def train_autoencoder_deep_fashion():
"""Trains the autoencoder for DeepFashion."""
print("=============================================================")
print("================ Train AE with DeepFashion ==================")
print("=============================================================\n")
encoder = CifarNet(input_channels=3, num_classes=50)
encoder = encoder.to(DEVICE)
decoder = Decoder(input_channels=64, num_classes=50, out_channels=3)
decoder = decoder.to(DEVICE)
parameters = list(encoder.parameters()) + list(decoder.parameters())
loss_fn = nn.MSELoss()
# Observe that all parameters are being optimized
optimizer = torch.optim.Adam(parameters, lr=LEARNING_RATE_TRAIN)
# Decay LR by a factor of GAMMA
scheduler = torch.optim.lr_scheduler.StepLR(optimizer=optimizer,
step_size=STEP_SIZE_TRAIN,
gamma=GAMMA)
return train(encoder, decoder, loss_fn, optimizer, scheduler, EPOCHS,
train_loader_deep_fashion)
def load(self) -> None:
self.model = CifarNet()
self.optimizer = SGD(self.model.parameters(), lr=0.001, momentum=0.9)
self.lr_scheduler = MultiStepLR(self.optimizer, [10, 30, 60, 90])
self.criterion = nn.CrossEntropyLoss()
# Load dataset
sample_path = os.path.join(self.sample_dir,
"sample-%s.csv" % self.task_id)
df = pd.read_csv(sample_path, header=None)
data = df.values.tolist()
self.dataset = CifarDataset(data)
def test(self, device) -> dict:
ret = {}
model = CifarNet()
criterion = nn.CrossEntropyLoss()
trainer = SupervisedTrainer(model, None, criterion, device=device)
all_correct, all_total = 0, 0
for i in range(10):
sample_path = os.path.join(self.sample_dir, "sample-%d.csv" % i)
df = pd.read_csv(sample_path, header=None)
data = df.values.tolist()
dataset = CifarDataset(data)
loss, correct, total = trainer.test("aggregate.pth", dataset)
ret[str(i)] = "%.2f%%(%d/%d)" % (100 * correct / total, correct,
total)
all_correct += correct
all_total += total
ret["ALL"] = "%.2f%%(%d/%d)" % (100 * all_correct / all_total,
all_correct, all_total)
self.set_item("acc", all_correct / all_total)
return ret
def train_exemplar_cnn_deep_fashion():
"""Trains the exemplar cnn model."""
print("============================================================")
print("============ Train ExemplarCNN with DeepFashion ============")
print("============================================================\n")
# number of predicted classes = number of training images
model = CifarNet(input_channels=3, num_classes=len(train_loader_deep_fashion.dataset))
model = model.to(DEVICE)
loss_fn = nn.CrossEntropyLoss()
# Observe that all parameters are being optimized
parameters = model.parameters()
optimizer = torch.optim.Adam(parameters, lr=LEARNING_RATE_TRAIN)
# Decay LR by a factor of GAMMA
scheduler = torch.optim.lr_scheduler.StepLR(optimizer=optimizer, step_size=STEP_SIZE_TRAIN, gamma=GAMMA)
return train(model, loss_fn, optimizer, scheduler, EPOCHS, train_loader_deep_fashion)
def train_rotation_net_deep_fashion():
"""Trains the rotation model."""
print("============================================================")
print("========== Train Rotation Model with DeepFashion ===========")
print("============================================================\n")
model = CifarNet(input_channels=3, num_classes=4)
model = model.to(DEVICE)
loss_fn = nn.CrossEntropyLoss()
# Observe that all parameters are being optimized
optimizer = torch.optim.Adam(model.parameters(), lr=LEARNING_RATE_TRAIN)
# Decay LR by a factor of GAMMA
scheduler = torch.optim.lr_scheduler.StepLR(optimizer=optimizer,
step_size=STEP_SIZE_TRAIN,
gamma=GAMMA)
return train(model, loss_fn, optimizer, scheduler, EPOCHS,
train_loader_deep_fashion, val_loader_deep_fashion)
def train_supervised_deep_fashion():
"""Trains the supervised model."""
print("============================================================")
print("============= Supervised Training DeepFashion ==============")
print("============================================================\n")
df_supervised_model = CifarNet(input_channels=3, num_classes=50)
df_supervised_model = df_supervised_model.to(DEVICE)
loss_fn = nn.CrossEntropyLoss()
# Observe that all parameters are being optimized
optimizer = torch.optim.Adam(df_supervised_model.parameters(),
lr=LEARNING_RATE_TRAIN)
# Decay LR by a factor of GAMMA
scheduler = torch.optim.lr_scheduler.StepLR(optimizer=optimizer,
step_size=STEP_SIZE_TRAIN,
gamma=GAMMA)
return fine_tune(df_supervised_model, loss_fn, optimizer, scheduler,
EPOCHS, train_loader_deep_fashion,
val_loader_deep_fashion)
class TrainTask(Task):
def __init__(self, task_id, sample_dir: Task, aggregate_dir: Task = None):
super(TrainTask, self).__init__(task_id=str(task_id))
self.sample_dir = sample_dir
self.aggregate_dir = aggregate_dir
def load(self) -> None:
self.model = CifarNet()
self.optimizer = SGD(self.model.parameters(), lr=0.001, momentum=0.9)
self.lr_scheduler = MultiStepLR(self.optimizer, [10, 30, 60, 90])
self.criterion = nn.CrossEntropyLoss()
# Load dataset
sample_path = os.path.join(self.sample_dir,
"sample-%s.csv" % self.task_id)
df = pd.read_csv(sample_path, header=None)
data = df.values.tolist()
self.dataset = CifarDataset(data)
def train(self, device: str) -> dict:
if self.aggregate_dir is not None:
pre_model_path = os.path.join(self.aggregate_dir, "aggregate.pth")
else:
pre_model_path = None
self.trainer = SupervisedTrainer(self.model,
self.optimizer,
self.criterion,
self.lr_scheduler,
epoch=10,
device=device,
init_model_path=pre_model_path,
console_out="console.out")
_, correct, total = self.trainer.test(pre_model_path, self.dataset)
ret = {
"init_acc":
"%.2f%%(%d/%d)" % (100 * correct / total, correct, total)
}
self.trainer.mount_dataset(self.dataset)
ret.update(self.trainer.train())
return ret
"*****************************************************************************************"
)
print("Dev set size: {}".format(dataset.dev.size))
print(
"*****************************************************************************************"
)
print("Test set size: {}".format(dataset.test.size))
print(
"========================================================================================="
)
print("Show first 3 training images")
# for i in range(3):
# plt.imshow(dataset.train.data['images'][i])
# plt.show()
cifar_net = CifarNet(dataset, args)
cifar_net.train()
predcited = []
for probs in cifar_net.predict(dataset.test.data["images"],
batch_size=args.batch_size):
pred = np.argmax(probs)
predcited.append(pred)
accuracy_test = accuracy_score(dataset.test.data["labels"], predcited)
TN, FP, FN, TP = confusion_matrix(dataset.test.data["labels"],
predcited).ravel()
_test_acc = (TP + TN) / (FP + TN + FN + TP)
print('_test_acc: {}'.format(_test_acc))