def main():
global opt
opt = parser.parse_args()
opt.gpuids = list(map(int, opt.gpuids))
print(opt)
if opt.cuda and not torch.cuda.is_available():
raise Exception("No GPU found, please run without --cuda")
cudnn.benchmark = True
train_set = get_training_set(opt.upscale_factor, opt.add_noise,
opt.noise_std)
validation_set = get_validation_set(opt.upscale_factor)
test_set = get_test_set(opt.upscale_factor)
training_data_loader = DataLoader(dataset=train_set,
num_workers=opt.threads,
batch_size=opt.batch_size,
shuffle=True)
validating_data_loader = DataLoader(dataset=validation_set,
num_workers=opt.threads,
batch_size=opt.test_batch_size,
shuffle=False)
testing_data_loader = DataLoader(dataset=test_set,
num_workers=opt.threads,
batch_size=opt.test_batch_size,
shuffle=False)
model = SRCNN()
criterion = nn.MSELoss()
if opt.cuda:
torch.cuda.set_device(opt.gpuids[0])
with torch.cuda.device(opt.gpuids[0]):
model = model.cuda()
criterion = criterion.cuda()
model = nn.DataParallel(model,
device_ids=opt.gpuids,
output_device=opt.gpuids[0])
optimizer = optim.Adam(model.parameters(), lr=opt.lr)
if opt.test:
model_name = join("model", opt.model)
model = torch.load(model_name)
model = nn.DataParallel(model,
device_ids=opt.gpuids,
output_device=opt.gpuids[0])
start_time = time.time()
test(model, criterion, testing_data_loader)
elapsed_time = time.time() - start_time
print("===> average {:.2f} image/sec for processing".format(
100.0 / elapsed_time))
return
for epoch in range(1, opt.epochs + 1):
train(model, criterion, epoch, optimizer, training_data_loader)
validate(model, criterion, validating_data_loader)
if epoch % 10 == 0:
checkpoint(model, epoch)
def _get_xy(path_to_data=None, binary=True, upsample=True, replicate=False):
"""
Returns Xs, Ys, shuffled.
Keeps back a validation set that you can get via X_validation_set and Y_validation_set.
"""
global cached_Xs
global cached_Ys
global cached_ptd
global cached_binary
if cached_Xs is not None and cached_Ys is not None and cached_ptd == path_to_data and cached_binary == binary and upsample and not replicate:
return cached_Xs, cached_Ys
else:
print("Getting the data. This will take a moment...")
Xs = [
x for x in data.get_X_feed(
path_to_data, upsample=upsample, replicate=replicate)
]
if binary:
Ys = np.array([
y for y in data.get_Y_feed_binary(path_to_data,
upsample=upsample)
])
else:
Ys = np.array([
y for y in data.get_Y_feed(Xs, path_to_data, upsample=upsample)
])
Xs = np.array([x[1] for x in Xs])
# Shuffle
index_shuf = [i for i in range(len(Xs))]
random.shuffle(index_shuf)
Xs = np.array([Xs[i] for i in index_shuf])
Ys = np.array([Ys[i] for i in index_shuf])
assert (len(Xs) == len(Ys))
# Keep back validation set
global X_validation_set
global Y_validation_set
X_validation_set, Y_validation_set = data.get_validation_set(
replicate=replicate)
print("Ones in validation set:",
len([y for y in Y_validation_set if y == 1]))
print("Zeros in validation set:",
len([y for y in Y_validation_set if y == 0]))
if upsample:
# Only cache upsampled data
cached_Xs = Xs
cached_Ys = Ys
cached_ptd = path_to_data
cached_binary = binary
return Xs, Ys
def main():
global opt
opt = parser.parse_args()
opt.gpuids = list(map(int, opt.gpuids))
print(opt)
if opt.cuda and not torch.cuda.is_available():
raise Exception("No GPU found, please run without --cuda")
cudnn.benchmark = True
if not opt.test:
train_set = get_training_set(opt.dataset, opt.crop_size,
opt.upscale_factor, opt.add_noise,
opt.noise_std)
validation_set = get_validation_set(opt.dataset, opt.crop_size,
opt.upscale_factor)
# test_set = get_test_set(
# opt.dataset, opt.crop_size, opt.upscale_factor)
if not opt.test:
training_data_loader = DataLoader(dataset=train_set,
num_workers=opt.threads,
batch_size=opt.batch_size,
shuffle=True)
validating_data_loader = DataLoader(dataset=validation_set,
num_workers=opt.threads,
batch_size=opt.test_batch_size,
shuffle=False)
# testing_data_loader = DataLoader(
# dataset=test_set, num_workers=opt.threads, batch_size=opt.test_batch_size, shuffle=False)
model = VDSR()
criterion = nn.MSELoss()
if opt.cuda:
torch.cuda.set_device(opt.gpuids[0])
with torch.cuda.device(opt.gpuids[0]):
model = model.cuda()
criterion = criterion.cuda()
optimizer = optim.Adam(model.parameters(),
lr=opt.lr,
weight_decay=opt.weight_decay)
# optimizer = optim.SGD(model.parameters(), lr=opt.lr, momentum=opt.momentum, weight_decay=opt.weight_decay)
# if opt.test:
# model_name = join("model", opt.model)
# model = torch.load(model_name)
# start_time = time.time()
# test(model, criterion, testing_data_loader)
# elapsed_time = time.time() - start_time
# print("===> average {:.2f} image/sec for test".format(
# 100.0/elapsed_time))
# return
train_time = 0.0
validate_time = 0.0
for epoch in range(1, opt.epochs + 1):
start_time = time.time()
train(model, criterion, epoch, optimizer, training_data_loader)
elapsed_time = time.time() - start_time
train_time += elapsed_time
# print("===> {:.2f} seconds to train this epoch".format(
# elapsed_time))
start_time = time.time()
validate(model, criterion, validating_data_loader)
elapsed_time = time.time() - start_time
validate_time += elapsed_time
# print("===> {:.2f} seconds to validate this epoch".format(
# elapsed_time))
if epoch % 10 == 0:
checkpoint(model, epoch)
print("===> average training time per epoch: {:.2f} seconds".format(
train_time / opt.epochs))
print("===> average validation time per epoch: {:.2f} seconds".format(
validate_time / opt.epochs))
print("===> training time: {:.2f} seconds".format(train_time))
print("===> validation time: {:.2f} seconds".format(validate_time))
print("===> total training time: {:.2f} seconds".format(train_time +
validate_time))
def main():
global opt
opt = parser.parse_args()
opt.gpuids = list(map(int, opt.gpuids))
print(opt)
if opt.cuda and not torch.cuda.is_available():
raise Exception("No GPU found, please run without --cuda")
cudnn.benchmark = True
if not opt.test:
train_set = get_training_set(opt.dataset, opt.add_noise, opt.convert_L,
opt.crop)
validation_set = get_validation_set(opt.dataset, opt.add_noise)
test_set = get_test_set(opt.dataset)
#test_set = get_test_set(opt.dataset, opt.add_noise)
if not opt.test:
training_data_loader = DataLoader(dataset=train_set,
num_workers=opt.threads,
batch_size=opt.batch_size,
shuffle=True)
validating_data_loader = DataLoader(dataset=validation_set,
num_workers=opt.threads,
batch_size=opt.test_batch_size,
shuffle=False)
testing_data_loader = DataLoader(dataset=test_set,
num_workers=opt.threads,
batch_size=opt.test_batch_size,
shuffle=False)
model = SVLRM()
criterion1 = CharnonnierLoss()
criterion2 = nn.MSELoss()
Loss = []
PSNR = []
RMSE = []
if opt.cuda:
torch.cuda.set_device(opt.gpuids[0])
with torch.cuda.device(opt.gpuids[0]):
model = model.cuda()
criterion1 = criterion1.cuda()
criterion2 = criterion2.cuda()
model = nn.DataParallel(model,
device_ids=opt.gpuids,
output_device=opt.gpuids[0])
optimizer = optim.Adam(model.parameters(),
eps=opt.eps,
weight_decay=opt.weight_decay)
if opt.test:
model_name = join("model", opt.model)
model = torch.load(model_name)
model.eval()
start_time = time.time()
#test(model, criterion2, testing_data_loader,PSNR,RMSE)
test(model, criterion2, testing_data_loader)
elapsed_time = time.time() - start_time
print("===> average {:.2f} image/sec for test".format(100.0 /
elapsed_time))
return
train_time = 0.0
validate_time = 0.0
for epoch in range(1, opt.epochs + 1):
start_time = time.time()
train(model, criterion1, epoch, optimizer, training_data_loader, Loss)
elapsed_time = time.time() - start_time
train_time += elapsed_time
print("===> {:.2f} seconds to train this epoch".format(elapsed_time))
if epoch % 50 == 0:
start_time = time.time()
validate(model, criterion2, validating_data_loader, PSNR, RMSE)
elapsed_time = time.time() - start_time
validate_time += elapsed_time
print("===> {:.2f} seconds to validate this epoch".format(
elapsed_time))
#if epoch % 10 == 0:
checkpoint(model, epoch)
print("===> average training time per epoch: {:.2f} seconds".format(
train_time / opt.epochs))
print("===> average validation time per epoch: {:.2f} seconds".format(
validate_time / opt.epochs))
print("===> training time: {:.2f} seconds".format(train_time))
print("===> validation time: {:.2f} seconds".format(validate_time))
print("===> total training time: {:.2f} seconds".format(train_time +
validate_time))
plt.figure(figsize=(15, 5))
plt.subplot(131) # 1行3列,第一个图
plt.plot(Loss)
plt.ylabel('Loss')
plt.xlabel('epochs')
plt.subplot(132) # 1行3列.第二个图
plt.plot(PSNR)
plt.ylabel('PSNR')
plt.xlabel('epochsX50')
plt.subplot(133) # 1行3列.第3个图
plt.plot(RMSE)
plt.ylabel('RMSE')
plt.xlabel('epochsX50')
plt.savefig("Loss_PSNR_RMSE.jpg")
file2 = open('PSNR.txt', 'w')
for item in PSNR:
file2.write(str(item) + "\n")
file2.close()
