# 轉灰階: 將輸入3維壓成1維。
transforms.Grayscale(),
# 縮放: 因為source data是32x32，我們將target data的28x28放大成32x32。
transforms.Resize((32, 32)),
# 水平翻轉 (Augmentation)
transforms.RandomHorizontalFlip(),
# 旋轉15度內 (Augmentation)，旋轉後空的地方補0
transforms.RandomRotation(15),
# 最後轉成Tensor供model使用。
transforms.ToTensor(),
])
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
feature_extractor = CNN_VAE().to(device)
#feature_extractor = FeatureExtractor().cuda()
label_predictor = LabelPredictor().to(device)
feature_extractor.load_state_dict(torch.load('extractor_model.bin'))
#label_predictor.load_state_dict(torch.load('predictor_model.bin'))
source_dataset = ImageFolder('real_or_drawing/train_data',
transform=source_transform)
target_dataset = ImageFolder('real_or_drawing/test_data',
transform=target_transform)
test_dataloader = DataLoader(target_dataset, batch_size=128, shuffle=False)
source_dataloader = DataLoader(source_dataset, batch_size=128, shuffle=False)
label_predictor.eval()
feature_extractor.eval()
for i, ((source_data, source_label),
(test_data, _)) in enumerate(zip(source_dataloader, test_dataloader)):
# total_user_data = []
# total_user_labels = []
# for subject_index in range(11):
# total_user_data.extend(list_total_user_data[subject_index])
# total_user_labels.extend(list_total_user_labels[subject_index])
total_user_data = np.array(list_total_user_data,
dtype=np.float32) # <np.ndarray> (11, 180, 400, 8)
total_user_labels = np.array(list_total_user_labels,
dtype=np.int64) # <np.ndarray> (11, 180)
# ----------------------------------------- Init Network -------------------------------------------------------- #
feature_extractor = FeatureExtractor().cuda()
domain_classifier = DomainClassifier().cuda()
label_predictor = LabelPredictor().cuda()
feature_extractor.load_state_dict(
torch.load(r'saved_model\feature_extractor_CE_8_subjects.pkl'))
domain_classifier.load_state_dict(
torch.load(r'saved_model\domain_classifier_CE_8_subjects.pkl'))
label_predictor.load_state_dict(
torch.load(r'saved_model\label_predictor_CE_8_subjects.pkl'))
# ------------------------------------------ Testing Stage -------------------------------------------------------- #
window_size = 52
stride = 1
max_fit = 30
jump = 1
threshold = 60 / 128
# tensor to DataLoader
train_dataloader = DataLoader(train_data,
batch_size=1024,
shuffle=True,
drop_last=True)
test_dataloader = DataLoader(test_data,
batch_size=1024,
shuffle=True,
drop_last=True)
# -------------------------------------- Training Stage ------------------------------------------- #
precision = 1e-8
feature_extractor = FeatureExtractor().cuda()
label_predictor = LabelPredictor().cuda()
domain_classifier = DomainClassifier().cuda()
class_criterion = nn.CrossEntropyLoss()
domain_criterion = nn.CrossEntropyLoss()
optimizer_F = optim.Adam(feature_extractor.parameters())
optimizer_C = optim.Adam(label_predictor.parameters())
optimizer_D = optim.Adam(label_predictor.parameters())
scheduler_F = optim.lr_scheduler.ReduceLROnPlateau(optimizer=optimizer_F,
mode='min',
factor=0.1,
patience=8,
verbose=True,
eps=precision)
target_transform,
'./real_or_drawing',
train=True)
print('dataset done')
target_dataset = ImgDataset(source_transform,
target_transform,
'./real_or_drawing',
train=False)
print('dataset done 2')
source_dataloader = DataLoader(source_dataset, batch_size=32, shuffle=True)
target_dataloader = DataLoader(target_dataset, batch_size=32, shuffle=True)
test_dataloader = DataLoader(target_dataset, batch_size=128, shuffle=False)
feature_extractor = FeatureExtractor().cuda()
label_predictor = LabelPredictor().cuda()
domain_classifier = DomainClassifier().cuda()
class_criterion = nn.CrossEntropyLoss()
domain_criterion = nn.BCEWithLogitsLoss()
optimizer_F = optim.Adam(feature_extractor.parameters()) #原為1e-3
optimizer_C = optim.Adam(label_predictor.parameters())
optimizer_D = optim.Adam(domain_classifier.parameters())
def train_epoch(source_dataloader, target_dataloader, lamb):
'''
Args:
source_dataloader: source data的dataloader
target_dataloader: target data的dataloader
# 轉灰階: 將輸入3維壓成1維。
transforms.Grayscale(),
# 縮放: 因為source data是32x32，我們將target data的28x28放大成32x32。
transforms.Resize((32, 32)),
# 水平翻轉 (Augmentation)
transforms.RandomHorizontalFlip(),
# 旋轉15度內 (Augmentation)，旋轉後空的地方補0
transforms.RandomRotation(15),
# 最後轉成Tensor供model使用。
transforms.ToTensor(),
])
set_seed(208)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
feature_extractor = CNN_VAE().to(device)
label_predictor = LabelPredictor().to(device)
domain_classifier = DomainClassifier().to(device)
class_criterion = nn.CrossEntropyLoss()
domain_criterion = nn.BCEWithLogitsLoss()
source_dataset = ImageFolder('real_or_drawing/train_data',
transform=source_transform)
target_dataset = ImageFolder('real_or_drawing/test_data',
transform=target_transform)
source_dataloader = DataLoader(source_dataset, batch_size=32, shuffle=True)
target_dataloader = DataLoader(target_dataset, batch_size=32, shuffle=True)
test_dataloader = DataLoader(target_dataset, batch_size=128, shuffle=False)
train(source_dataloader,
# 轉灰階: 將輸入3維壓成1維。
transforms.Grayscale(),
# 縮放: 因為source data是32x32，我們將target data的28x28放大成32x32。
transforms.Resize((32, 32)),
# 水平翻轉 (Augmentation)
#transforms.RandomHorizontalFlip(),
# 旋轉15度內 (Augmentation)，旋轉後空的地方補0
#transforms.RandomRotation(15),
# 最後轉成Tensor供model使用。
transforms.ToTensor(),
])
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
feature_extractor = CNN_VAE().to(device)
#feature_extractor = FeatureExtractor().cuda()
label_predictor = LabelPredictor().to(device)
feature_extractor.load_state_dict(torch.load('extractor_model.bin'))
label_predictor.load_state_dict(torch.load('predictor_model.bin'))
target_dataset = ImageFolder(os.path.join(sys.argv[1], 'test_data'),
transform=target_transform)
test_dataloader = DataLoader(target_dataset, batch_size=128, shuffle=False)
result = []
label_predictor.eval()
feature_extractor.eval()
for i, (test_data, _) in enumerate(test_dataloader):
test_data = test_data.to(device)
class_logits = label_predictor(feature_extractor(test_data))
# 縮放: 因為source data是32x32，我們將target data的28x28放大成32x32。
transforms.Resize((32, 32)),
# 水平翻轉 (Augmentation)
transforms.RandomHorizontalFlip(),
# 旋轉15度內 (Augmentation)，旋轉後空的地方補0
transforms.RandomRotation(15),#, fill=(0,)),
# 最後轉成Tensor供model使用。
transforms.ToTensor(),
])
target_dataset = ImageFolder('real_or_drawing/test_data', transform=target_transform)
test_dataloader = DataLoader(target_dataset, batch_size=128, shuffle=False)
feature_extractor = FeatureExtractor().cuda()
feature_extractor.load_state_dict(torch.load('strong1_extractor_model_1000.bin'))
label_predictor = LabelPredictor().cuda()
label_predictor.load_state_dict(torch.load('strong1_predictor_model_1000.bin'))
domain_classifier = DomainClassifier().cuda()
#domain_classifier.load_state_dict(torch.load('extractor_model_300.bin'))
feature_extractor.eval()
label_predictor.eval()
label_dict = {}
for i in range(10):
label_dict[i] = []
for i, (test_data, _) in enumerate(test_dataloader):
test_data = test_data.cuda()
class_logits = label_predictor(feature_extractor(test_data))
x = torch.argmax(class_logits, dim=1).cpu().detach().numpy()
_y = torch.max(class_logits, dim=1)