss.item(), input.size(0))
acces.update(acc[0], input.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
# plot progress
bar.suffix = '({batch}/{size}) Data: {data:.6f}s | Batch: {bt:.3f}s | Total: {total:} | ETA: {eta:} | Loss: {loss:.4f} | Acc: {acc: .4f}'.format(
batch=i + 1,
size=len(val_loader),
data=data_time.val,
bt=batch_time.avg,
total=bar.elapsed_td,
eta=bar.eta_td,
loss=losses.avg,
acc=acces.avg)
bar.next()
bar.finish()
return losses.avg, acces.avg, predictions
def validate(val_loader, model, criterion, num_classes, debug=False, flip=True):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
# predictions
predictions = torch.Tensor(val_loader.dataset.__len__(), num_classes, 2)
# switch to evaluate mode
model.eval()
gt_win, pred_win = None, None
end = time.time()
bar = Bar('Processing', max=len(val_loader))
for i, (inputs, target, meta) in enumerate(val_loader):
# measure data loading time
data_time.update(time.time() - end)
target = target.cuda(async=True)
input_var = torch.autograd.Variable(inputs.cuda(), volatile=True)
target_var = torch.autograd.Variable(target, volatile=True)
# compute output
output = model(input_var)
score_map = output[-1].data.cpu()
if flip:
flip_input_var = torch.autograd.Variable(
torch.from_numpy(
fliplr(inputs.clone().numpy())).float().cuda(),
volatile=True
)
flip_output_var = model(flip_input_var)
flip_output = flip_back(flip_output_var[-1].data.cpu())
score_map += flip_output
loss = 0
for o in output:
loss += criterion(o, target_var)
acc = accuracy_segm(score_map, target.cpu())
if debug:
for j in range(len(score_map)):
save_im_in(inputs[j], "debug/test_in_{}.jpg".format(j))
save_im_out(score_map[j, 0, :, :],
"debug/test_out_{}.jpg".format(j))
save_im_out(target[j, 0, :, :],
"debug/test_target_{}.jpg".format(j))
# measure accuracy and record loss
losses.update(loss.data[0], inputs.size(0))
acces.update(acc[0], inputs.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
# plot progress
bar.suffix = '({batch}/{size}) Data: {data:.6f}s | Batch: {bt:.3f}s | Total: {total:} | ETA: {eta:} | Loss: {loss:.4f} | Acc: {acc: .4f}'.format(
batch=i + 1,
size=len(val_loader),
data=data_time.val,
bt=batch_time.avg,
total=bar.elapsed_td,
eta=bar.eta_td,
loss=losses.avg,
acc=acces.avg
)
bar.next()
bar.finish()
return losses.avg, acces.avg
def validate(val_loader,
model,
criterion,
num_classes,
args,
flip=False,
test_batch=6):
batch_time = AverageMeter()
data_time = AverageMeter()
acces = AverageMeter()
pck_score = np.zeros(num_classes)
pck_count = np.zeros(num_classes)
# predictions
predictions = torch.Tensor(val_loader.dataset.__len__(), num_classes, 2)
# switch to evaluate mode
model.eval()
end = time.time()
bar = Bar('Eval ', max=len(val_loader))
with torch.no_grad():
for i, (input, target, meta) in enumerate(val_loader):
# measure data loading time
data_time.update(time.time() - end)
input = input.to(device, non_blocking=True)
target = target.to(device, non_blocking=True)
output, output_refine = model(input, 1, return_domain=False)
score_map = output_refine[0].cpu()
if flip:
flip_input = torch.from_numpy(
fliplr(input.clone().cpu().numpy())).float().to(device)
_, flip_output_refine = model(flip_input,
1,
return_domain=False)
flip_output = flip_output_refine[0].cpu()
flip_output = flip_back(flip_output, 'real_animal')
score_map += flip_output
acc, _ = accuracy_2animal(score_map, target.cpu(), idx1, idx2)
# cal per joint [email protected]
for j in range(num_classes):
if acc[j + 1] > -1:
pck_score[j] += acc[j + 1].numpy()
pck_count[j] += 1
# generate predictions
preds = final_preds(score_map, meta['center'], meta['scale'],
[64, 64])
for n in range(score_map.size(0)):
predictions[meta['index'][n], :, :] = preds[n, :, :]
# measure accuracy and record loss
acces.update(acc[0], input.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
# plot progress
bar.suffix = '({batch}/{size}) Data: {data:.3f}s | Batch: {bt:.3f}s | Total: {total:} | ETA: {eta:} | Acc: {acc: .8f}'.format(
batch=i + 1,
size=len(val_loader),
data=data_time.val,
bt=batch_time.avg,
total=bar.elapsed_td,
eta=bar.eta_td,
acc=acces.avg)
bar.next()
bar.finish()
for j in range(num_classes):
pck_score[j] /= float(pck_count[j])
print("\nper joint [email protected]:")
print('Animal: {}, total number of joints: {}'.format(
args.animal, pck_count.sum()))
print(list(pck_score))
parts = {
'eye': [0, 1],
'chin': [2],
'hoof': [3, 4, 5, 6],
'hip': [7],
'knee': [8, 9, 10, 11],
'shoulder': [12, 13],
'elbow': [14, 15, 16, 17]
}
for p in parts.keys():
part = parts[p]
score = 0.
count = 0.
for joint in part:
score += pck_score[joint] * pck_count[joint]
count += pck_count[joint]
print('\n Joint {}: {} '.format(p, score / count))
return _, acces.avg, predictions
def validate(val_loader,
model,
criterion,
debug=False,
flip=True,
test_batch=6,
njoints=68):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
# predictions
predictions = torch.Tensor(val_loader.dataset.__len__(), njoints, 2)
# switch to evaluate mode
model.eval()
gt_win, pred_win = None, None
end = time.time()
bar = Bar('Eval ', max=len(val_loader))
interocular_dists = torch.zeros((njoints, val_loader.dataset.__len__()))
with torch.no_grad():
for i, (input, target, meta) in enumerate(val_loader):
# measure data loading time
data_time.update(time.time() - end)
input = input.to(device, non_blocking=True)
target = target.to(device, non_blocking=True)
target_weight = meta['target_weight'].to(device, non_blocking=True)
# compute output
output = model(input)
score_map = output[-1].cpu() if type(
output) == list else output.cpu()
if flip:
flip_input = torch.from_numpy(fliplr(
input.clone().numpy())).float().to(device)
flip_output = model(flip_input)
flip_output = flip_output[-1].cpu() if type(
flip_output) == list else flip_output.cpu()
flip_output = flip_back(flip_output)
score_map += flip_output
if type(output) == list: # multiple output
loss = 0
for o in output:
loss += criterion(o, target, target_weight, len(idx))
output = output[-1]
else: # single output
loss = criterion(output, target, target_weight, len(idx))
acc, batch_interocular_dists = accuracy(score_map, target.cpu(),
idx)
interocular_dists[:, i * test_batch:(i + 1) *
test_batch] = batch_interocular_dists
# generate predictions
preds = final_preds(score_map, meta['center'], meta['scale'],
[64, 64])
for n in range(score_map.size(0)):
predictions[meta['index'][n], :, :] = preds[n, :, :]
if debug:
gt_batch_img = batch_with_heatmap(input, target)
pred_batch_img = batch_with_heatmap(input, score_map)
if not gt_win or not pred_win:
plt.subplot(121)
gt_win = plt.imshow(gt_batch_img)
plt.subplot(122)
pred_win = plt.imshow(pred_batch_img)
else:
gt_win.set_data(gt_batch_img)
pred_win.set_data(pred_batch_img)
plt.pause(.05)
plt.draw()
# measure accuracy and record loss
losses.update(loss.item(), input.size(0))
acces.update(acc[0], input.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
# plot progress
bar.suffix = '({batch}/{size}) Data: {data:.3f}s | Batch: {bt:.3f}s | Total: {total:} | ETA: {eta:} | Loss: {loss:.8f} | Acc: {acc: .8f}'.format(
batch=i + 1,
size=len(val_loader),
data=data_time.val,
bt=batch_time.avg,
total=bar.elapsed_td,
eta=bar.eta_td,
loss=losses.avg,
acc=acces.avg)
bar.next()
bar.finish()
idx_array = np.array(idx) - 1
interocular_dists_pickup = interocular_dists[idx_array, :]
mean_error = torch.mean(
interocular_dists_pickup[interocular_dists_pickup != -1])
auc = calc_metrics(interocular_dists,
idx) # this is auc of predicted maps and target.
#print("=> Mean Error: {:.8f}, [email protected]: {:.8f} based on maps".format(mean_error, auc))
return losses.avg, acces.avg, predictions, auc, mean_error
def validate(self):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
predictions = torch.Tensor(self.val_loader.dataset.__len__(),
self.num_classes, 2)
self.netG.eval()
gt_win, pred_win = None, None
end = time.time()
bar = Bar('Eval ', max=len(self.val_loader))
with torch.no_grad():
for i, (input, target, meta, mpii) in enumerate(self.val_loader):
if mpii == False:
continue
data_time.update(time.time() - end)
input = input.to(self.device, non_blocking=True)
target = target.to(self.device, non_blocking=True)
target_weight = meta['target_weight'].to(self.device,
non_blocking=True)
output = self.netG(input)
score_map = output[-1].cpu() if type(
output) == list else output.cpu()
if self.flip:
flip_input = torch.from_numpy
flip_output = self.netG(flip_input)
flip_output = flip_output[-1].cpu() if type(
flip_output) == list else flip_output.cpu()
flip_output = flip_back(flip_output)
score_map += flip_output
if type(output) == list:
loss = 0
for o in output:
loss += self.criterion(o, target, target_weight)
output = output[-1]
else:
loss = self.criterion(output, target, target_weight)
acc = accuracy(score_map, target.cpu(), self.idx)
preds = final_preds(score_map, meta['center'], meta['scale'],
[64, 64])
for n in range(score_map.size(0)):
predictions[meta['index'][n], :, :] = preds[n, :, :]
if self.debug:
gt_batch_img = batch_with_heatmap(input, target)
pred_batch_img = batch_with_heatmap(input, score_map)
if not gt_win or not pred_win:
plt.subplot(121)
gt_win = plt.imshow(gt_batch_img)
plt.subplot(122)
pred_win = plt.imshow(pred_batch_img)
else:
gt_win.set_data(gt_batch_img)
pred_win.set_data(pred_batch_img)
plt.pause(.05)
plt.draw()
losses.update(loss.item, input.size(0))
acces.update(acc[0], input.size(0))
batch_time.update(time.time() - end)
end = time.time()
bar.suffix = '({batch}/{size}) Data: {data:.6f}s | Batch: {bt:.3f}s | Total: {total:} | ETA: {eta:} | Loss: {loss:.4f} | Acc: {acc: .4f}'.format(
batch=i + 1,
size=len(self.val_loader),
data=data_time.val,
bt=batch_time.avg,
total=bar.elapsed_td,
eta=bar.eta_td,
loss=losses.avg,
acc=acces.avg)
bar.next()
bar.finish()
return losses.avg, acces.avg, predictions
def validate(val_loader,
model,
criterion,
flip=True,
test_batch=6,
njoints=18):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
# predictions
predictions = torch.Tensor(val_loader.dataset.__len__(), njoints, 2)
# switch to evaluate mode
model.eval()
gt_win, pred_win = None, None
end = time.time()
bar = Bar('Eval ', max=len(val_loader))
with torch.no_grad():
for i, (input, target, meta) in enumerate(val_loader):
# measure data loading time
data_time.update(time.time() - end)
input = input.to(device, non_blocking=True)
if global_animal == 'horse':
target = target.to(device, non_blocking=True)
target_weight = meta['target_weight'].to(device,
non_blocking=True)
elif global_animal == 'tiger':
target = target.to(device, non_blocking=True)
target_weight = meta['target_weight'].to(device,
non_blocking=True)
target = target[:,
np.array([
1, 2, 3, 4, 5, 6, 7, 8, 15, 16, 17, 18, 13,
14, 9, 10, 11, 12
]) - 1, :, :]
target_weight = target_weight[:,
np.array([
1, 2, 3, 4, 5, 6, 7, 8, 15,
16, 17, 18, 13, 14, 9, 10,
11, 12
]) - 1, :]
else:
raise Exception('please add new animal category')
# compute output
output = model(input)
score_map = output[-1].cpu() if type(
output) == list else output.cpu()
if flip:
flip_input = torch.from_numpy(fliplr(
input.clone().numpy())).float().to(device)
flip_output = model(flip_input)
flip_output = flip_output[-1].cpu() if type(
flip_output) == list else flip_output.cpu()
flip_output = flip_back(flip_output)
score_map += flip_output
if type(output) == list: # multiple output
loss = 0
for o in output:
loss += criterion(o, target, target_weight, len(idx))
output = output[-1]
else: # single output
loss = criterion(output, target, target_weight, len(idx))
acc, _ = accuracy(score_map, target.cpu(), idx)
# generate predictions
preds = final_preds(score_map, meta['center'], meta['scale'],
[64, 64])
#for n in range(score_map.size(0)):
# predictions[meta['index'][n], :, :] = preds[n, :, :]
# measure accuracy and record loss
losses.update(loss.item(), input.size(0))
acces.update(acc[0], input.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
# plot progress
bar.suffix = '({batch}/{size}) Data: {data:.3f}s | Batch: {bt:.3f}s | Total: {total:} | ETA: {eta:} | Loss: {loss:.8f} | Acc: {acc: .8f}'.format(
batch=i + 1,
size=len(val_loader),
data=data_time.val,
bt=batch_time.avg,
total=bar.elapsed_td,
eta=bar.eta_td,
loss=losses.avg,
acc=acces.avg)
bar.next()
bar.finish()
return losses.avg, acces.avg
def validate(val_loader,
model,
criterion,
criterion_seg,
debug=False,
flip=True,
test_batch=6,
njoints=68):
batch_time = AverageMeter()
data_time = AverageMeter()
losses_kpt = AverageMeter()
losses_seg = AverageMeter()
acces = AverageMeter()
inter_meter = AverageMeter()
union_meter = AverageMeter()
# predictions
predictions = torch.Tensor(val_loader.dataset.__len__(), njoints, 2)
# switch to evaluate mode
model.eval()
gt_win, pred_win = None, None
end = time.time()
bar = Bar('Eval ', max=len(val_loader))
interocular_dists = torch.zeros((njoints, val_loader.dataset.__len__()))
with torch.no_grad():
for i, (input, target, target_seg, meta) in enumerate(val_loader):
# measure data loading time
data_time.update(time.time() - end)
input, target, target_seg = input.to(device), target.to(
device, non_blocking=True), target_seg.to(device)
target_weight = meta['target_weight'].to(device, non_blocking=True)
# compute output
output_kpt, output_seg = model(input)
score_map = output_kpt[-1].cpu() if type(
output_kpt) == list else output_kpt.cpu()
if flip:
flip_input = torch.from_numpy(fliplr(
input.clone().numpy())).float().to(device)
flip_output = model(flip_input)
flip_output = flip_output[-1].cpu() if type(
flip_output) == list else flip_output.cpu()
flip_output = flip_back(flip_output)
score_map += flip_output
if type(output_kpt) == list: # multiple output
loss_kpt = 0
loss_seg = 0
for (o, o_seg) in zip(output_kpt, output_seg):
loss_kpt += criterion(o, target, target_weight, len(idx))
loss_seg += criterion_seg(o_seg, target_seg)
output = output_kpt[-1]
output_seg = output_seg[-1]
else: # single output
loss_kpt = criterion(output_kpt, target, target_weight,
len(idx))
loss_seg = criterion(output_seg, target_seg)
acc, batch_interocular_dists = accuracy(score_map, target.cpu(),
idx)
_, pred_seg = torch.max(output_seg, 1)
# generate predictions
preds = final_preds(score_map, meta['center'], meta['scale'],
[64, 64])
for n in range(score_map.size(0)):
predictions[meta['index'][n], :, :] = preds[n, :, :]
if debug:
gt_batch_img = batch_with_heatmap(input, target)
pred_batch_img = batch_with_heatmap(input, score_map)
if not gt_win or not pred_win:
plt.subplot(121)
gt_win = plt.imshow(gt_batch_img)
plt.subplot(122)
pred_win = plt.imshow(pred_batch_img)
else:
gt_win.set_data(gt_batch_img)
pred_win.set_data(pred_batch_img)
plt.pause(.05)
plt.draw()
# measure accuracy and record loss
losses_kpt.update(loss_kpt.item(), input.size(0))
losses_seg.update(loss_seg.item(), input.size(0))
acces.update(acc[0], input.size(0))
inter, union = inter_and_union(
pred_seg.data.cpu().numpy().astype(np.uint8),
target_seg.data.cpu().numpy().astype(np.uint8))
inter_meter.update(inter)
union_meter.update(union)
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
iou = inter_meter.sum / (union_meter.sum + 1e-10)
# plot progress
bar.suffix = '({batch}/{size}) Data: {data:.3f}s | Batch: {bt:.3f}s | Total: {total:} | ETA: {eta:} | Loss_kpt: {loss_kpt:.8f} | Loss_seg: {loss_seg:.8f} | Acc: {acc: .8f} | IOU: {iou:.2f}'.format(
batch=i + 1,
size=len(val_loader),
data=data_time.val,
bt=batch_time.avg,
total=bar.elapsed_td,
eta=bar.eta_td,
loss_kpt=losses_kpt.avg,
loss_seg=losses_seg.avg,
acc=acces.avg,
iou=iou.mean() * 100)
bar.next()
bar.finish()
print(iou)
return losses_kpt.avg, acces.avg, predictions, iou.mean() * 100
def validate(config,
val_loader,
val_dataset,
model,
criterion,
output_dir,
tb_log_dir,
writer_dict=None):
batch_time = AverageMeter()
losses = AverageMeter()
acc = AverageMeter()
# switch to evaluate mode
model.eval()
num_samples = len(val_dataset)
all_preds = np.zeros((num_samples, config.MODEL.NUM_JOINTS, 3),
dtype=np.float32)
all_boxes = np.zeros((num_samples, 6))
image_path = []
image_ids = []
bbox_infos = []
filenames = []
imgnums = []
idx = 0
with torch.no_grad():
end = time.time()
for i, (input, target, target_weight, meta) in enumerate(val_loader):
# compute output
output = model(input)
if config.TEST.FLIP_TEST:
# this part is ugly, because pytorch has not supported negative index
# input_flipped = model(input[:, :, :, ::-1])
input_flipped = np.flip(input.cpu().numpy(), 3).copy()
input_flipped = torch.from_numpy(input_flipped).cuda()
output_flipped = model(input_flipped)
output_flipped = flip_back(output_flipped.cpu().numpy(),
val_dataset.flip_pairs)
output_flipped = torch.from_numpy(output_flipped.copy()).cuda()
# feature is not aligned, shift flipped heatmap for higher accuracy
if config.TEST.SHIFT_HEATMAP:
output_flipped[:, :, :, 1:] = \
output_flipped.clone()[:, :, :, 0:-1]
# output_flipped[:, :, :, 0] = 0
output = (output + output_flipped) * 0.5
target = target.cuda(non_blocking=True)
target_weight = target_weight.cuda(non_blocking=True)
loss = criterion(output, target, target_weight)
num_images = input.size(0)
# measure accuracy and record loss
losses.update(loss.item(), num_images)
_, avg_acc, cnt, pred = accuracy(output.cpu().numpy(),
target.cpu().numpy())
acc.update(avg_acc, cnt)
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
c = meta['center'].numpy()
s = meta['scale'].numpy()
score = meta['score'].numpy()
preds, maxvals = get_final_preds(config,
output.clone().cpu().numpy(), c,
s)
all_preds[idx:idx + num_images, :, 0:2] = preds[:, :, 0:2]
all_preds[idx:idx + num_images, :, 2:3] = maxvals
# double check this all_boxes parts
all_boxes[idx:idx + num_images, 0:2] = c[:, 0:2]
all_boxes[idx:idx + num_images, 2:4] = s[:, 0:2]
all_boxes[idx:idx + num_images, 4] = np.prod(s * 200, 1)
all_boxes[idx:idx + num_images, 5] = score
image_path.extend(meta['image'])
if 'image_id' in meta:
image_ids.extend(meta['image_id'].numpy())
#print(meta['image_id'])
# for posetrack dataset, im_bbox must be considered
if 'im_bbox' in meta:
now_boxes = meta['im_bbox']
bbox_infos.extend(now_boxes.numpy())
if config.DATASET.DATASET == 'posetrack':
filenames.extend(meta['filename'])
imgnums.extend(meta['imgnum'].numpy())
idx += num_images
if i % config.PRINT_FREQ == 0:
msg = 'Test: [{0}/{1}]\t' \
'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\t' \
'Loss {loss.val:.4f} ({loss.avg:.4f})\t' \
'Accuracy {acc.val:.3f} ({acc.avg:.3f})'.format(
i, len(val_loader), batch_time=batch_time,
loss=losses, acc=acc)
logger.info(msg)
prefix = '{}_{}'.format(os.path.join(output_dir, 'val'), i)
save_debug_images(config, input, meta, target, pred * 4,
output, prefix)
name_values, perf_indicator = val_dataset.evaluate(
config, all_preds, output_dir, all_boxes, image_path, image_ids,
bbox_infos)
_, full_arch_name = get_model_name(config)
if isinstance(name_values, list):
for name_value in name_values:
_print_name_value(name_value, full_arch_name)
else:
_print_name_value(name_values, full_arch_name)
if writer_dict:
writer = writer_dict['writer']
global_steps = writer_dict['valid_global_steps']
writer.add_scalar('valid_loss', losses.avg, global_steps)
writer.add_scalar('valid_acc', acc.avg, global_steps)
if isinstance(name_values, list):
for name_value in name_values:
writer.add_scalars('valid', dict(name_value), global_steps)
else:
writer.add_scalars('valid', dict(name_values), global_steps)
writer_dict['valid_global_steps'] = global_steps + 1
return perf_indicator
def validate(val_loader,
model,
criterion,
debug=False,
flip=True,
test_batch=6,
njoints=68):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces_re = AverageMeter()
# switch to evaluate mode
model.eval()
gt_win, pred_win = None, None
end = time.time()
bar = Bar('Eval ', max=len(val_loader))
with torch.no_grad():
for i, (input, target, meta) in enumerate(val_loader):
# measure data loading time
data_time.update(time.time() - end)
input = input.to(device, non_blocking=True)
target = target.to(device, non_blocking=True)
target_weight = meta['target_weight'].to(device, non_blocking=True)
# compute output
output, output_refine = model(input)
score_map = output[-1].cpu() if type(
output) == list else output.cpu()
score_map_refine = output_refine[-1].cpu() if type(
output_refine) == list else output_refine.cpu()
if flip:
flip_input = torch.from_numpy(fliplr(
input.clone().numpy())).float().to(device)
flip_output, flip_output_re = model(flip_input)
flip_output = flip_output[-1].cpu() if type(
flip_output) == list else flip_output.cpu()
flip_output_re = flip_output_re[-1].cpu() if type(
flip_output_re) == list else flip_output_re.cpu()
flip_output = flip_back(flip_output, 'real_animal')
flip_output_re = flip_back(flip_output_re, 'real_animal')
score_map += flip_output
score_map_refine += flip_output_re
if type(output) == list: # multiple output
loss = 0
for (o, o_re) in (output, output_refine):
loss = loss + criterion(
o, target, target_weight, len(idx)) + criterion(
o_re, target, target_weight, len(idx))
else: # single output
loss = criterion(
output, target, target_weight, len(idx)) + criterion(
output_refine, target, target_weight, len(idx))
acc_re, _ = accuracy(score_map_refine, target.cpu(), idx)
if debug:
gt_batch_img = batch_with_heatmap(input, target)
pred_batch_img = batch_with_heatmap(input, score_map)
if not gt_win or not pred_win:
plt.subplot(121)
gt_win = plt.imshow(gt_batch_img)
plt.subplot(122)
pred_win = plt.imshow(pred_batch_img)
else:
gt_win.set_data(gt_batch_img)
pred_win.set_data(pred_batch_img)
plt.pause(.05)
plt.draw()
# measure accuracy and record loss
losses.update(loss.item(), input.size(0))
acces_re.update(acc_re[0], input.size(0))
# measure elapsed time
batch_time.update(time.time() - end)
end = time.time()
# plot progress
bar.suffix = '({batch}/{size}) Data: {data:.3f}s | Batch: {bt:.3f}s | Total: {total:} | ETA: {eta:} ' \
'| Loss: {loss:.8f} | Acc_re: {acc_re: .8f}'.format(
batch=i + 1,
size=len(val_loader),
data=data_time.val,
bt=batch_time.avg,
total=bar.elapsed_td,
eta=bar.eta_td,
loss=losses.avg,
acc_re=acces_re.avg
)
bar.next()
bar.finish()
return losses.avg, acces_re.avg
