Question

我已经在Pytorch中为该网络训练了224x224尺寸的图像和4个类。

class CustomConvNet(nn.Module):
    def __init__(self, num_classes):
        super(CustomConvNet, self).__init__()

        self.layer1 = self.conv_module(3, 64)
        self.layer2 = self.conv_module(64, 128)
        self.layer3 = self.conv_module(128, 256)
        self.layer4 = self.conv_module(256, 256)
        self.layer5 = self.conv_module(256, 512)
        self.gap = self.global_avg_pool(512, num_classes)
        #self.linear = nn.Linear(512, num_classes)
        #self.relu = nn.ReLU()
        #self.softmax = nn.Softmax()

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.layer4(out)
        out = self.layer5(out)
        out = self.gap(out)
        out = out.view(-1, 4)
        #out = self.linear(out)

        return out

    def conv_module(self, in_num, out_num):
        return nn.Sequential(
            nn.Conv2d(in_num, out_num, kernel_size=3, stride=1, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=(2, 2), stride=None))

    def global_avg_pool(self, in_num, out_num):
        return nn.Sequential(
            nn.Conv2d(in_num, out_num, kernel_size=3, stride=1, padding=1),
            #nn.BatchNorm2d(out_num),
            #nn.LeakyReLU(),

            nn.ReLU(),
            nn.Softmax(),
            nn.AdaptiveAvgPool2d((1, 1)))

我从第一个Conv2D获得了权重，大小为torch.Size([64, 3, 3, 3])

我将其另存为：

weightsCNN = net.layer1[0].weight.data
np.save('CNNweights.npy', weightsCNN)

这是我在Tensorflow中构建的模型。我想将从Pytorch模型中保存的权重传递到此Tensorflow CNN中。

    model = models.Sequential()
    model.add(layers.Conv2D(64, (3, 3), activation='relu', input_shape=(224, 224, 3)))
    model.add(layers.MaxPooling2D((2, 2)))

    model.add(layers.Conv2D(128, (3, 3), activation='relu'))
    model.add(layers.MaxPooling2D((2, 2)))

    model.add(layers.Conv2D(256, (3, 3), activation='relu'))
    model.add(layers.MaxPooling2D((2, 2)))

    model.add(layers.Conv2D(256, (3, 3), activation='relu'))
    model.add(layers.MaxPooling2D((2, 2)))

    model.add(layers.Conv2D(512, (3, 3), activation='relu'))
    model.add(layers.MaxPooling2D((2, 2)))

    model.add(layers.Conv2D(512, (3, 3), activation='relu'))

    model.add(layers.GlobalAveragePooling2D())
    model.add(layers.Dense(4, activation='softmax'))
    print(model.summary())


    adam = optimizers.Adam(learning_rate=0.0001, amsgrad=False)
    model.compile(loss='categorical_crossentropy',
                  optimizer=adam,
                  metrics=['accuracy'])


    nb_train_samples = 6596
    nb_validation_samples = 1290
    epochs = 10
    batch_size = 256


    history = model.fit_generator(
        train_generator,
        steps_per_epoch=np.ceil(nb_train_samples/batch_size),
        epochs=epochs,
        validation_data=validation_generator,
        validation_steps=np.ceil(nb_validation_samples / batch_size)
        )

实际上我该怎么做？ Tensorflow需要什么形状的砝码？谢谢！

Answer 1

您可以非常简单地检查所有keras层的所有权重的形状：

for layer in model.layers:
    print([tensor.shape for tensor in layer.get_weights()])

这将为您提供所有权重（包括偏差）的形状，因此您可以相应地准备加载的numpy权重。

要设置它们，请执行类似的操作：

for torch_weight, layer in zip(model.layers, torch_weights):
    layer.set_weights(torch_weight)

其中torch_weights应该是包含您必须加载的np.array列表的列表。

通常，torch_weights的每个元素将包含一个np.array来表示权重，一个用于偏见。

记住从打印中收到的形状必须与您在set_weights中放入的形状完全相同。

有关更多信息，请参见documentation。

顺便说一句。确切的形状取决于图层和模型执行的操作，有时可能需要转置一些数组以“适合它们”。

将CNN Pytorch中的预训练砝码传递到Tensorflow中的CNN

1 个答案: