def build_model(self):
print ('==> Build model and setup loss and optimizer')
#build model
self.model = resnet101(pretrained=True, channel=3).cuda()
#Loss function and optimizer
self.criterion = nn.CrossEntropyLoss().cuda()
self.optimizer = torch.optim.SGD(self.model.parameters(), self.lr, momentum=0.9)
self.scheduler = ReduceLROnPlateau(self.optimizer, 'min', patience=5,verbose=True)
def main():
# load data
print("Loading dataset...")
train_data = COCO_motivations_Dataset(data_root, train=True)
val_data = COCO_motivations_Dataset(data_root, train=False)
batch_size = 2
batch_size = batch_size if len(
params.gpus) == 0 else batch_size * len(params.gpus)
train_dataloader = DataLoader(train_data,
batch_size=batch_size,
shuffle=True,
num_workers=num_workers)
print('train dataset len: {}'.format(len(train_dataloader.dataset)))
val_dataloader = DataLoader(val_data,
batch_size=batch_size,
shuffle=False,
num_workers=num_workers)
print('val dataset len: {}'.format(len(val_dataloader.dataset)))
# models
# model = resnet34(pretrained=False, modelpath=model_path, num_classes=1000) # batch_size=120, 1GPU Memory < 7000M
# model.fc = nn.Linear(512, 256)
model = resnet101(pretrained=False, modelpath=model_path,
num_classes=1000) # batch_size=60, 1GPU Memory > 9000M
model.fc = nn.Linear(512 * 4, 256)
# optimizer
trainable_vars = [
param for param in model.parameters() if param.requires_grad
]
print("Training with sgd")
params.optimizer = torch.optim.SGD(trainable_vars,
lr=init_lr,
momentum=momentum,
weight_decay=weight_decay,
nesterov=nesterov)
# Train
params.lr_scheduler = ReduceLROnPlateau(params.optimizer,
'min',
factor=lr_decay,
patience=10,
cooldown=10,
verbose=True)
trainer = Trainer(model, params, train_dataloader, val_dataloader)
trainer.train()
def build_model(self):
print('==> Build model and setup loss and optimizer')
#build model
#self.model = resnet101_pretrain_UCF101(pretrained=True, channel=3).cuda()
self.model = resnet101(pretrained=True, channel=3).cuda()
# If only finetune the last fully connected layer
#for param in self.model.parameters():
# param.requires_grad = False
# Replace the last fully-connected layer
# Parameters of newly constructed modules have requires_grad=True by default
# If only finetune the last fully connected layer
#self.model.fc_custom = nn.Linear(2048, 101).cuda()
#Loss function and optimizer
self.criterion = nn.CrossEntropyLoss().cuda()
# If only finetune the last fully connected layer
#self.optimizer = torch.optim.SGD(self.model.fc_custom.parameters(), self.lr, momentum=0.9)
self.optimizer = torch.optim.SGD(self.model.parameters(),
self.lr,
momentum=0.9)
#self.optimizer = torch.optim.Adam(self.model.parameters(), lr=self.lr)
self.scheduler = ReduceLROnPlateau(self.optimizer,
'min',
patience=arg.lr_patience,
verbose=True)
print("Loading dataset...")
train_data = Hand(data_root,train=True)
val_data = Hand(data_root,train=False)
batch_size = batch_size if len(params.gpus) == 0 else batch_size*len(params.gpus)
train_dataloader = DataLoader(train_data, batch_size=batch_size, shuffle=True, num_workers=num_workers)
print('train dataset len: {}'.format(len(train_dataloader.dataset)))
val_dataloader = DataLoader(val_data, batch_size=batch_size, shuffle=False, num_workers=num_workers)
print('val dataset len: {}'.format(len(val_dataloader.dataset)))
# models
# model = resnet34(pretrained=False, modelpath=model_path, num_classes=1000) # batch_size=120, 1GPU Memory < 7000M
# model.fc = nn.Linear(512, 6)
model = resnet101(pretrained=False, modelpath=model_path, num_classes=1000) # batch_size=60, 1GPU Memory > 9000M
model.fc = nn.Linear(512*4, 6)
# optimizer
trainable_vars = [param for param in model.parameters() if param.requires_grad]
print("Training with sgd")
params.optimizer = torch.optim.SGD(trainable_vars, lr=init_lr,
momentum=momentum,
weight_decay=weight_decay,
nesterov=nesterov)
# Train
params.lr_scheduler = ReduceLROnPlateau(params.optimizer, 'min', factor=lr_decay, patience=10, cooldown=10, verbose=True)
trainer = Trainer(model, params, train_dataloader, val_dataloader)
trainer.train()
transform_test = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225)),
])
testset = DogvsCat('./data/test',
transform=transform_test,
train=False,
test=True)
testloader = torch.utils.data.DataLoader(testset,
batch_size=batchSize,
shuffle=False,
num_workers=num_workers)
model = resnet101(pretrained=True)
model.fc = nn.Linear(2048, 2)
model.load_state_dict(torch.load('model/model.pth'))
model.cuda()
model.eval()
results = []
with torch.no_grad():
for image, label in testloader:
image = Variable(image.cuda())
out = model(image)
label = F.softmax(out, dim=1)
label = label.numpy().tolist()
_, predicted = torch.max(out.data, 1)
predicted = predicted.data.cpu().numpy().tolist()
results.extend([[i, ";".join(str(j))]
