《python深度学习》卷积神经网络的可视化

import tensorflow as tf
import tensorflow.keras
tensorflow.keras.__version__
from tensorflow.keras import models
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing import image
import numpy as np
import matplotlib.pyplot as plt


model = load_model('E:/zbx_code/plantimg.h5')
model.summary()  # As a reminder.
img_path = 'E:/plant_img/resize/orig_plant_img_percent70_resize_224/potato_resize_224/1.jpg'

# We preprocess the image into a 4D tensor
img = image.load_img(img_path, target_size=(224, 224))
img_tensor = image.img_to_array(img)
img_tensor = np.expand_dims(img_tensor, axis=0)
# Remember that the model was trained on inputs
# that were preprocessed in the following way:
img_tensor /= 255.

# Its shape is (1, 150, 150, 3)
print(img_tensor.shape)

# plt.imshow(img_tensor[0])
# plt.show()

# Extracts the outputs of the top 8 layers:
layer_outputs = [layer.output for layer in model.layers[:8]]
# Creates a model that will return these outputs, given the model input:
activation_model = models.Model(inputs=model.input, outputs=layer_outputs)

# This will return a list of 5 Numpy arrays:
# one array per layer activation
activations = activation_model.predict(img_tensor)

# first_layer_activation = activations[0]
# print(first_layer_activation.shape)

# # plt.matshow(first_layer_activation[0, :, :, 3], cmap='viridis')
# # plt.show()

# plt.matshow(first_layer_activation[0, :, :, 2], cmap='viridis')
# plt.show()

# These are the names of the layers, so can have them as part of our plot
layer_names = []
for layer in model.layers[:8]:
    layer_names.append(layer.name)

images_per_row = 16

# Now let's display our feature maps
for layer_name, layer_activation in zip(layer_names, activations):
    # This is the number of features in the feature map
    n_features = layer_activation.shape[-1]

    # The feature map has shape (1, size, size, n_features)
    size = layer_activation.shape[1]

    # We will tile the activation channels in this matrix
    n_cols = n_features // images_per_row
    display_grid = np.zeros((size * n_cols, images_per_row * size))
    print(type(display_grid))
    # We'll tile each filter into this big horizontal grid
    for col in range(n_cols):
        for row in range(images_per_row):
            channel_image = layer_activation[0,:, :,col * images_per_row + row]
            # Post-process the feature to make it visually palatable
            channel_image -= channel_image.mean()
            channel_image /= channel_image.std()
            channel_image *= 64
            channel_image += 128
            channel_image = np.clip(channel_image, 0, 255).astype('uint8')
            print(channel_image)
            display_grid[col * size : (col + 1) * size,
                         row * size : (row + 1) * size] = channel_image
            # print(display_grid.shape[0])
    # Display the grid
    scale = 1. / size
    # print(scale*display_grid[0])
    plt.figure(figsize=(int(scale * (display_grid.shape[1])),
                        int(scale * display_grid.shape[1])))
    plt.title(layer_name)
    plt.grid(False)
    plt.imshow(display_grid, aspect='equal', cmap='viridis')
    plt.savefig('E:/featureimg/' + layer_name + '.jpg')
plt.show()