我用PyTorch制作了一个神经网络模型，它有点类似于vgg19模型。每次我输入批量大小的值时，我都会收到错误：
ValueError: Expected input batch_size (1) to match target batch_size (16).
批量大小值为 1 时不会发生这种情况，它会开始训练，没有任何复杂性。
我只是想改变批量大小而不会出现任何错误。
我自己无法找到（或理解）这个问题的解决方案。我提供下面的模型脚本。
注意：在模型的 train() 方法中，批量大小的默认值为 16。使用此配置，它会抛出错误，如我上面所示，当我调用此方法时，我将批量大小值设置为 1，并且它工作正常。
import os
import glob
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.utils.data import DataLoader
from torchvision import datasets, transforms
class ICModel(nn.Module):
def __init__(self):
super().__init__()
# CNN
self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=2)
self.conv2 = nn.Conv2d(64, 128, kernel_size=3, stride=2)
self.conv3 = nn.Conv2d(128, 256, kernel_size=3, stride=2)
self.conv4 = nn.Conv2d(256, 512, kernel_size=3, stride=2)
# FULLY CONNECTED LAYERS
self.fc1 = nn.Linear(61952, 256)
self.fc2 = nn.Linear(256, 64)
self.out = nn.Linear(64, 2)
def forward(self, x):
# CONV - 1
x = F.relu(self.conv1(x))
x = F.max_pool2d(x, kernel_size=3, stride=1)
# CONV - 2
x = F.relu(self.conv2(x))
x = F.max_pool2d(x, kernel_size=3, stride=1)
# CONV - 3
x = F.relu(self.conv3(x))
x = F.max_pool2d(x, kernel_size=3, stride=1)
# CONV - 4
x = F.relu(self.conv4(x))
flattened_size = x.shape[0] * x.shape[1] * x.shape[2] * x.shape[3]
x = x.view(-1, flattened_size)
# FULLY CONNECTED LAYERS
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.out(x)
return F.log_softmax(x, dim=1)
def train(self, dataset_dir='', epochs=5, batch_size=16, seed=35, learning_rate=0.001, model_weights_path=''):
if dataset_dir == '':
raise Exception("Please enter a valid dataset directory path!")
train_correct = []
train_losses = []
torch.manual_seed(seed)
# CRITERION AND OPTIMIZER SETUP
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(self.parameters(), lr=learning_rate)
optim_width, optim_height = 224, 224
data_transforms = transforms.Compose([
transforms.Resize((optim_width, optim_height)), # Resize images to average dimensions
transforms.ToTensor(), # Convert images to PyTorch tensors
transforms.Normalize(mean=[0.456, 0.456, 0.456], std=[0.456, 0.456, 0.456]) # Normalize images
])
dataset = datasets.ImageFolder(root=dataset_dir, transform=data_transforms)
train_loader = DataLoader(dataset=dataset, batch_size=batch_size, shuffle=True)
for epoch in range(epochs):
trn_corr = 0
for b, (X_train, y_train) in enumerate(train_loader):
b += 1
y_pred = self(X_train)
loss = criterion(y_pred, y_train)
predicted = torch.max(y_pred, dim=1)[1]
batch_corr = (predicted == y_train).sum()
trn_corr += batch_corr.item()
optimizer.zero_grad()
loss.backward()
optimizer.step()
if b % 4 == 0:
print(f'Epoch: {epoch} Batch: {b} Loss: {loss.item()}')
train_losses.append(loss)
train_correct.append(trn_corr)
if (model_weights_path != '') & os.path.exists(model_weights_path) & os.path.isdir(model_weights_path):
torch.save({
'model_state_dict': self.state_dict(),
'optimizer_state_dict': optimizer.state_dict()
}, model_weights_path)
def test(self, dataset_dir='', batch_size=16):
if dataset_dir == '':
raise Exception("Please enter a valid dataset directory path!")
optim_width, optim_height = 224, 224
test_losses = []
tst_crr = 0
criterion = nn.CrossEntropyLoss()
data_transforms = transforms.Compose([
transforms.Resize((optim_width, optim_height)), # Resize images to average dimensions
transforms.Grayscale(),
transforms.ToTensor(), # Convert images to PyTorch tensors
transforms.Normalize(mean=[0.456], std=[0.456]) # Normalize images
])
dataset = datasets.ImageFolder(root=dataset_dir, transform=data_transforms)
test_loader = DataLoader(dataset=dataset, batch_size=batch_size, shuffle=True)
with torch.no_grad():
for b, (X_test, y_test) in enumerate(test_loader):
y_val = self(X_test)
predicted = torch.max(y_val.data, dim=1)[1]
tst_crr += (predicted == y_test).sum()
loss = criterion(y_val, y_test)
test_losses.append(loss.item())
test_results = {
'true_positive': tst_crr,
'false_positive': len(dataset.imgs) - tst_crr
}
return test_results, test_losses
这是错误的完整回溯：
Traceback (most recent call last):
File "/Users/eaidy/Repos/ML/inclination-classification-pytorch/src/main.py", line 12, in <module>
ic_model.train(dataset_dir=train_dataset_absolute_path, epochs=1, batch_size=16, learning_rate=1e-5)
File "/Users/eaidy/Repos/ML/inclination-classification-pytorch/src/models/cnn_model.py", line 94, in train
loss = criterion(y_pred, y_train)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/eaidy/Repos/ML/inclination-classification-pytorch/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/eaidy/Repos/ML/inclination-classification-pytorch/.venv/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/eaidy/Repos/ML/inclination-classification-pytorch/.venv/lib/python3.11/site-packages/torch/nn/modules/loss.py", line 1179, in forward
return F.cross_entropy(input, target, weight=self.weight,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/eaidy/Repos/ML/inclination-classification-pytorch/.venv/lib/python3.11/site-packages/torch/nn/functional.py", line 3059, in cross_entropy
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ValueError: Expected input batch_size (1) to match target batch_size (16).
问题就在这里
flattened_size = x.shape[0] * x.shape[1] * x.shape[2] * x.shape[3]
x = x.view(-1, flattened_size)
x(batch_size, channels, height, width)flattened_size = batch_size * channels * height * widthx = x.view(-1, flattened_size)x(1, flattened_size)在损失计算中，您尝试计算
loss(x,y)x(1, flattened_size)y(bs,)展平时应保留批次尺寸：
x = x.view(x.shape[0], -1)
您还需要调整第一个全连接层的输入大小。