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.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,
num_classes,
out_res,
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(score_map, target.cpu(), idx)
# generate predictions
preds = final_preds(score_map, meta['center'], meta['scale'],
[out_res, out_res])
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[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 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 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,
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))
batch_loss = []
with torch.no_grad():
for i, (input, target) 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)
output = output[-1]
else: # single output
loss = criterion(output, target)
acc = accuracy(score_map, target.cpu(), idx)
batch_loss += [loss.item()]
# 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, np.mean(batch_loss)
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, 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))
batch_loss = []
for i, (input, target) 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:
#print(o.size(), target.size()); exit(1)
loss += criterion(o, target)
output = output[-1]
else: # single output
loss = criterion(output, target)
acc = accuracy(output, target, idx)
batch_loss += [loss.item()]
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, np.mean(batch_loss)
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,
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(non_blocking=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 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 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
def train(train_loader,
model,
criterion,
optimizer,
args,
debug=False,
flip=True,
train_batch=6,
epoch=0,
njoints=18):
batch_time = AverageMeter()
data_time = AverageMeter()
losses = AverageMeter()
acces_re = 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, output_re = model(input)
if type(output) == list: # multiple output
loss = 0
for (o, o_re) in zip(output, output_re):
loss = loss + criterion(
o, target, target_weight, len(idx)) + criterion(
o_re, target, target_weight, len(idx))
if args.self_kd:
soft_label = o_re.clone().detach().requires_grad_(False)
loss = loss + args.soft_weight * criterion(o, soft_label)
output = output[-1]
output_re = output_re[-1]
else: # single output
loss = criterion(output, target,
target_weight, len(idx)) + criterion(
output_re, target, target_weight, len(idx))
acc_re, _ = accuracy(output_re, 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_re.update(acc_re[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_re: {acc_re: .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_re=acces_re.avg
)
bar.next()
bar.finish()
return losses.avg, acces_re.avg