【深度学习】使用Python可视化卷积神经网络方法汇总

model.summary()

_________________________________________________________________Layer (type)                 Output Shape              Param #   =================================================================conv2d_1 (Conv2D)            (None, 26, 26, 32)        320       _________________________________________________________________conv2d_2 (Conv2D)            (None, 24, 24, 64)        18496     _________________________________________________________________max_pooling2d_1 (MaxPooling2 (None, 12, 12, 64)        0         _________________________________________________________________dropout_1 (Dropout)          (None, 12, 12, 64)        0         _________________________________________________________________flatten_1 (Flatten)          (None, 9216)              0         _________________________________________________________________dense_1 (Dense)              (None, 128)               1179776   _________________________________________________________________dropout_2 (Dropout)          (None, 128)               0         _________________________________________________________________preds (Dense)                (None, 10)                1290      =================================================================Total params: 1,199,882Trainable params: 1,199,882Non-trainable params: 0

top_layer = model.layers[0]plt.imshow(top_layer.get_weights()[0][:, :, :, 0].squeeze(), cmap='gray')

from vis.visualization import visualize_activationfrom vis.utils import utilsfrom keras import activations
from matplotlib import pyplot as plt%matplotlib inlineplt.rcParams['figure.figsize'] = (18, 6)
# 按名称搜索图层索引。# 或者，我们可以将其指定为-1，因为它对应于最后一层。layer_idx = utils.find_layer_idx(model, 'preds')
#用线性层替换softmaxmodel.layers[layer_idx].activation = activations.linearmodel = utils.apply_modifications(model)
# 这是我们要最大化的输出节点。filter_idx = 0img = visualize_activation(model, layer_idx, filter_indices=filter_idx)plt.imshow(img[..., 0])

for output_idx in np.arange(10):   # 让我们这次关闭详细输出以避免混乱   img = visualize_activation(model, layer_idx, filter_indices=output_idx, input_range=(0., 1.))   plt.figure()   plt.title('Networks perception of {}'.format(output_idx))   plt.imshow(img[..., 0])

def iter_occlusion(image, size=8):
   occlusion = np.full((size * 5, size * 5, 1), [0.5], np.float32)   occlusion_center = np.full((size, size, 1), [0.5], np.float32)   occlusion_padding = size * 2
   # print('padding...')   image_padded = np.pad(image, ( \   (occlusion_padding, occlusion_padding), (occlusion_padding, occlusion_padding), (0, 0) \   ), 'constant', constant_values = 0.0)
   for y in range(occlusion_padding, image.shape[0] + occlusion_padding, size):



    
       for x in range(occlusion_padding, image.shape[1] + occlusion_padding, size):           tmp = image_padded.copy()
           tmp[y - occlusion_padding:y + occlusion_center.shape[0] + occlusion_padding, \             x - occlusion_padding:x + occlusion_center.shape[1] + occlusion_padding] \             = occlusion
           tmp[y:y + occlusion_center.shape[0], x:x + occlusion_center.shape[1]] = occlusion_center
           yield x - occlusion_padding, y - occlusion_padding, \             tmp[occlusion_padding:tmp.shape[0] - occlusion_padding, occlusion_padding:tmp.shape[1] - occlusion_padding]
i = 23 # 例如data = val_x[i]correct_class = np.argmax(val_y[i])
# model.predict的输入向量inp = data.reshape(1, 28, 28, 1)
# matplotlib imshow函数的图片img = data.reshape(28, 28)
# 遮盖img_size = img.shape[0]occlusion_size = 4
print('occluding...')
heatmap = np.zeros((img_size, img_size), np.float32)class_pixels = np.zeros((img_size, img_size), np.int16)
from collections import defaultdictcounters = defaultdict(int)
for n, (x, y, img_float) in enumerate(iter_occlusion(data, size=occlusion_size)):
    X = img_float.reshape(1, 28, 28, 1)    out = model.predict(X)    #print('#{}: {} @ {} (correct class: {})'.format(n, np.argmax(out), np.amax(out), out[0][correct_class]))    #print('x {} - {} | y {} - {}'.format(x, x + occlusion_size, y, y + occlusion_size))
    heatmap[y:y + occlusion_size, x:x + occlusion_size] = out[0][correct_class]    class_pixels[y:y + occlusion_size, x:x + occlusion_size] = np.argmax(out)    counters[np.argmax(out)] += 1

class_idx = 0indices = np.where(val_y[:, class_idx] == 1.)[0]
# 从这里选取一些随机输入。idx = indices[0]
# 让sanity检查选中的图像。from matplotlib import pyplot as plt%matplotlib inlineplt.rcParams['figure.figsize'] = (18, 6)
plt.imshow(val_x[idx][..., 0])

from vis.visualization import visualize_saliencyfrom vis.utils import utilsfrom keras import activations
# 按名称搜索图层索引


    
# 或者，我们可以将其指定为-1，因为它对应于最后一层。layer_idx = utils.find_layer_idx(model, 'preds')
# 用线性层替换softmaxmodel.layers[layer_idx].activation = activations.linearmodel = utils.apply_modifications(model)
grads = visualize_saliency(model, layer_idx, filter_indices=class_idx, seed_input=val_x[idx])# 可视化为热图。plt.imshow(grads, cmap='jet')

# 线性层。for class_idx in np.arange(10):     indices = np.where(val_y[:, class_idx] == 1.)[0]    idx = indices[0]
    f, ax = plt.subplots(1, 4)    ax[0].imshow(val_x[idx][..., 0])
    for i, modifier in enumerate([None, 'guided', 'relu']):        grads = visualize_saliency(model, layer_idx, filter_indices=class_idx,         seed_input=val_x[idx], backprop_modifier=modifier)        if modifier is None:            modifier = 'vanilla'        ax[i+1].set_title(modifier)         ax[i+1].imshow(grads, cmap='jet')

from vis.visualization import visualize_cam
# 线性层。for class_idx in np.arange(10):  indices = np.where(val_y[:, class_idx] == 1.)[0] idx = indices[0]
f, ax = plt.subplots(1, 4) ax[0].imshow(val_x[idx][..., 0])
for i, modifier in enumerate([None, 'guided', 'relu']):    grads = visualize_cam(model, layer_idx, filter_indices=class_idx,     seed_input=val_x[idx], backprop_modifier=modifier)     if modifier is None:        modifier = 'vanilla'    ax[i+1].set_title(modifier)     ax[i+1].imshow(grads, cmap='jet')