pytorch + visdom CNN处理自建图片数据集的方法

ata_transforms = {
  'train': transforms.Compose([
    # 随机切成224x224 大小图片 统一图片格式
    transforms.RandomResizedCrop(224),
    # 图像翻转
    transforms.RandomHorizontalFlip(),
    # totensor 归一化(0,255) >> (0,1)  normalize  channel=（channel-mean）/std
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
  ]),
  "val" : transforms.Compose([
    # 图片大小缩放 统一图片格式
    transforms.Resize(256),
    # 以中心裁剪
    transforms.CenterCrop(224),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
  ])
}

data_dir = './hymenoptera_data'
# trans data
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), data_transforms[x]) for x in ['train', 'val']}
# load data
data_loaders = {x: DataLoader(image_datasets[x], batch_size=BATCH_SIZE, shuffle=True) for x in ['train', 'val']}

data_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes
print(data_sizes, class_names)

inputs, classes = next(iter(data_loaders['val']))

out = torchvision.utils.make_grid(inputs)
inp = torch.transpose(out, 0, 2)
mean = torch.FloatTensor([0.485, 0.456, 0.406])
std = torch.FloatTensor([0.229, 0.224, 0.225])
inp = std * inp + mean
inp = torch.transpose(inp, 0, 2)
viz.images(inp)

class CNN(nn.Module):
  def __init__(self, in_dim, n_class):
    super(CNN, self).__init__()
    self.cnn = nn.Sequential(
      nn.BatchNorm2d(in_dim),
      nn.ReLU(True),
      nn.Conv2d(in_dim, 16, 7), # 224 >> 218
      nn.BatchNorm2d(16),
      nn.ReLU(inplace=True),
      nn.MaxPool2d(2, 2), # 218 >> 109
      nn.ReLU(True),
      nn.Conv2d(16, 32, 5), # 105
      nn.BatchNorm2d(32),
      nn.ReLU(True),
      nn.Conv2d(32, 64, 5), # 101
      nn.BatchNorm2d(64),
      nn.ReLU(True),
      nn.Conv2d(64, 64, 3, 1, 1),
      nn.BatchNorm2d(64),
      nn.ReLU(True),
      nn.MaxPool2d(2, 2), # 101 >> 50
      nn.Conv2d(64, 128, 3, 1, 1), #
      nn.BatchNorm2d(128),
      nn.ReLU(True),
      nn.MaxPool2d(3), # 50 >> 16
    )
    self.fc = nn.Sequential(
      nn.Linear(128*16*16, 120),
      nn.BatchNorm1d(120),
      nn.ReLU(True),
      nn.Linear(120, n_class))
  def forward(self, x):
    out = self.cnn(x)
    out = self.fc(out.view(-1, 128*16*16))
    return out

# 输入3层rgb ，输出 分类 2    
model = CNN(3, 2)

line = viz.line(Y=np.arange(10))
loss_f = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=LR, momentum=0.9)
scheduler = optim.lr_scheduler.StepLR(optimizer, step_size=7, gamma=0.1)

BATCH_SIZE = 4
LR = 0.001
EPOCHS = 10

model = torchvision.models.resnet18(True)
num_ftrs = model.fc.in_features
model.fc = nn.Linear(num_ftrs, 2)

model = torchvision.models.resnet18(pretrained=True)
num_ftrs = model.fc.in_features
model.fc = nn.Linear(num_ftrs, 2)