def main():
"""Create the model and start the evaluation process."""
args = get_arguments()
gpu0 = args.gpu
model = Res_Deeplab(num_classes=args.num_classes)
saved_state_dict = torch.load(args.restore_from)
model.load_state_dict(saved_state_dict)
model.eval()
model.cuda(gpu0)
testloader = data.DataLoader(VOCDataSet(args.data_dir,
args.data_list,
crop_size=(505, 505),
mean=IMG_MEAN,
scale=False,
mirror=False),
batch_size=1,
shuffle=False,
pin_memory=True)
interp = nn.Upsample(size=(505, 505), mode='bilinear')
data_list = []
for index, batch in enumerate(testloader):
if index % 100 == 0:
print('%d processd' % (index))
images, label, size, name = batch
images = Variable(images, volatile=True)
h, w, c = size[0].numpy()
images075 = nn.Upsample(size=(int(h * 0.75), int(w * 0.75)),
mode='bilinear')(images)
images05 = nn.Upsample(size=(int(h * 0.5), int(w * 0.5)),
mode='bilinear')(images)
out100 = model(images.cuda(args.gpu))
out075 = model(images075.cuda(args.gpu))
out05 = model(images05.cuda(args.gpu))
o_h, o_w = out100.size()[2:]
interpo1 = nn.Upsample(size=(o_h, o_w), mode='bilinear')
out_max = torch.max(torch.stack(
[out100, interpo1(out075),
interpo1(out05)]),
dim=0)[0]
output = interp(out_max).cpu().data[0].numpy()
output = output[:, :h, :w]
output = output.transpose(1, 2, 0)
output = np.asarray(np.argmax(output, axis=2), dtype=np.int)
gt = np.asarray(label[0].numpy()[:h, :w], dtype=np.int)
# show_all(gt, output)
data_list.append([gt.flatten(), output.flatten()])
get_iou(data_list, args.num_classes)
def main():
"""Create the model and start the evaluation process."""
args = get_arguments()
model = Res_Deeplab(num_classes=args.num_classes)
saved_state_dict = torch.load(args.restore_from)
model.load_state_dict(saved_state_dict)
model.eval()
if torch.cuda.is_available():
args.device = torch.device('cuda')
model = model.cuda()
print()
else:
args.device = torch.device('cpu')
print('the model is operating on {}'.format(args.device))
testloader = data.DataLoader(VOCDataSet(args.data_dir,
args.data_list,
hue_value=args.hue_value,
crop_size=(505, 505),
mean=IMG_MEAN,
scale=False,
mirror=False),
batch_size=1,
shuffle=False,
pin_memory=True)
interp = nn.Upsample(size=(505, 505), mode='bilinear')
data_list = []
for index, batch in enumerate(testloader):
if index % 100 == 0:
print('%d processd' % (index))
image, label, size, name = batch
image = image.to(device=args.device)
size = size[0].numpy()
output = model(Variable(image, volatile=True))
output = interp(output).cpu().data[0].numpy()
output = output[:, :size[0], :size[1]]
gt = np.asarray(label[0].numpy()[:size[0], :size[1]], dtype=np.int)
output = output.transpose(1, 2, 0)
output = np.asarray(np.argmax(output, axis=2), dtype=np.int)
# show_all(gt, output)
data_list.append([gt.flatten(), output.flatten()])
get_iou(data_list, args.num_classes, args.hue_value)
def main():
"""Create the model and start the evaluation process."""
args = get_arguments()
gpu0 = args.gpu
model = Res_Deeplab(num_classes=args.num_classes)
saved_state_dict = torch.load(args.restore_from)
model.load_state_dict(saved_state_dict)
model.eval()
model.cuda(gpu0)
testloader = data.DataLoader(VOCDataSet(args.data_dir,
args.data_list,
crop_size=(505, 505),
mean=IMG_MEAN,
scale=False,
mirror=False),
batch_size=1,
shuffle=False,
pin_memory=True)
interp = nn.Upsample(size=(505, 505), mode='bilinear')
data_list = []
with open('result.txt', 'w') as f:
for index, batch in enumerate(testloader, 0):
#print('%d processd'%(index))
image, label, size, name = batch
size = size[0].numpy() #the size of original input image
#print("size:",size)
output = model(Variable(image, volatile=True).cuda(gpu0))
#print("model output size: ",output.size())
output = interp(output).cpu().data[0].numpy()
output = output[:, :size[0], :size[1]]
gt = np.asarray(label[0].numpy()[:size[0], :size[1]], dtype=np.int)
output = output.transpose(1, 2, 0)
prob = softmax(output, axis=2)
entropy = (-prob * np.log(prob)).mean() * 100
output = np.asarray(np.argmax(output, axis=2), dtype=np.int)
# show_all(gt, output)
data_list.append([gt.flatten(), output.flatten()])
iou = get_iou(data_list, args.num_classes)
data_list = []
print('{:.4f}, {:.4f}'.format(entropy.item(), iou.item()))
f.write('{:.8f}, {:.8f}\n'.format(entropy.item(), iou.item()))
def iou():
"""Create the model and start the evaluation process."""
args = get_arguments()
gpu0 = args.gpu
model = Res_Deeplab(num_classes=args.num_classes)
saved_state_dict = torch.load(args.restore_from)
model.load_state_dict(saved_state_dict)
model.eval()
model.cuda(gpu0)
testloader = data.DataLoader(VOCDataSet(args.data_dir,
args.data_list,
crop_size=(505, 505),
mean=IMG_MEAN,
scale=False,
mirror=False),
batch_size=1,
shuffle=False,
pin_memory=True)
interp = nn.Upsample(size=(505, 505), mode='bilinear', align_corners=True)
data_list = []
for index, batch in enumerate(testloader):
if index % 100 == 0:
#print('%d processd'%(index))
sys.stdout.flush()
image, label, size, name = batch
size = size[0].numpy()
with torch.no_grad():
output = model(Variable(image).cuda(gpu0))
output = interp(output).cpu().data[0].numpy()
output = output[:, :size[0], :size[1]]
gt = np.asarray(label[0].numpy()[:size[0], :size[1]], dtype=np.int)
output = output.transpose(1, 2, 0)
output = np.asarray(np.argmax(output, axis=2), dtype=np.int)
# show_all(gt, output)
data_list.append([gt.flatten(), output.flatten()])
return get_iou(data_list, args.num_classes)
def main():
"""Create the model and start the evaluation process."""
args = get_arguments()
gpu0 = args.gpu
model = Res_Deeplab(num_classes=args.num_classes)
saved_state_dict = torch.load(args.restore_from)
model.load_state_dict(saved_state_dict)
model.eval()
model.cuda(gpu0)
testloader = data.DataLoader(VOCDataSet(args.data_dir,
args.data_list,
crop_size=(505, 505),
mean=IMG_MEAN,
scale=False,
mirror=False),
batch_size=1,
shuffle=False,
pin_memory=True)
interp = nn.Upsample(size=(505, 505), mode='bilinear')
sigmoid = nn.Sigmoid()
data_list = []
for index, batch in enumerate(testloader):
if index % 1 == 0:
print('%d processd' % (index))
image, size, name = batch
size = size[0].numpy()
output = model(Variable(image, volatile=True).cuda(gpu0))
output = interp(output)
output = output[:, :size[0], :size[1]]
output = torch.from_numpy(output).float()
result = torchvision.transforms.ToPILImage()(output)
path = os.path.join(SR_dir, name[0])
result.save(path)
def main():
"""Create the model and start the evaluation process."""
gpu0 = 0
model = Res_Deeplab(num_classes=NUM_CLASSES)
saved_state_dict = torch.load(RESTORE_FROM)
model.load_state_dict(saved_state_dict)
model.eval()
model.cuda(gpu0)
testloader = data.DataLoader(VOCDataSet(DATA_DIRECTORY, DATA_LIST_PATH, crop_size=(321, 321), mean=IMG_MEAN, scale=False, mirror=False),
batch_size=1, shuffle=False, pin_memory=True)
interp = nn.Upsample(size=(321, 321), mode='bilinear', align_corners=True) #changed to model 321,321
data_list = []
for index, batch in enumerate(testloader):
if index % 100 == 0:
print('%d processd'%(index))
torch.save(batch, SAVE_TO + '/batch' + str(index) + '.pth') # Save the batch
image, label, size, name = batch
size = size[0].numpy()
output = model(Variable(image, volatile=True).cuda(gpu0))
output = interp(output)
torch.save(output, SAVE_TO + '/prediction' + str(index) + '.pth') #Save b11 prediction
output = output.cpu().data[0].numpy()
output = output[:,:size[0],:size[1]]
gt = np.asarray(label[0].numpy()[:size[0],:size[1]], dtype=np.int)
output = output.transpose(1,2,0)
output = np.asarray(np.argmax(output, axis=2), dtype=np.int)
data_list.append([gt.flatten(), output.flatten()])
get_iou(data_list, NUM_CLASSES)
def main():
"""Create the model and start the training."""
print("=====> Set GPU for training")
if args.cuda:
print("====> use gpu id: '{}'".format(args.gpus))
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpus
if not torch.cuda.is_available():
raise Exception(
"No GPU found or Wrong gpu id, please run without --cuda")
args.seed = random.randint(1, 10000)
print("Random Seed: ", args.seed)
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
h, w = map(int, args.input_size.split(','))
input_size = (h, w)
cudnn.enabled = True
# Create network.
print("=====> Building network")
model = Res_Deeplab(num_classes=args.num_classes)
# For a small batch size, it is better to keep
# the statistics of the BN layers (running means and variances)
# frozen, and to not update the values provided by the pre-trained model.
# If is_training=True, the statistics will be updated during the training.
# Note that is_training=False still updates BN parameters gamma (scale) and beta (offset)
# if they are presented in var_list of the optimiser definition.
print("=====> Loading pretrained weights")
saved_state_dict = torch.load(args.restore_from)
new_params = model.state_dict().copy()
for i in saved_state_dict:
#Scale.layer5.conv2d_list.3.weight
i_parts = i.split('.')
# print i_parts
if not args.num_classes == 21 or not i_parts[1] == 'layer5':
new_params['.'.join(i_parts[1:])] = saved_state_dict[i]
model.load_state_dict(new_params)
model.train()
model.cuda()
cudnn.benchmark = True
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
print('====> Computing network parameters')
total_paramters = netParams(model)
print('Total network parameters: ' + str(total_paramters))
print("=====> Preparing training data")
trainloader = data.DataLoader(VOCDataSet(args.data_dir,
args.data_list,
max_iters=args.num_steps *
args.batch_size,
crop_size=input_size,
scale=args.random_scale,
mirror=args.random_mirror,
mean=IMG_MEAN),
batch_size=args.batch_size,
shuffle=True,
num_workers=2,
pin_memory=True)
optimizer = optim.SGD([{
'params': get_1x_lr_params_NOscale(model),
'lr': args.learning_rate
}, {
'params': get_10x_lr_params(model),
'lr': 10 * args.learning_rate
}],
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay)
optimizer.zero_grad()
interp = nn.Upsample(size=input_size, mode='bilinear')
logFileLoc = args.snapshot_dir + args.logFile
if os.path.isfile(logFileLoc):
logger = open(logFileLoc, 'a')
else:
logger = open(logFileLoc, 'w')
logger.write("Parameters: %s" % (str(total_paramters)))
logger.write("\n%s\t\t%s" % ('iter', 'Loss(train)'))
logger.flush()
print("=====> Begin to train")
for i_iter, batch in enumerate(trainloader):
images, labels, _, _ = batch
images = Variable(images).cuda()
optimizer.zero_grad()
adjust_learning_rate(optimizer, i_iter)
pred = interp(model(images))
loss = loss_calc(pred, labels)
loss.backward()
optimizer.step()
print('iter = ', i_iter, 'of', args.num_steps, 'completed, loss = ',
loss.data.cpu().numpy())
logger.write("\n%d\t\t%.5f" % (i_iter, loss.data.cpu().numpy()))
logger.flush()
if i_iter >= args.num_steps - 1:
print('save model ...')
torch.save(
model.state_dict(),
osp.join(args.snapshot_dir,
'VOC12_scenes_' + str(args.num_steps) + '.pth'))
break
if i_iter % args.save_pred_every == 0 and i_iter != 0:
print('taking snapshot ...')
torch.save(
model.state_dict(),
osp.join(args.snapshot_dir,
'VOC12_scenes_' + str(i_iter) + '.pth'))
logger.close()
end = timeit.default_timer()
print(end - start, 'seconds')
def main():
"""Create the model and start the training."""
os.environ["CUDA_VISIBLE_DEVICES"] = str(args.gpu)
h, w = map(int, args.input_size.split(','))
input_size = (h, w)
cudnn.enabled = True
# Create network.
model = Res_Deeplab(num_classes=args.num_classes)
# For a small batch size, it is better to keep
# the statistics of the BN layers (running means and variances)
# frozen, and to not update the values provided by the pre-trained model.
# If is_training=True, the statistics will be updated during the training.
# Note that is_training=False still updates BN parameters gamma (scale) and beta (offset)
# if they are presented in var_list of the optimiser definition.
saved_state_dict = torch.load(args.restore_from)
new_params = model.state_dict().copy()
for i in saved_state_dict:
#Scale.layer5.conv2d_list.3.weight
i_parts = i.split('.')
# print i_parts
if not args.num_classes == 21 or not i_parts[1] == 'layer5':
new_params['.'.join(i_parts[1:])] = saved_state_dict[i]
model.load_state_dict(new_params)
#model.float()
#model.eval() # use_global_stats = True
model.train()
model.cuda()
cudnn.benchmark = True
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
trainloader = data.DataLoader(VOCDataSet(args.data_dir,
args.data_list,
max_iters=args.num_steps *
args.batch_size,
crop_size=input_size,
scale=args.random_scale,
mirror=args.random_mirror,
mean=IMG_MEAN),
batch_size=args.batch_size,
shuffle=True,
num_workers=0,
pin_memory=True)
optimizer = optim.SGD([{
'params': get_1x_lr_params_NOscale(model),
'lr': args.learning_rate
}, {
'params': get_10x_lr_params(model),
'lr': 10 * args.learning_rate
}],
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay)
optimizer.zero_grad()
interp = nn.Upsample(size=input_size, mode='bilinear', align_corners=True)
for i_iter, batch in enumerate(trainloader):
images, labels, _, _ = batch
images = Variable(images).cuda()
optimizer.zero_grad()
adjust_learning_rate(optimizer, i_iter)
pred = interp(model(images))
loss = loss_calc(pred, labels)
loss.backward()
optimizer.step()
print('iter = ', i_iter, 'of', args.num_steps, 'completed, loss = ',
loss.data.cpu().numpy())
sys.stdout.flush()
if i_iter >= args.num_steps - 1:
print('save model ...')
sys.stdout.flush()
torch.save(
model.state_dict(),
osp.join(args.snapshot_dir,
'VOC12_scenes_' + str(args.num_steps) + '.pth'))
break
if i_iter % args.save_pred_every == 0 and i_iter != 0:
print('taking snapshot ...')
sys.stdout.flush()
torch.save(
model.state_dict(),
osp.join(args.snapshot_dir,
'VOC12_scenes_' + str(i_iter) + '.pth'))
end = timeit.default_timer()
print(end - start, 'seconds')
sys.stdout.flush()
def main():
"""Create the model and start the training."""
h, w = map(int, args.input_size.split(','))
input_size = (h, w)
cudnn.enabled = True
gpu = args.gpu
# Create network.
model = Res_Deeplab(num_classes=args.num_classes)
# For a small batch size, it is better to keep
# the statistics of the BN layers (running means and variances)
# frozen, and to not update the values provided by the pre-trained model.
# If is_training=True, the statistics will be updated during the training.
# Note that is_training=False still updates BN parameters gamma (scale) and beta (offset)
# if they are presented in var_list of the optimiser definition.
saved_state_dict = torch.load(args.restore_from)
new_params = model.state_dict().copy()
for i in saved_state_dict:
#Scale.layer5.conv2d_list.3.weight
i_parts = i.split('.')
# print i_parts
if not args.num_classes == 21 or not i_parts[1] == 'layer5':
new_params['.'.join(i_parts[1:])] = saved_state_dict[i]
model.load_state_dict(new_params)
#model.float()
#model.eval() # use_global_stats = True
model.train()
model.cuda(args.gpu)
cudnn.benchmark = True
if not os.path.exists(args.snapshot_dir):
os.makedirs(args.snapshot_dir)
trainloader = data.DataLoader(VOCDataSet(args.data_dir,
args.data_list,
max_iters=args.num_steps *
args.iter_size,
crop_size=input_size,
scale=args.random_scale,
mirror=args.random_mirror,
mean=IMG_MEAN),
batch_size=args.batch_size,
shuffle=True,
num_workers=1,
pin_memory=True)
optimizer = optim.SGD([{
'params': get_1x_lr_params_NOscale(model),
'lr': args.learning_rate
}, {
'params': get_10x_lr_params(model),
'lr': 10 * args.learning_rate
}],
lr=args.learning_rate,
momentum=args.momentum,
weight_decay=args.weight_decay)
optimizer.zero_grad()
b_loss = 0
for i_iter, batch in enumerate(trainloader):
images, labels, _, _ = batch
images, labels = Variable(images), labels.numpy()
h, w = images.size()[2:]
images075 = nn.Upsample(size=(int(h * 0.75), int(w * 0.75)),
mode='bilinear')(images)
images05 = nn.Upsample(size=(int(h * 0.5), int(w * 0.5)),
mode='bilinear')(images)
out = model(images.cuda(args.gpu))
out075 = model(images075.cuda(args.gpu))
out05 = model(images05.cuda(args.gpu))
o_h, o_w = out.size()[2:]
interpo1 = nn.Upsample(size=(o_h, o_w), mode='bilinear')
interpo2 = nn.Upsample(size=(h, w), mode='bilinear')
out_max = interpo2(
torch.max(torch.stack([out, interpo1(out075),
interpo1(out05)]),
dim=0)[0])
loss = loss_calc(out_max, labels, args.gpu)
d1, d2 = float(labels.shape[1]), float(labels.shape[2])
loss100 = loss_calc(
out,
nd.zoom(labels, (1.0, out.size()[2] / d1, out.size()[3] / d2),
order=0), args.gpu)
loss075 = loss_calc(
out075,
nd.zoom(labels,
(1.0, out075.size()[2] / d1, out075.size()[3] / d2),
order=0), args.gpu)
loss05 = loss_calc(
out05,
nd.zoom(labels, (1.0, out05.size()[2] / d1, out05.size()[3] / d2),
order=0), args.gpu)
loss_all = (loss + loss100 + loss075 + loss05) / args.iter_size
loss_all.backward()
b_loss += loss_all.data.cpu().numpy()
b_iter = i_iter / args.iter_size
if b_iter >= args.num_steps - 1:
print 'save model ...'
optimizer.step()
torch.save(
model.state_dict(),
osp.join(args.snapshot_dir,
'VOC12_scenes_' + str(args.num_steps) + '.pth'))
break
if i_iter % args.iter_size == 0 and i_iter != 0:
print 'iter = ', b_iter, 'of', args.num_steps, 'completed, loss = ', b_loss
optimizer.step()
adjust_learning_rate(optimizer, b_iter)
optimizer.zero_grad()
b_loss = 0
if i_iter % (args.save_pred_every *
args.iter_size) == 0 and b_iter != 0:
print 'taking snapshot ...'
torch.save(
model.state_dict(),
osp.join(args.snapshot_dir,
'VOC12_scenes_' + str(b_iter) + '.pth'))
end = timeit.timeit()
print end - start, 'seconds'
# load the state dictionary of the model
# IMPORTANT! HAS TO BE CHANGED HERE, USE PATH TO YOUR BEST TRAINED MODEL
pathToTrainedModel = '/root/20000StepsDefaultParametersBatch6/VOC12_scenes_20000.pth'
saved_state_dict = torch.load(pathToTrainedModel)
model.load_state_dict(saved_state_dict)
# no training/updating weights here
model.eval()
model.cuda()
# Trainloader from Pytorch deeplab, uses the pascal voc data set
trainloader = data.DataLoader(VOCDataSet(DATA_DIRECTORY,
DATA_LIST_PATH,
max_iters=10,
crop_size=input_size,
scale=False,
mirror=False,
mean=IMG_MEAN),
batch_size=BATCH_SIZE,
shuffle=False,
num_workers=0,
pin_memory=True)
interp = nn.Upsample(size=input_size, mode='bilinear', align_corners=True)
# Iterate over the trainloader for the above mentioned times
for i_iter, batch in enumerate(trainloader):
# get the images and labels (ground truth) of each batch
images, labels, _, _ = batch
images = Variable(images).cuda() #gets and saves a gpu output
