def homework2(test_dir):
test_transform = transforms.Compose([
transforms.Resize((224, 224)),
AddPepperNoise(0.9, p=0.8),
transforms.ToTensor(),
])
test_data = RMBDataset(data_dir=test_dir, transform=test_transform)
test_loader = DataLoader(dataset=test_data, batch_size=1)
for i, data in enumerate(test_loader):
inputs, labels = data # B C H W
img_tensor = inputs[0, ...] # C H W
img = transform_invert(img_tensor, test_transform)
plt.imshow(img)
plt.show()
plt.pause(0.5)
plt.close()
def homework1(test_dir):
test_transform = transforms.Compose([
transforms.Resize((224, 224)),
# 1 裁剪
#transforms.CenterCrop(120),
# 2 翻转
#transforms.RandomHorizontalFlip(p=1),
# 3 旋转
#transforms.RandomRotation(45),
# 4 色相
#transforms.ColorJitter(hue=0.4),
# 5 饱和度
#transforms.ColorJitter(saturation=50),
# 6 灰度图
#transforms.Grayscale(3),
# 7 错切
#transforms.RandomAffine(0,shear=45),
# 8 缩放
#transforms.RandomAffine(0,scale=(0.5,0.5)),
# 9 平移
#transforms.RandomAffine(0,translate=(0.5,0)),
# 10 遮挡
#transforms.ToTensor(),
#transforms.RandomErasing(p=0.5,scale=(0.1,0.4),value=0),
transforms.ToTensor(),
])
# 构建MyDataset实例
test_data = RMBDataset(data_dir=test_dir, transform=test_transform)
test_loader = DataLoader(dataset=test_data, batch_size=1)
for i, data in enumerate(test_loader):
inputs, labels = data # B C H W
img_tensor = inputs[0, ...] # C H W
img = transform_invert(img_tensor, test_transform)
plt.imshow(img)
plt.show()
plt.pause(0.5)
plt.close()
train_transform = transforms.Compose([
transforms.Resize((32, 32)),
transforms.RandomCrop(32, padding=4),
transforms.RandomGrayscale(p=0.9),
transforms.ToTensor(),
transforms.Normalize(norm_mean, norm_std),
])
valid_transform = transforms.Compose([
transforms.Resize((32, 32)),
transforms.ToTensor(),
transforms.Normalize(norm_mean, norm_std),
])
# 构建MyDataset实例
train_data = RMBDataset(data_dir=train_dir, transform=train_transform)
valid_data = RMBDataset(data_dir=valid_dir, transform=valid_transform)
# 构建DataLoder
train_loader = DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
valid_loader = DataLoader(dataset=valid_data, batch_size=BATCH_SIZE)
# ============================ step 2/5 模型 ============================
net = LeNet(classes=2)
net.initialize_weights()
# ============================ step 3/5 损失函数 ============================
criterion = nn.CrossEntropyLoss() # 选择损失函数
# ============================ step 4/5 优化器 ============================
# transforms.RandomHorizontalFlip(p=1),
# 2 Vertical Flip
# transforms.RandomVerticalFlip(p=0.5),
# 3 RandomRotation
# transforms.RandomRotation(90),
# transforms.RandomRotation((90), expand=True),
# transforms.RandomRotation(30, center=(0, 0)),
# transforms.RandomRotation(30, center=(0, 0), expand=True), # expand only for center rotation
transforms.ToTensor(),
transforms.Normalize(norm_mean, norm_std),
])
train_data = RMBDataset(data_dir=train_dir, transform=train_transform)
train_loader = DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
# ============================ step 5/5 训练 ============================
for i, data in enumerate(train_loader):
inputs, labels = data # B C H W
img_tensor = inputs[0, ...] # C H W
img = transform_invert(img_tensor, train_transform)
plt.imshow(img)
plt.show()
plt.pause(0.5)
plt.close()
# bs, ncrops, c, h, w = inputs.shape
# for n in range(ncrops):
train_transform = transforms.Compose([
transforms.Resize((32, 32)),
transforms.RandomCrop(32, padding=4),
transforms.ToTensor(),
transforms.Normalize(norm_mean, norm_std)
])
valid_transform = transforms.Compose([
transforms.Resize((32, 32)),
transforms.ToTensor(),
transforms.Normalize(norm_mean, norm_std)
])
# 构建MyDataset实例
train_data = RMBDataset(data_dir=train_dir,
transform=train_transform,
label_name=cat_dog_label)
valid_data = RMBDataset(data_dir=valid_dir,
transform=valid_transform,
label_name=cat_dog_label)
# 构建DataLoader
train_loader = DataLoader(dataset=train_data,
batch_size=BATCH_SIZE,
shuffle=True)
valid_loader = DataLoader(dataset=valid_data, batch_size=BATCH_SIZE)
# 2. 构建模型
net = LeNet(classes=2)
net.initialize_weights()