def main():
# parse the argument
parser = argparse.ArgumentParser()
parser.add_argument(
'data_list',
help='The path of data list file, which consists of one image path per line'
)
parser.add_argument(
'model',
help='The model for image classification',
choices=[
'alexnet', 'vgg13', 'vgg16', 'vgg19', 'resnet', 'googlenet',
'inception-resnet-v2', 'inception_v4', 'xception'
])
parser.add_argument(
'params_path', help='The file which stores the parameters')
args = parser.parse_args()
# PaddlePaddle init
paddle.init(use_gpu=True, trainer_count=1)
image = paddle.layer.data(
name="image", type=paddle.data_type.dense_vector(DATA_DIM))
if args.model == 'alexnet':
out = alexnet.alexnet(image, class_dim=CLASS_DIM)
elif args.model == 'vgg13':
out = vgg.vgg13(image, class_dim=CLASS_DIM)
elif args.model == 'vgg16':
out = vgg.vgg16(image, class_dim=CLASS_DIM)
elif args.model == 'vgg19':
out = vgg.vgg19(image, class_dim=CLASS_DIM)
elif args.model == 'resnet':
out = resnet.resnet_imagenet(image, class_dim=CLASS_DIM)
elif args.model == 'googlenet':
out, _, _ = googlenet.googlenet(image, class_dim=CLASS_DIM)
elif args.model == 'inception-resnet-v2':
assert DATA_DIM == 3 * 331 * 331 or DATA_DIM == 3 * 299 * 299
out = inception_resnet_v2.inception_resnet_v2(
image, class_dim=CLASS_DIM, dropout_rate=0.5, data_dim=DATA_DIM)
elif args.model == 'inception_v4':
out = inception_v4.inception_v4(image, class_dim=CLASS_DIM)
elif args.model == 'xception':
out = xception.xception(image, class_dim=CLASS_DIM)
# load parameters
with gzip.open(args.params_path, 'r') as f:
parameters = paddle.parameters.Parameters.from_tar(f)
file_list = [line.strip() for line in open(args.data_list)]
test_data = [(paddle.image.load_and_transform(image_file, 256, 224, False)
.flatten().astype('float32'), ) for image_file in file_list]
probs = paddle.infer(
output_layer=out, parameters=parameters, input=test_data)
lab = np.argsort(-probs)
for file_name, result in zip(file_list, lab):
print "Label of %s is: %d" % (file_name, result[0])
def init_net(self):
net_args = {
"pretrained": True,
"n_input_channels": len(self.kwargs["static"]["imagery_bands"])
}
# https://pytorch.org/docs/stable/torchvision/models.html
if self.kwargs["net"] == "resnet18":
self.model = resnet.resnet18(**net_args)
elif self.kwargs["net"] == "resnet34":
self.model = resnet.resnet34(**net_args)
elif self.kwargs["net"] == "resnet50":
self.model = resnet.resnet50(**net_args)
elif self.kwargs["net"] == "resnet101":
self.model = resnet.resnet101(**net_args)
elif self.kwargs["net"] == "resnet152":
self.model = resnet.resnet152(**net_args)
elif self.kwargs["net"] == "vgg11":
self.model = vgg.vgg11(**net_args)
elif self.kwargs["net"] == "vgg11_bn":
self.model = vgg.vgg11_bn(**net_args)
elif self.kwargs["net"] == "vgg13":
self.model = vgg.vgg13(**net_args)
elif self.kwargs["net"] == "vgg13_bn":
self.model = vgg.vgg13_bn(**net_args)
elif self.kwargs["net"] == "vgg16":
self.model = vgg.vgg16(**net_args)
elif self.kwargs["net"] == "vgg16_bn":
self.model = vgg.vgg16_bn(**net_args)
elif self.kwargs["net"] == "vgg19":
self.model = vgg.vgg19(**net_args)
elif self.kwargs["net"] == "vgg19_bn":
self.model = vgg.vgg19_bn(**net_args)
else:
raise ValueError("Invalid network specified: {}".format(
self.kwargs["net"]))
# run type: 1 = fine tune, 2 = fixed feature extractor
# - replace run type option with "# of layers to fine tune"
if self.kwargs["run_type"] == 2:
layer_count = len(list(self.model.parameters()))
for layer, param in enumerate(self.model.parameters()):
if layer <= layer_count - 5:
param.requires_grad = False
# Parameters of newly constructed modules have requires_grad=True by default
# get existing number for input features
# set new number for output features to number of categories being classified
# see: https://pytorch.org/tutorials/beginner/finetuning_torchvision_models_tutorial.html
if "resnet" in self.kwargs["net"]:
num_ftrs = self.model.fc.in_features
self.model.fc = nn.Linear(num_ftrs, self.ncats)
elif "vgg" in self.kwargs["net"]:
num_ftrs = self.model.classifier[6].in_features
self.model.classifier[6] = nn.Linear(num_ftrs, self.ncats)
def load_model(args):
if args.model == 'vgg11':
model = vgg.vgg11().to(device)
if args.model == 'vgg13':
model = vgg.vgg13().to(device)
if args.model == 'vgg16':
model = vgg.vgg16().to(device)
elif args.model == 'vgg19':
model = vgg.vgg19().to(device)
elif args.model == 'modified_vgg11':
model = modified_vgg.vgg11().to(device)
elif args.model == 'modified_vgg13':
model = modified_vgg.vgg13().to(device)
elif args.model == 'modified_vgg16':
model = modified_vgg.vgg16().to(device)
elif args.model == 'modified_vgg19':
model = modified_vgg.vgg19().to(device)
return model
def NeptuneLog():
neptune.log_metric('batch_size', batch_sizes)
neptune.log_metric('learning_rate', learning_rate)
neptune.log_text('pre-trained', str(pretrain_check))
neptune.log_text('model', model_name)
neptune.log_text('date_time', date_time)
neptune.create_experiment(model_name)
NeptuneLog()
if model_name == 'vgg11':
model = vgg.vgg11(pretrained=pretrain_check)
elif model_name == 'vgg11_bn':
model = vgg.vgg11_bn(pretrained=pretrain_check)
elif model_name == 'vgg13':
model = vgg.vgg13(pretrained=pretrain_check)
elif model_name == 'vgg13_bn':
model = vgg.vgg13_bn(pretrained=pretrain_check)
elif model_name == 'vgg16':
model = vgg.vgg16(pretrained=pretrain_check)
elif model_name == 'vgg16_bn':
model = vgg.vgg16_bn(pretrained=pretrain_check)
elif model_name == 'vgg19':
model = vgg.vgg19(pretrained=pretrain_check)
elif model_name == 'vgg19_bn':
model = vgg.vgg19_bn(pretrained=pretrain_check)
model.eval()
model = torch.nn.DataParallel(model).cuda()
optimizer = optim.Adam(model.parameters(),
lr=learning_rate,
def main():
# parse the argument
parser = argparse.ArgumentParser()
parser.add_argument(
'model',
help='The model for image classification',
choices=['alexnet', 'vgg13', 'vgg16', 'vgg19', 'resnet', 'googlenet'])
args = parser.parse_args()
# PaddlePaddle init
paddle.init(use_gpu=True, trainer_count=1)
image = paddle.layer.data(
name="image", type=paddle.data_type.dense_vector(DATA_DIM))
lbl = paddle.layer.data(
name="label", type=paddle.data_type.integer_value(CLASS_DIM))
extra_layers = None
learning_rate = 0.01
if args.model == 'alexnet':
out = alexnet.alexnet(image, class_dim=CLASS_DIM)
elif args.model == 'vgg13':
out = vgg.vgg13(image, class_dim=CLASS_DIM)
elif args.model == 'vgg16':
out = vgg.vgg16(image, class_dim=CLASS_DIM)
elif args.model == 'vgg19':
out = vgg.vgg19(image, class_dim=CLASS_DIM)
elif args.model == 'resnet':
out = resnet.resnet_imagenet(image, class_dim=CLASS_DIM)
learning_rate = 0.1
elif args.model == 'googlenet':
out, out1, out2 = googlenet.googlenet(image, class_dim=CLASS_DIM)
loss1 = paddle.layer.cross_entropy_cost(
input=out1, label=lbl, coeff=0.3)
paddle.evaluator.classification_error(input=out1, label=lbl)
loss2 = paddle.layer.cross_entropy_cost(
input=out2, label=lbl, coeff=0.3)
paddle.evaluator.classification_error(input=out2, label=lbl)
extra_layers = [loss1, loss2]
cost = paddle.layer.classification_cost(input=out, label=lbl)
# Create parameters
parameters = paddle.parameters.create(cost)
# Create optimizer
optimizer = paddle.optimizer.Momentum(
momentum=0.9,
regularization=paddle.optimizer.L2Regularization(rate=0.0005 *
BATCH_SIZE),
learning_rate=learning_rate / BATCH_SIZE,
learning_rate_decay_a=0.1,
learning_rate_decay_b=128000 * 35,
learning_rate_schedule="discexp", )
train_reader = paddle.batch(
paddle.reader.shuffle(
flowers.train(),
# To use other data, replace the above line with:
# reader.train_reader('train.list'),
buf_size=1000),
batch_size=BATCH_SIZE)
test_reader = paddle.batch(
flowers.valid(),
# To use other data, replace the above line with:
# reader.test_reader('val.list'),
batch_size=BATCH_SIZE)
# End batch and end pass event handler
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 1 == 0:
print "\nPass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
if isinstance(event, paddle.event.EndPass):
with gzip.open('params_pass_%d.tar.gz' % event.pass_id, 'w') as f:
parameters.to_tar(f)
result = trainer.test(reader=test_reader)
print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
# Create trainer
trainer = paddle.trainer.SGD(
cost=cost,
parameters=parameters,
update_equation=optimizer,
extra_layers=extra_layers)
trainer.train(
reader=train_reader, num_passes=200, event_handler=event_handler)
def main():
# parse the argument
parser = argparse.ArgumentParser()
parser.add_argument('-m',
'--model',
help='The model for image classification',
choices=[
'alexnet', 'vgg13', 'vgg16', 'vgg19', 'resnet',
'googlenet', 'inception-resnet-v2', 'inception_v4',
'xception'
])
parser.add_argument(
'-r',
'--retrain_file',
type=str,
default='',
help="The model file to retrain, none is for train from scratch")
args = parser.parse_args()
# PaddlePaddle init
paddle.init(use_gpu=True, trainer_count=1)
image = paddle.layer.data(name="image",
type=paddle.data_type.dense_vector(DATA_DIM))
lbl = paddle.layer.data(name="label",
type=paddle.data_type.integer_value(CLASS_DIM))
extra_layers = None
learning_rate = 0.0001
if args.model == 'alexnet':
out = alexnet.alexnet(image, class_dim=CLASS_DIM)
elif args.model == 'vgg13':
out = vgg.vgg13(image, class_dim=CLASS_DIM)
elif args.model == 'vgg16':
out = vgg.vgg16(image, class_dim=CLASS_DIM)
elif args.model == 'vgg19':
out = vgg.vgg19(image, class_dim=CLASS_DIM)
elif args.model == 'resnet':
conv, pool, out = resnet.resnet_imagenet(image, class_dim=CLASS_DIM)
learning_rate = 0.1
elif args.model == 'googlenet':
out, out1, out2 = googlenet.googlenet(image, class_dim=CLASS_DIM)
loss1 = paddle.layer.cross_entropy_cost(input=out1,
label=lbl,
coeff=0.3)
paddle.evaluator.classification_error(input=out1, label=lbl)
loss2 = paddle.layer.cross_entropy_cost(input=out2,
label=lbl,
coeff=0.3)
paddle.evaluator.classification_error(input=out2, label=lbl)
extra_layers = [loss1, loss2]
elif args.model == 'inception-resnet-v2':
assert DATA_DIM == 3 * 331 * 331 or DATA_DIM == 3 * 299 * 299
out = inception_resnet_v2.inception_resnet_v2(image,
class_dim=CLASS_DIM,
dropout_rate=0.5,
data_dim=DATA_DIM)
elif args.model == 'inception_v4':
conv, pool, out = inception_v4.inception_v4(image, class_dim=CLASS_DIM)
elif args.model == 'xception':
out = xception.xception(image, class_dim=CLASS_DIM)
cost = paddle.layer.classification_cost(input=out, label=lbl)
# Create parameters
parameters = paddle.parameters.create(cost)
for k, v in parameters.__param_conf__.items():
print(" config key {0}\t\t\tval{1}".format(k, v))
print("-" * 50)
#print(parameters.__param_conf__[0])
if args.retrain_file is not None and '' != args.retrain_file:
print("restore parameters from {0}".format(args.retrain_file))
exclude_params = [
param for param in parameters.names()
if param.startswith('___fc_layer_0__')
]
parameters.init_from_tar(gzip.open(args.retrain_file), exclude_params)
# Create optimizer
optimizer = paddle.optimizer.Momentum(
momentum=0.9,
regularization=paddle.optimizer.L2Regularization(rate=0.0005 *
BATCH_SIZE),
learning_rate=learning_rate / BATCH_SIZE,
learning_rate_decay_a=0.1,
learning_rate_decay_b=128000 * 35,
learning_rate_schedule="discexp",
)
train_reader = paddle.batch(
paddle.reader.shuffle(
# flowers.train(),
# To use other data, replace the above line with:
reader.train_reader('valid_train0.lst'),
buf_size=2048),
batch_size=BATCH_SIZE)
test_reader = paddle.batch(
# flowers.valid(),
# To use other data, replace the above line with:
reader.test_reader('valid_val.lst'),
batch_size=BATCH_SIZE)
# Create trainer
trainer = paddle.trainer.SGD(cost=cost,
parameters=parameters,
update_equation=optimizer,
extra_layers=extra_layers)
# End batch and end pass event handler
def event_handler(event):
global step
global start
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 10 == 0:
print "\nPass %d, Batch %d, Cost %f, %s, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics,
time.time() - start)
start = time.time()
loss_scalar.add_record(step, event.cost)
acc_scalar.add_record(
step, 1 - event.metrics['classification_error_evaluator'])
start = time.time()
step += 1
if event.batch_id % 100 == 0:
with gzip.open('params_pass_%d.tar.gz' % event.pass_id,
'w') as f:
trainer.save_parameter_to_tar(f)
if isinstance(event, paddle.event.EndPass):
with gzip.open('params_pass_%d.tar.gz' % event.pass_id, 'w') as f:
trainer.save_parameter_to_tar(f)
result = trainer.test(reader=test_reader)
print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
trainer.train(reader=train_reader,
num_passes=200,
event_handler=event_handler)
def get_model(args):
network = args.network
if network == 'vgg11':
model = vgg.vgg11(num_classes=args.class_num)
elif network == 'vgg13':
model = vgg.vgg13(num_classes=args.class_num)
elif network == 'vgg16':
model = vgg.vgg16(num_classes=args.class_num)
elif network == 'vgg19':
model = vgg.vgg19(num_classes=args.class_num)
elif network == 'vgg11_bn':
model = vgg.vgg11_bn(num_classes=args.class_num)
elif network == 'vgg13_bn':
model = vgg.vgg13_bn(num_classes=args.class_num)
elif network == 'vgg16_bn':
model = vgg.vgg16_bn(num_classes=args.class_num)
elif network == 'vgg19_bn':
model = vgg.vgg19_bn(num_classes=args.class_num)
elif network == 'resnet18':
model = models.resnet18(num_classes=args.class_num)
model.conv1 = torch.nn.Conv2d(in_channels=1,
out_channels=model.conv1.out_channels,
kernel_size=model.conv1.kernel_size,
stride=model.conv1.stride,
padding=model.conv1.padding,
bias=model.conv1.bias)
elif network == 'resnet34':
model = models.resnet34(num_classes=args.class_num)
model.conv1 = torch.nn.Conv2d(in_channels=1,
out_channels=model.conv1.out_channels,
kernel_size=model.conv1.kernel_size,
stride=model.conv1.stride,
padding=model.conv1.padding,
bias=model.conv1.bias)
elif network == 'resnet50':
model = models.resnet50(num_classes=args.class_num)
model.conv1 = torch.nn.Conv2d(in_channels=1,
out_channels=model.conv1.out_channels,
kernel_size=model.conv1.kernel_size,
stride=model.conv1.stride,
padding=model.conv1.padding,
bias=model.conv1.bias)
elif network == 'resnet101':
model = models.resnet101(num_classes=args.class_num)
model.conv1 = torch.nn.Conv2d(in_channels=1,
out_channels=model.conv1.out_channels,
kernel_size=model.conv1.kernel_size,
stride=model.conv1.stride,
padding=model.conv1.padding,
bias=model.conv1.bias)
elif network == 'resnet152':
model = models.resnet152(num_classes=args.class_num)
model.conv1 = torch.nn.Conv2d(in_channels=1,
out_channels=model.conv1.out_channels,
kernel_size=model.conv1.kernel_size,
stride=model.conv1.stride,
padding=model.conv1.padding,
bias=model.conv1.bias)
elif network == 'densenet121':
model = densenet.densenet121(num_classes=args.class_num)
elif network == 'densenet169':
model = densenet.densenet169(num_classes=args.class_num)
elif network == 'densenet161':
model = densenet.densenet161(num_classes=args.class_num)
elif network == 'densenet201':
model = densenet.densenet201(num_classes=args.class_num)
return model
def main():
# parse the argument
parser = argparse.ArgumentParser()
parser.add_argument(
'model',
help='The model for image classification',
choices=['alexnet', 'vgg13', 'vgg16', 'vgg19', 'resnet', 'googlenet'])
args = parser.parse_args()
# PaddlePaddle init
paddle.init(use_gpu=True, trainer_count=7)
image = paddle.layer.data(
name="image", type=paddle.data_type.dense_vector(DATA_DIM))
lbl = paddle.layer.data(
name="label", type=paddle.data_type.integer_value(CLASS_DIM))
extra_layers = None
learning_rate = 0.01
if args.model == 'alexnet':
out = alexnet.alexnet(image, class_dim=CLASS_DIM)
elif args.model == 'vgg13':
out = vgg.vgg13(image, class_dim=CLASS_DIM)
elif args.model == 'vgg16':
out = vgg.vgg16(image, class_dim=CLASS_DIM)
elif args.model == 'vgg19':
out = vgg.vgg19(image, class_dim=CLASS_DIM)
elif args.model == 'resnet':
out = resnet.resnet_imagenet(image, class_dim=CLASS_DIM)
learning_rate = 0.1
elif args.model == 'googlenet':
out, out1, out2 = googlenet.googlenet(image, class_dim=CLASS_DIM)
loss1 = paddle.layer.cross_entropy_cost(
input=out1, label=lbl, coeff=0.3)
paddle.evaluator.classification_error(input=out1, label=lbl)
loss2 = paddle.layer.cross_entropy_cost(
input=out2, label=lbl, coeff=0.3)
paddle.evaluator.classification_error(input=out2, label=lbl)
extra_layers = [loss1, loss2]
cost = paddle.layer.classification_cost(input=out, label=lbl)
# Create parameters
parameters = paddle.parameters.create(cost)
# Create optimizer
optimizer = paddle.optimizer.Momentum(
momentum=0.9,
regularization=paddle.optimizer.L2Regularization(rate=0.0005 *
BATCH_SIZE),
learning_rate=learning_rate / BATCH_SIZE,
learning_rate_decay_a=0.1,
learning_rate_decay_b=128000 * 35,
learning_rate_schedule="discexp", )
train_reader = paddle.batch(
paddle.reader.shuffle(
flowers.train(),
# To use other data, replace the above line with:
# reader.train_reader('train.list'),
buf_size=1000),
batch_size=BATCH_SIZE)
test_reader = paddle.batch(
flowers.valid(),
# To use other data, replace the above line with:
# reader.test_reader('val.list'),
batch_size=BATCH_SIZE)
# Create trainer
trainer = paddle.trainer.SGD(
cost=cost,
parameters=parameters,
update_equation=optimizer,
extra_layers=extra_layers)
# End batch and end pass event handler
def event_handler(event):
if isinstance(event, paddle.event.EndIteration):
if event.batch_id % 1 == 0:
print "\nPass %d, Batch %d, Cost %f, %s" % (
event.pass_id, event.batch_id, event.cost, event.metrics)
if isinstance(event, paddle.event.EndPass):
with gzip.open('params_pass_%d.tar.gz' % event.pass_id, 'w') as f:
trainer.save_parameter_to_tar(f)
result = trainer.test(reader=test_reader)
print "\nTest with Pass %d, %s" % (event.pass_id, result.metrics)
trainer.train(
reader=train_reader, num_passes=200, event_handler=event_handler)