MindSpore ResNet50 模型构建及训练：错误分析与解决方案

MindSpore ResNet50 模型构建及训练：错误分析与解决方案/n/n本文将介绍使用 MindSpore 框架构建 ResNet50 模型并进行训练，并分析解决在模型构建阶段遇到的'pad_mode'参数类型错误。/n/n### 代码示例/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'''/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'''/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/n### 错误分析/n/n错误提示表明在 Conv2D 中，'pad_mode' 参数的类型应为字符串 'str'，但实际传入的是整型 'int' 类型的 '3'。/n/n根据代码，错误发生在初始化 ConvBlock 中的 Conv2D 时，传入的参数类型不符合要求。具体原因可能是：/n/n1. 调用 resnet50 函数时传入错误的参数: 检查 resnet50 函数的调用方式，确认是否正确传入 ResBlock 和 [3, 4, 6, 3] 作为参数。/n2. Conv2D 的实现问题: 仔细检查 ConvBlock 类中的 nn.Conv2d 初始化语句，确认 padding 参数是否应该传入字符串类型。/n/n### 解决方案/n/n1. 修正 Conv2D 的参数: 在 ConvBlock 类中的 nn.Conv2d 初始化语句中，将 padding=3 改为 padding='same' 或其他有效的字符串类型。/n2. 调整 resnet50 函数的调用: 如果 resnet50 函数的调用方式存在问题，则需要根据实际情况修改参数传入方式。/n/n/n### 总结/n/n在使用 MindSpore 框架构建模型时，需要仔细检查参数类型是否符合要求，避免出现类似的错误。对于 Conv2D 中的 'pad_mode' 参数，应使用字符串类型，例如 'same' 或 'valid' 等。/n/n本例中，错误的根本原因在于没有正确理解和使用 nn.Conv2d 中 'pad_mode' 参数的类型要求，导致了错误的出现。通过分析错误信息，定位到代码错误，并进行相应的修改，最终解决了问题。/n/n希望这篇文章能够帮助您更好地理解 MindSpore 框架中的 Conv2D 操作，并能够在使用 MindSpore 框架构建模型时，避免类似的错误出现。/n