使用 PyTorch 进行迁移学习 [resnet18]。数据集：狗品种识别

Question

我正在尝试在 PyTorch 中实现迁移学习方法。这是我正在使用的数据集：Dog-Breed

这是我正在遵循的步骤。

1. Load the data and read csv using pandas.
2. Resize (60, 60) the train images and store them as numpy array.
3. Apply stratification and split the train data into 7:1:2 (train:validation:test)
4. use the resnet18 model and train. 

数据集位置

LABELS_LOCATION = './dataset/labels.csv'
TRAIN_LOCATION = './dataset/train/'
TEST_LOCATION = './dataset/test/'
ROOT_PATH = './dataset/'

读取 CSV（labels.csv）

def read_csv(csvf):
    # print(pandas.read_csv(csvf).values)
    data=pandas.read_csv(csvf).values
    labels_dict = dict(data)
    idz=list(labels_dict.keys())
    clazz=list(labels_dict.values())
    return labels_dict,idz,clazz

我这样做是因为有一个约束，我将在接下来使用 DataLoader 加载数据时提到该约束。

def class_hashmap(class_arr):
    uniq_clazz = Counter(class_arr)
    class_dict = {}
    for i, j in enumerate(uniq_clazz):
        class_dict[j] = i
    return class_dict

labels, ids, class_names = read_csv(LABELS_LOCATION)
train_images = os.listdir(TRAIN_LOCATION)
class_numbers = class_hashmap(class_names)

接下来，我使用 将图像大小调整为 60,60 opencv，并将结果存储为 numpy 数组。

resize = []
indexed_labels = []
for t_i in train_images:
    # resize.append(transform.resize(io.imread(TRAIN_LOCATION+t_i), (60, 60, 3)))  # (60,60) is the height and widht; 3 is the number of channels
    resize.append(cv2.resize(cv2.imread(TRAIN_LOCATION+t_i), (60, 60)).reshape(3, 60, 60))
    indexed_labels.append(class_numbers[labels[t_i.split('.')[0]]])

resize = np.asarray(resize)
print(resize.shape)

在indexed_labels中，我给每个标签一个数字。

接下来，我将数据分成7:1:2部分

X = resize  # numpy array of images [training data]
y = np.array(indexed_labels)  # indexed labels for images [training labels]

sss = StratifiedShuffleSplit(n_splits=3, test_size=0.2, random_state=0)
sss.get_n_splits(X, y)


for train_index, test_index in sss.split(X, y):
    X_temp, X_test = X[train_index], X[test_index]  # split train into train and test [data]
    y_temp, y_test = y[train_index], y[test_index]  # labels

sss = StratifiedShuffleSplit(n_splits=3, test_size=0.123, random_state=0)
sss.get_n_splits(X_temp, y_temp)

for train_index, test_index in sss.split(X_temp, y_temp):
    print("TRAIN:", train_index, "VAL:", test_index)
    X_train, X_val = X[train_index], X[test_index]  # training and validation data
    y_train, y_val = y[train_index], y[test_index]  # training and validation labels

接下来，我将上一步中的数据加载到 torch DataLoaders 中

batch_size = 500
learning_rate = 0.001

train = torch.utils.data.TensorDataset(torch.from_numpy(X_train), torch.from_numpy(y_train))
train_loader = torch.utils.data.DataLoader(train, batch_size=batch_size, shuffle=False)

val = torch.utils.data.TensorDataset(torch.from_numpy(X_val), torch.from_numpy(y_val))
val_loader = torch.utils.data.DataLoader(val, batch_size=batch_size, shuffle=False)

test = torch.utils.data.TensorDataset(torch.from_numpy(X_test), torch.from_numpy(y_test))
test_loader = torch.utils.data.DataLoader(test, batch_size=batch_size, shuffle=False)

# print(train_loader.size)

dataloaders = {
    'train': train_loader,
    'val': val_loader
}

接下来，我加载预训练的 rensnet 模型。

model_ft = models.resnet18(pretrained=True)

# freeze all model parameters
# for param in model_ft.parameters():
#     param.requires_grad = False

num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, len(class_numbers))

if use_gpu:
    model_ft = model_ft.cuda()
    model_ft.fc = model_ft.fc.cuda()

criterion = nn.CrossEntropyLoss()

# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(model_ft.fc.parameters(), lr=0.001, momentum=0.9)

# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)

model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,
                       num_epochs=25)

然后我使用 train_model，这是PyTorch文档中描述的方法。

但是，当我运行这个时，我收到错误。

Traceback (most recent call last):
  File "/Users/nirvair/Sites/pyTorch/TL.py",
    line 244, in <module>
        num_epochs=25)
      File "/Users/nirvair/Sites/pyTorch/TL.py", line 176, in train_model
        outputs = model(inputs)
      File "/Library/Python/2.7/site-packages/torch/nn/modules/module.py", line 224, in __call__
        result = self.forward(*input, **kwargs)
      File "/Library/Python/2.7/site-packages/torchvision/models/resnet.py", line 149, in forward
        x = self.avgpool(x)
      File "/Library/Python/2.7/site-packages/torch/nn/modules/module.py", line 224, in __call__
        result = self.forward(*input, **kwargs)
      File "/Library/Python/2.7/site-packages/torch/nn/modules/pooling.py", line 505, in forward
        self.padding, self.ceil_mode, self.count_include_pad)
      File "/Library/Python/2.7/site-packages/torch/nn/functional.py", line 264, in avg_pool2d
        ceil_mode, count_include_pad)
      File "/Library/Python/2.7/site-packages/torch/nn/_functions/thnn/pooling.py", line 360, in forward
        ctx.ceil_mode, ctx.count_include_pad)
    RuntimeError: Given input size: (512x2x2). Calculated output size: (512x0x0). Output size is too small at /Users/soumith/code/builder/wheel/pytorch-src/torch/lib/THNN/generic/SpatialAveragePooling.c:64

我似乎无法弄清楚这里出了什么问题。

Answer 1

您的网络对于您正在使用的图像大小 (60x60) 来说太深了。如您所知，随着输入图像在各层中传播，CNN 层确实会产生越来越小的特征图。这是因为您没有使用填充。

您遇到的错误只是表明下一层需要 512 个大小为 2 像素 x 2 像素的特征图。前向传递生成的实际特征图是 512 个大小为 0x0 的图。这种不匹配是触发错误的原因。

一般来说，所有库存网络，例如RESNET-18、Inception等，都要求输入图像的大小为224x224（至少）。您可以使用 [1] 更轻松地完成此操作torchvision transforms。您还可以使用更大的图像尺寸，但 AlexNet 除外，它具有硬编码的特征向量大小，如我在 [2] 中的回答所述。

额外提示：如果您在预训练模式下使用网络，则需要使用 [3] 中 pytorch 文档中的参数来白化数据。

链接

1. http://pytorch.org/docs/master/torchvision/transforms.html
2. /sf/answers/3280564241/
3. http://pytorch.org/docs/master/torchvision/models.html