我如何在预测阶段获得所有输出的keras层（特征图）？

Question

我尝试获取 cfiar 数据集并尝试获取每个输出的特征图，将其中一张测试图像作为输入。

(train_images, train_labels), (test_images, test_labels) = datasets.cifar10.load_data()

# Normalize pixel values to be between 0 and 1
train_images, test_images = train_images / 255.0, test_images / 255.0

class_names = ['airplane', 'automobile', 'bird', 'cat', 'deer',
           'dog', 'frog', 'horse', 'ship', 'truck']

model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10))

model.compile(optimizer='adam',
          loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
          metrics=['accuracy'])

history = model.fit(train_images, train_labels, epochs=10, 
                validation_data=(test_images, test_labels))

test_loss, test_acc = model.evaluate(test_images,  test_labels, verbose=2)

layer_input = test_images[0]                  

for i in range(len(model.layers)):
    get_layer_output = K.function(inputs = model.layers[i].input, outputs = model.layers[i].output)
    print(get_layer_output(layer_input))
    layer_input = model.layers[i].output

我的感觉是我误解了一些关于如何设置输入以及如何在预测期间获取输出的内容。

Answer 1

如果您使用 Sequential 模型，您应该将输入设置为 model.layers[0].input。

首先，将测试输入的维度扩展为包括Batch_Size:

layer_input = test_images[0]    
plt.imshow(layer_input)   # Plot Test Image
layer_input = tf.expand_dims(layer_input,0)   # Add prefix of Batch Size 
print(layer_input.shape)  # Prints  : (1, 32, 32, 3)

输出:

修改绘图代码：

for i in range(len(model.layers)):
    get_layer_output = K.function(inputs = model.layers[0].input, outputs = model.layers[i].output)

    get_1_output = get_layer_output(layer_input)
    # print(get_1_output.shape) << Use this to check if the Output shape matches the shape of Model.summary()

    if get_1_output.ndim == 4:             # Check for Dimensionality to plot ONE feature map (Batch size, Length, Width
      plt.imshow(get_1_output[0][:,:,:3])  # Plots the output of Conv2D and MaxPooling
    else:
      print(get_1_output)   # If not Image, ie. Array, print the Values

    plt.show()

输出:

希望我回答了你的问题。

我如何在预测阶段获得所有输出的keras层（特征图）？

How can i get the all output keras layers (features maps) during prediction phase?

python

deep-learning

conv-neural-network

keras

tensorflow2.0