MindSpore ResNet 模型加载错误：ValueError: The primitive[Conv2D]'s x shape size must be equal to 4, but got 3.

这个报错是因为在调用load_model_from_ckpt()函数加载模型参数时，模型的输入形状与训练时不一致导致的。具体来说，训练时模型的输入数据是一个batch的数据，形状为(batch_size, 3, 100, 100)，而在加载模型参数时，只传入了一个样本的数据，形状为(3, 100, 100)，这导致了输入形状不一致的问题。

解决方法是在调用load_model_from_ckpt()函数时，指定一个输入数据的形状，例如：

input_shape = (1, 3, 100, 100)  # 模型输入数据的形状
network = load_model_from_ckpt(input_shape)

然后在load_model_from_ckpt()函数中将这个形状传递给模型的输入层，例如：

class ResNet(nn.Cell):
    def __init__(self, block, layers, num_classes=34, input_shape=None):
        super(ResNet, self).__init__()
        self.in_channels = 64
        self.input_shape = input_shape  # 保存输入形状

        self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2,   pad_mode='valid')
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU()
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2,   pad_mode='valid')

        self.layer1 = self.make_layer(block, 64, layers[0])
        self.layer2 = self.make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self.make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self.make_layer(block, 512, layers[3], stride=2)

        self.avgpool = nn.AvgPool2d(kernel_size=3, stride=1,   pad_mode='valid')
        self.fc = nn.Dense(512 * block.expansion, num_classes)

    def construct(self, x):
        if self.input_shape is not None:
            x = ops.Reshape()(x, self.input_shape)  # 将输入数据形状转换为(batch_size, channels, height, width)
        x = self.conv1(x)
        x = self.bn1(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        x = self.avgpool(x)
        x = ops.Reshape()(x, (ops.Shape()(x)[0], -1))
        x = self.fc(x)

        return x

def load_model_from_ckpt(input_shape):
    context.set_context(mode=context.GRAPH_MODE, device_target='CPU')
    # 创建ResNet模型
    network = ResNet(ResidualBlock,[2,2,2,2], input_shape=input_shape)
    # 加载ckpt文件中的模型参数
    param_dict = load_checkpoint('D:/pythonproject2/ckpt/checkpoint_resnet_1-20_49.ckpt')
     #将模型参数加载到模型中
    load_param_into_net(network, param_dict)
    # 返回模型
    return network