MindSpore ResNet50 模型训练代码错误分析及修复

MindSpore ResNet50 模型训练代码错误分析及修复/n/n本文分析了 MindSpore ResNet50 模型训练代码中出现的 'TypeError: For 'Conv2D', the type of 'pad_mode' should be 'str', but got '3' with type 'int'.' 错误，并提供了详细的代码修复方法。/n/n错误代码：/n/npython/nimport mindspore.nn as nn/nimport mindspore.ops as ops/nimport mindspore.common.dtype as mstype/nimport os/nimport numpy as np/nfrom mindspore import Tensor/nfrom PIL import Image/nfrom mindspore.dataset import vision/nfrom mindspore import Model # 承载网络结构/nfrom mindspore.nn.metrics import Accuracy # 测试模型用/nfrom mindspore.train.callback import LossMonitor/n/n/nclass ConvBlock(nn.Cell):/n def __init__(self, in_channels, out_channels, kernel_size=3, stride=1, padding=1):/n super(ConvBlock, self).__init__()/n self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding, has_bias=False)/n self.bn = nn.BatchNorm2d(out_channels)/n self.relu = nn.ReLU()/n/n def construct(self, x):/n x = self.conv(x)/n x = self.bn(x)/n x = self.relu(x)/n return x/n/nclass ResBlock(nn.Cell):/n def __init__(self, in_channels, out_channels, stride=1):/n super(ResBlock, self).__init__()/n self.conv1 = ConvBlock(in_channels, out_channels, stride=stride)/n self.conv2 = ConvBlock(out_channels, out_channels, kernel_size=3, stride=1, padding=1)/n self.downsample = nn.SequentialCell([nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=stride, has_bias=False), nn.BatchNorm2d(out_channels)])/n self.relu = nn.ReLU()/n/n def construct(self, x):/n identity = x/n x = self.conv1(x)/n x = self.conv2(x)/n if self.downsample is not None:/n identity = self.downsample(identity)/n x = x + identity/n x = self.relu(x)/n return x/n/nclass ResNet(nn.Cell):/n def __init__(self, block, layers, num_classes=1000):/n super(ResNet, self).__init__()/n self.in_channels = 64/n self.conv1 = ConvBlock(3, 64, kernel_size=7, stride=2, padding=3)/n self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, pad_mode='same')/n self.layer1 = self._make_layer(block, 64, layers[0])/n self.layer2 = self._make_layer(block, 128, layers[1], stride=2)/n self.layer3 = self._make_layer(block, 256, layers[2], stride=2)/n self.layer4 = self._make_layer(block, 512, layers[3], stride=2)/n self.avgpool = nn.AvgPool2d(7, 1)/n self.dropout = nn.Dropout(0.4)/n self.fc = nn.Dense(512 * block.expansion, num_classes)/n/n def _make_layer(self, block, out_channels, blocks, stride=1):/n downsample = None/n if stride != 1 or self.in_channels != out_channels * block.expansion:/n downsample = nn.SequentialCell([nn.Conv2d(self.in_channels, out_channels * block.expansion, kernel_size=1, stride=stride, has_bias=False), nn.BatchNorm2d(out_channels * block.expansion)])/n layers = []/n layers.append(block(self.in_channels, out_channels, stride, downsample))/n self.in_channels = out_channels * block.expansion/n for i in range(1, blocks):/n layers.append(block(self.in_channels, out_channels))/n return nn.SequentialCell(layers)/n/n def construct(self, x):/n x = self.conv1(x)/n x = self.maxpool(x)/n x = self.layer1(x)/n x = self.layer2(x)/n x = self.layer3(x)/n x = self.layer4(x)/n x = self.avgpool(x)/n x = self.dropout(x)/n x = ops.Reshape()(x, (-1, 512 * 1 * 1))/n x = self.fc(x)/n return x/n/nlenet = ResNet()/n/ndef resnet50():/n return ResNet(ResBlock, [3, 4, 6, 3])/n/n# 加载预训练集'''''/n'''''''''/ndef load_dataset(data_path):/n images = []/n labels = []/n for subdir in os.listdir(data_path):/n subpath = os.path.join(data_path, subdir)/n for filename in os.listdir(subpath):/n imgpath = os.path.join(subpath, filename)/n img = Image.open(imgpath)/n img = img.resize((224, 224))/n img = np.array(img).astype(np.float32)/n img = img.transpose((2, 0, 1))/n images.append(img)/n labels.append(int(subdir))/n images = np.array(images)/n labels = np.array(labels)/n return Tensor(images), Tensor(labels)/n'''''''''''/nnet_loss = nn.SoftmaxCrossEntropyWithLogits(sparse=True)/nlr = 0.01/nmomentum = 0.9/nnet_opt = nn.Momentum(lenet.trainable_params(), lr, momentum)/nmodel = Model(lenet, net_loss, net_opt, metrics={'accuracy': Accuracy()})/n/nloss_cb = LossMonitor(per_print_times=train_data.get_dataset_size())/n# 训练模型/nmodel.train(3, train_data, loss_cb) # 训练3个epoch/nmodel.eval(test_data)/n中文/nTraceback (most recent call last):/n File /'D://pythonProject6//trainmodel.py/', line 91, in <module>/n net = resnet50()/n File /'D://pythonProject6//trainmodel.py/', line 85, in resnet50/n return ResNet(ResBlock, [3, 4, 6, 3])/n File /'D://pythonProject6//trainmodel.py/', line 50, in __init__/n self.conv1 = ConvBlock(3, 64, kernel_size=7, stride=2, padding=3)/n File /'D://pythonProject6//trainmodel.py/', line 18, in __init__/n self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding, has_bias=False)/n File /'D://miniconda3//envs//MindSpore//lib//site-packages//mindspore/_extends//utils.py/', line 46, in deco/n fn(self, *args, **kwargs)/n File /'D://miniconda3//envs//MindSpore//lib//site-packages//mindspore//nn//layer//conv.py/', line 304, in __init__/n data_format=self.data_format)/n File /'D://miniconda3//envs//MindSpore//lib//site-packages//mindspore//ops//primitive.py/', line 654, in deco/n fn(self, *args, **kwargs)/n File /'D://miniconda3//envs//MindSpore//lib//site-packages//mindspore//ops//operations//nn_ops.py/', line 1252, in __init__/n validator.check_value_type('pad_mode', pad_mode, [str], self.name)/n File /'D://miniconda3//envs//MindSpore//lib//site-packages//mindspore/_checkparam.py/', line 654, in check_value_type/n raise_error_msg()/n File /'D://miniconda3//envs//MindSpore//lib//site-packages//mindspore/_checkparam.py/', line 643, in raise_error_msg/n raise TypeError(f'{msg_prefix} type of /'{arg_name}/' should be {'one of ' if num_types > 1 else ''}'TypeError: For 'Conv2D', the type of 'pad_mode' should be 'str', but got '3' with type 'int'./n/n**错误原因：**/n/n根据错误提示，代码中在调用`nn.Conv2d`时，传入的`pad_mode`参数应该是一个字符串，但实际传入了一个整数`3`。需要检查一下`ConvBlock`和`ResNet`类中的`Conv2d`层调用是否正确。/n/n**代码修复：**/n/n在`ConvBlock`类中，`nn.Conv2d`的`padding`参数表示填充大小，而`pad_mode`表示填充模式，应该设置为字符串，例如'SAME'或'VALID'。修改后的代码如下：/n/npython/nclass ConvBlock(nn.Cell):/n def init(self, in_channels, out_channels, kernel_size=3, stride=1, padding=1, pad_mode='same'):/n super(ConvBlock, self).init()/n self.conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding, has_bias=False, pad_mode=pad_mode)/n self.bn = nn.BatchNorm2d(out_channels)/n self.relu = nn.ReLU()/n/n def construct(self, x):/n x = self.conv(x)/n x = self.bn(x)/n x = self.relu(x)/n return x/n```/n/n总结：/n/n通过将ConvBlock类中的pad_mode参数设置为字符串'same'，修复了代码中的错误。在使用MindSpore框架时，务必仔细阅读官方文档，确保参数类型和值符合要求，避免出现类似错误。/n