def train(train_loader, model, criterion, optimizer, idx, flip=True):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
# switch to train mode
model.train()
end = time.time()
gt_win, pred_win = None, None
bar = Bar('Processing', max=len(train_loader))
for i, (inputs, target, meta) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
input_var = torch.autograd.Variable(inputs.to(device=device))
target_var = torch.autograd.Variable(
target.to(device=device, non_blocking=True))
# compute output
output = model(input_var)
score_map = output[-1].data.cpu()
loss = criterion(output[0], target_var)
for j in range(1, len(output)):
loss += criterion(output[j], target_var)
acc = accuracy(score_map, target, idx, pck_threshold)
# measure accuracy and record loss
losses.update(loss.item(), inputs.size(0))
acces.update(acc[0], inputs.size(0))
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 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(train_loader),
data=data_time.val,
bt=batch_time.val,
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):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
# predictions
predictions = torch.Tensor(val_loader.dataset.__len__(), 12)
# switch to evaluate mode
model.eval()
end = time.time()
bar = Bar('Processing', max=len(val_loader))
for i, (inputs, target) in enumerate(val_loader):
# measure data loading time
data_time.update(time.time() - end)
input_var = torch.autograd.Variable(inputs.cuda())
input_var = input_var.unsqueeze(0)
input_var = input_var.type(torch.FloatTensor)
target_var = torch.autograd.Variable(target)
target_var = target_var.type(torch.FloatTensor)
target_var = target_var.cuda()
# compute output
output = model(input_var)
output = output.unsqueeze(0)
loss = criterion(output, target_var)
acc = accuracy(output.detach(), target.cpu())
# generate predictions
predictions[i] = output.detach()
# measure accuracy and record loss
losses.update(loss.item(), inputs.size(0))
acces.update(acc, 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:.6f} | 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 train(train_loader, model, criterion, optimizer):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
# switch to train mode
model.train()
end = time.time()
bar = Bar('Processing', max=len(train_loader))
for i, (inputs, target) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
# target = target.cuda(async=True)
input_var = torch.autograd.Variable(inputs.cuda())
input_var = input_var.unsqueeze(0)
input_var = input_var.type(torch.FloatTensor)
target_var = torch.autograd.Variable(target)
target_var = target_var.type(torch.FloatTensor)
target_var = target_var.cuda()
# compute output
output = model(input_var)
output = output.unsqueeze(0)
loss = criterion(output, target_var)
acc = accuracy(output.detach(), target.cpu())
# measure accuracy and record loss
losses.update(loss.item(), inputs.size(0))
acces.update(acc, inputs.size(0))
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 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:.6f} | Acc: {acc: .4f}'.format(
batch=i + 1,
size=len(train_loader),
data=data_time.val,
bt=batch_time.val,
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 train(train_loader, model, criterion, optimizer, debug=False, flip=True):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
# switch to train mode
model.train()
end = time.time()
gt_win, pred_win = None, None
bar = Bar('Train', max=len(train_loader))
for i, (input, target, meta) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
input, target = input.to(device), target.to(device, non_blocking=True)
target_weight = meta['target_weight'].to(device, non_blocking=True)
# compute output
output = model(input)
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(output, target, idx)
if debug: # visualize groundtruth and predictions
gt_batch_img = batch_with_heatmap(input, target)
pred_batch_img = batch_with_heatmap(input, output)
if not gt_win or not pred_win:
ax1 = plt.subplot(121)
ax1.title.set_text('Groundtruth')
gt_win = plt.imshow(gt_batch_img)
ax2 = plt.subplot(122)
ax2.title.set_text('Prediction')
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))
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 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(train_loader),
data=data_time.val,
bt=batch_time.val,
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, 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 train(train_loader, model, tmodel, criterion, optimizer, kdloss_alpha, debug=False, flip=True):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
kdlosses = AverageMeter()
unkdlosses = AverageMeter()
tslosses = AverageMeter()
gtlosses = AverageMeter()
acces = AverageMeter()
# switch to train mode
model.train()
end = time.time()
gt_win, pred_win = None, None
bar = Bar('Processing', max=len(train_loader))
for i, (inputs, target, meta) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
input_var = torch.autograd.Variable(inputs.cuda())
target_var = torch.autograd.Variable(target.cuda(async=True))
# compute output
output = model(input_var)
score_map = output[-1].data.cpu()
# compute teacher network output
toutput = tmodel(input_var)
toutput = toutput[-1].detach()
# lmse : student vs ground truth
# gtmask will filter out the samples without ground truth
gtloss = torch.tensor(0.0).cuda()
kdloss = torch.tensor(0.0).cuda()
kdloss_unlabeled = torch.tensor(0.0).cuda()
unkdloss_alpha = 1.0
gtmask = meta['gtmask']
train_batch = score_map.shape[0]
for j in range(0, len(output)):
_output = output[j]
for i in range(gtmask.shape[0]):
if gtmask[i] < 0.1:
# unlabeled data, gtmask=0.0, kdloss only
# need to dividen train_batch to keep number equal
kdloss_unlabeled += criterion(_output[i,:,:,:], toutput[i, :,:,:])/train_batch
else:
# labeled data: kdloss + gtloss
gtloss += criterion(_output[i,:,:,:], target_var[i, :,:,:])/train_batch
kdloss += criterion(_output[i,:,:,:], toutput[i,:,:,:])/train_batch
loss_labeled = kdloss_alpha * (kdloss) + (1 - kdloss_alpha)*gtloss
total_loss = loss_labeled + unkdloss_alpha * kdloss_unlabeled
acc = accuracy(score_map, target, idx)
if debug: # visualize groundtruth and predictions
gt_batch_img = batch_with_heatmap(inputs, target)
pred_batch_img = batch_with_heatmap(inputs, score_map)
teacher_batch_img = batch_with_heatmap(inputs, toutput)
if not gt_win or not pred_win or not pred_teacher:
ax1 = plt.subplot(131)
ax1.title.set_text('Groundtruth')
gt_win = plt.imshow(gt_batch_img)
ax2 = plt.subplot(132)
ax2.title.set_text('Prediction')
pred_win = plt.imshow(pred_batch_img)
ax2 = plt.subplot(133)
ax2.title.set_text('teacher')
pred_teacher = plt.imshow(teacher_batch_img)
else:
gt_win.set_data(gt_batch_img)
pred_win.set_data(pred_batch_img)
pred_teacher.set_data(teacher_batch_img)
plt.pause(.05)
plt.draw()
# measure accuracy and record loss
gtlosses.update(gtloss.item(), inputs.size(0))
kdlosses.update(kdloss.item(), inputs.size(0))
unkdlosses.update(kdloss_unlabeled.item(), inputs.size(0))
losses.update(total_loss.item(), inputs.size(0))
acces.update(acc[0], inputs.size(0))
# compute gradient and do SGD step
optimizer.zero_grad()
total_loss.backward()
optimizer.step()
# 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:.6f} | KdLoss:{kdloss:.6f}| unKdLoss:{unkdloss:.6f}| GtLoss:{gtloss:.6f} | Acc: {acc: .4f}'.format(
batch=i + 1,
size=len(train_loader),
data=data_time.val,
bt=batch_time.val,
total=bar.elapsed_td,
eta=bar.eta_td,
loss=losses.avg,
kdloss=kdlosses.avg,
unkdloss=unkdlosses.avg,
tsloss=tslosses.avg,
gtloss=gtlosses.avg,
acc=acces.avg
)
bar.next()
bar.finish()
return losses.avg, acces.avg
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,
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 train(train_loader,
model,
criterion,
criterion_seg,
optimizer,
debug=False,
flip=True,
train_batch=6,
epoch=0,
njoints=68):
batch_time = AverageMeter()
data_time = AverageMeter()
losses_kpt = AverageMeter()
losses_seg = AverageMeter()
acces = AverageMeter()
inter_meter = AverageMeter()
union_meter = AverageMeter()
# switch to train mode
model.train()
end = time.time()
gt_win, pred_win = None, None
bar = Bar('Train', max=len(train_loader))
for i, (input, target, target_seg, meta) in enumerate(train_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)
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_kpt = output_kpt[-1]
output_seg = output_seg[-1]
else: # single output
loss_kpt = criterion(output_kpt, target, target_weight, len(idx))
loss_seg = criterion_seg(output_seg, target_seg)
acc, batch_interocular_dists = accuracy(output_kpt, target, idx)
_, pred_seg = torch.max(output_seg, 1)
if debug: # visualize groundtruth and predictions
gt_batch_img = batch_with_heatmap(input, target)
pred_batch_img = batch_with_heatmap(input, output)
if not gt_win or not pred_win:
ax1 = plt.subplot(121)
ax1.title.set_text('Groundtruth')
gt_win = plt.imshow(gt_batch_img)
ax2 = plt.subplot(122)
ax2.title.set_text('Prediction')
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()
loss = loss_kpt + (0.01 / (epoch + 1)) * loss_seg
# 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)
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 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: .4f} | IOU: {iou: .2f}'.format(
batch=i + 1,
size=len(train_loader),
data=data_time.val,
bt=batch_time.val,
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
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, target2, meta) in enumerate(val_loader):
# measure data loading time
data_time.update(time.time() - end)
target = target.cuda(async=True)
target2 = target2.cuda(async=True)
input_var = torch.autograd.Variable(inputs.cuda(), volatile=True)
target_var = torch.autograd.Variable(target, volatile=True)
target2_var = torch.autograd.Variable(target2, volatile=True)
# compute output
output = model(input_var)
score_map_hg = output[-2].data.cpu()
score_map_emb = output[-1].data.cpu()
score_map_emb2 = score_map_emb.cuda(async=True)
loss = criterion(output[0], target_var)
for j in range(1, (len(output) - 1)):
loss += criterion(output[j], target_var)
loss += criterion(output[-1], target2_var)
acc = accuracy(score_map_emb2, target2, idx)
# generate predictions
#print(np.shape(predictions))
preds = final_preds(score_map_emb, meta['center'], meta['scale'],
[64, 64])
for n in range(score_map_emb.size(0)):
predictions[meta['index'][n], :, :] = preds[n, ::2, :]
#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_emb)
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.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, predictions
def myvalidate( model, criterion, num_classes, debug=False, flip=True):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
img_folder = '/data3/wzwu/dataset/my'
img_num = 1
r = 0
center1 = torch.Tensor([1281,2169])
center2 = torch.Tensor([[1281,2169]])
scale = torch.Tensor([10.0])
inp_res = 256
meanstd_file = './data/mpii/mean.pth.tar'
if isfile(meanstd_file):
meanstd = torch.load(meanstd_file)
mean = meanstd['mean']
std = meanstd['std']
input_list = []
for i in range(img_num):
img_name = str(i)+'.jpg'
img_path = os.path.join(img_folder,img_name)
print('img_path')
print(img_path)
set_trace()
img = load_image(img_path)
inp = crop(img, center1, scale, [inp_res, inp_res], rot=r)
inp = color_normalize(inp, mean, std)
input_list.append(inp)
# predictions
predictions = torch.Tensor(img_num, num_classes, 2)
# switch to evaluate mode
model.eval()
gt_win, pred_win = None, None
end = time.time()
bar = Bar('Eval ', max=img_num)
with torch.no_grad():
for i, input in enumerate(input_list):
# measure data loading time
s0, s1, s2 = input.size()
input = input.view(1, s0, s1, s2)
data_time.update(time.time() - end)
input = input.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
# generate predictions
set_trace()
preds = final_preds(score_map, center2, scale, [64, 64])
set_trace()
print('preds')
print(preds)
print('predictions')
print(predictions)
for n in range(score_map.size(0)):
predictions[i, :, :] = preds[n, :, :]
if debug:
pred_batch_img = batch_with_heatmap(input, score_map)
if not gt_win or not pred_win:
#plt.subplot(121)
#plt.subplot(122)
pred_win = plt.imshow(pred_batch_img)
else:
pred_win.set_data(pred_batch_img)
plt.pause(.05)
plt.draw()
plt.savefig('/data3/wzwu/test/'+str(i)+'.png')
# 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=img_num,
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 predictions
def train(train_loader, model, criterion, optimizer, debug=False, flip=True):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
# switch to train mode
model.train()
end = time.time()
gt_win, pred_win = None, None
bar = Bar('Processing', max=len(train_loader))
for i, (inputs, target, meta) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
input_var = torch.autograd.Variable(inputs.cuda())
target_var = torch.autograd.Variable(target.cuda(async=True))
# compute output
output = model(input_var)
score_map = output[-1].data.cpu()
loss = criterion(output[0], target_var)
for j in range(1, len(output)):
loss += criterion(output[j], target_var)
acc = accuracy_segm(score_map, target)
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))
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 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(train_loader),
data=data_time.val,
bt=batch_time.val,
total=bar.elapsed_td,
eta=bar.eta_td,
loss=losses.avg,
acc=acces.avg
)
bar.next()
bar.finish()
return losses.avg, acces.avg
def train(train_loader,
model,
criterion,
optimizer,
debug=False,
flip=True,
train_iters=0):
print("Train iters: {}".format(train_iters))
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
# switch to train mode
model.train()
debug_count = 0
end = time.time()
gt_win, pred_win = None, None
bar_len = [train_iters if train_iters != 0 else len(train_loader)][0]
train_iters = [train_iters if train_iters != 0 else len(train_loader)][0]
bar = Bar('Train', max=bar_len)
curr_iter = 0
while curr_iter < train_iters:
for i, (input, target, meta) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
input, target = input.to(device), target.to(device,
non_blocking=True)
target_weight = meta['target_weight'].to(device, non_blocking=True)
# compute output
output = model(input)
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(output, target, idx)
if debug: # visualize groundtruth and predictions
gt_batch_img = batch_with_heatmap(input, target)
pred_batch_img = batch_with_heatmap(input, output)
fig = plt.figure()
ax1 = fig.add_subplot(121)
ax1.title.set_text('Groundtruth')
gt_win = plt.imshow(gt_batch_img)
ax2 = fig.add_subplot(122)
ax2.title.set_text('Prediction')
pred_win = plt.imshow(pred_batch_img)
plt.pause(.05)
plt.draw()
fig.savefig('debug/debug_{}.png'.format(str(debug_count)),
dpi=500)
debug_count += 1
# measure accuracy and record loss
losses.update(loss.item(), input.size(0))
acces.update(acc[0], input.size(0))
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 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(train_loader) if train_iters == 0 else train_iters
][0],
data=data_time.val,
bt=batch_time.val,
total=bar.elapsed_td,
eta=bar.eta_td,
loss=losses.avg,
acc=acces.avg)
bar.next()
curr_iter += 1
if curr_iter >= train_iters - 1:
break
bar.finish()
return losses.avg, acces.avg
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 train(inqueues,
outqueues,
train_loader,
model,
criterion,
optimizer,
debug=False,
flip=True,
clip=1,
_logger=None):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
sum_losses = AverageMeter()
# switch to train mode
model.train()
criterion.valid = False
end = time.time()
gt_win, pred_win = None, None
bar = Bar('Processing', max=len(train_loader))
for i, (inputs, target, meta) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
if True:
input_var = torch.autograd.Variable(inputs.cuda())
target_var = torch.autograd.Variable(target.cuda(async=True))
# compute output
output = model(input_var)
if len(inqueues) > 0:
loss = []
acc = []
sum_loss = []
for j in range(len(output)):
grad = []
for ii in range(output[0].size(0)):
data = {}
data['output'] = output[j][ii]
data['meta'] = {}
data['meta']['bi_target'] = meta['bi_target'][ii]
data['meta']['pck'] = meta['pck'][ii]
data['meta']['points'] = meta['points'][ii]
data['meta']['tpts'] = meta['tpts'][ii]
inqueues[ii].send(data)
for ii in range(output[0].size(0)):
_loss, _acc, _sum_loss, _grad = outqueues[ii].recv()
loss.append(_loss)
grad.append(_grad)
if j == len(output) - 1:
acc.append(_acc)
sum_loss.append(_sum_loss)
optimizer.zero_grad()
output[0].backward(torch.stack(grad, 0))
torch.nn.utils.clip_grad_norm_(model.parameters(), clip)
optimizer.step()
loss = sum(loss) / output[0].size(0)
acc = sum(acc) / output[0].size(0)
sum_loss = sum(sum_loss) / output[0].size(0)
else:
optimizer.zero_grad()
loss, acc, sum_loss = criterion(output[0], meta)
for j in range(1, len(output)):
_loss, acc, sum_loss = criterion(output[j], meta)
loss += _loss
loss.backward()
optimizer.step()
if debug: # visualize groundtruth and predictions
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:
ax1 = plt.subplot(121)
ax1.title.set_text('Groundtruth')
gt_win = plt.imshow(gt_batch_img)
ax2 = plt.subplot(122)
ax2.title.set_text('Prediction')
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.data.item(), inputs.size(0))
acces.update(acc.item(), inputs.size(0))
sum_losses.update(sum_loss)
loss = None
torch.cuda.empty_cache()
# 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} | Sum_Loss: {sum_loss:.4f} | Acc: {acc: .4f}'.format(
batch=i + 1,
size=len(train_loader),
data=data_time.val,
bt=batch_time.val,
total=bar.elapsed_td,
loss=losses.avg * 100,
sum_loss=sum_losses.avg * 100,
acc=acces.avg * 100)
_logger.info(bar.suffix)
bar.finish()
return losses.avg * 100, acces.avg * 100
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(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,
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 train(self, gen_iterations, start_t, epoch, lr):
batch_time = AverageMeter()
data_time = AverageMeter()
self.netG.train()
end = time.time()
gt_win, pred_win = None, None
bar = Bar('Train', max=len(self.train_loader))
step = 0
errD_total = None
errG_total = None
for i, (input, target, meta, mpii) in enumerate(self.train_loader):
data_time.update(time.time() - end)
######################################################
# (1) Prepare training data and Compute text embeddings
######################################################
input, target = input.to(self.device), target.to(self.device,
non_blocking=True)
target_weight = meta['target_weight'].to(self.device,
non_blocking=True)
#######################################################
# (2) Generate fake heatmaps
######################################################
output = self.netG(input)
#######################################################
# (3) Update D network
######################################################
errD_total = 0
D_logs = ''
for i in range(self.num_stacks):
self.netsD[i].zero_grad()
errD = discriminator_loss(self.netsD[i], target, target_weight,
output[i], input, self.real_labels,
self.fake_labels, mpii)
errD.backword()
self.optimizersD[i].step()
errD_total += errD
D_logs += 'errD%d: %d.2f ' % (i, errD.data[0])
#######################################################
# (4) Update G network: maximize log(D(G(z)))
######################################################
step += 1
gen_iterations += 1
self.netG.zero_grad()
errG_total, G_logs = \
generator_loss(self.netsD, self.domainD, output, self.real_labels, input, target_weight, mpii)
if self.debug:
gt_batch_img = batch_with_heatmap(input, target)
pred_batch_img = batch_with_heatmap(input, output)
if not gt_win or not pred_win:
ax1 = plt.subplot(121)
ax1.title.set_text('Groundtruth')
gt_win = plt.imshow(gt_batch_img)
ax2 = plt.subplot(122)
ax2.title.set_text('Prediction')
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()
errG_total.backward()
self.optimizerG.step()
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:}'.format(
batch=i + 1,
size=len(self.train_loader),
data=data_time.val,
bt=batch_time.val,
total=bar.elapsed_td,
eta=bar.eta_td)
bar.next()
if gen_iterations % 100 == 0:
print(D_logs + '\n' + G_logs)
end_t = time.time()
print('''[%d/%d]
Loss_D: %.2f Loss_G: %.2f Time: %.2fs''' %
(epoch, self.epochs, errD_total.data[0], errG_total.data[0],
end_t - start_t))
if epoch % cfg.TRAIN.SNAPSHOT_INTERVAL == 0:
self.save_model(self.netsD, lr, epoch)
bar.finish()
def train(train_loader, model, criterion, optimizer, debug=False, flip=True):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
# switch to train mode
model.train()
end = time.time()
gt_win, pred_win = None, None
bar = Bar('Processing', max=len(train_loader))
for i, (inputs, target, meta) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
input_var = torch.autograd.Variable(inputs.cuda())
target_var = torch.autograd.Variable(target.cuda(async=True))
# compute output
output = model(input_var)
score_map = output[-1].data.cpu()
loss = criterion(output[0], target_var)
for j in range(1, len(output)):
loss += criterion(output[j], target_var)
acc = accuracy(score_map, target, idx)
if debug: # visualize groundtruth and predictions
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:
ax1 = plt.subplot(121)
ax1.title.set_text('Groundtruth')
gt_win = plt.imshow(gt_batch_img)
ax2 = plt.subplot(122)
ax2.title.set_text('Prediction')
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.data[0], inputs.size(0))
acces.update(acc[0], inputs.size(0))
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 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(train_loader),
data=data_time.val,
bt=batch_time.val,
total=bar.elapsed_td,
eta=bar.eta_td,
loss=losses.avg,
acc=acces.avg
)
bar.next()
bar.finish()
return losses.avg, acces.avg
def train(train_loader,
model,
criterion,
optimizer,
debug=False,
flip=True,
train_batch=6,
epoch=0,
njoints=68):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces = AverageMeter()
# switch to train mode
model.train()
end = time.time()
gt_win, pred_win = None, None
bar = Bar('Train', max=len(train_loader))
interocular_dists = torch.zeros((njoints, train_loader.dataset.__len__()))
for i, (input, target, meta) in enumerate(train_loader):
# measure data loading time
data_time.update(time.time() - end)
input, target = input.to(device), target.to(device, non_blocking=True)
target_weight = meta['target_weight'].to(device, non_blocking=True)
# compute output
output = model(input)
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(output, target, idx)
interocular_dists[:, i * train_batch:(i + 1) *
train_batch] = batch_interocular_dists
if debug: # visualize groundtruth and predictions
gt_batch_img = batch_with_heatmap(input, target)
pred_batch_img = batch_with_heatmap(input, output)
if not gt_win or not pred_win:
ax1 = plt.subplot(121)
ax1.title.set_text('Groundtruth')
gt_win = plt.imshow(gt_batch_img)
ax2 = plt.subplot(122)
ax2.title.set_text('Prediction')
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))
# compute gradient and do SGD step
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 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(train_loader),
data=data_time.val,
bt=batch_time.val,
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
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,
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