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
这是我要遵循的步骤。
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.
数据集的位置
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
我这样做是因为我将在接下来使用 DataLoader 加载数据时提到的一个约束。
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，我将数据拆分为 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
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)
然后我使用了 train_model，这是 PyTorch 的文档中描述的一种方法。
但是，当我运行它时，我得到一个错误。
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。