利用Python實現卷積神經網路的視覺化

model.summary()複製程式碼

_________________________________________________________________
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: 1,199,882
Trainable params: 1,199,882
Non-trainable params: 0複製程式碼

top_layer = model.layers[0]
plt.imshow(top_layer.get_weights()[0][:, :, :, 0].squeeze(), cmap=`gray`)複製程式碼

2.啟用方法

from vis.visualization import visualize_activation
from vis.utils import utils
from keras import activations

from matplotlib import pyplot as plt
%matplotlib inline
plt.rcParams[`figure.figsize`] = (18, 6)

# Utility to search for layer index by name.
# Alternatively we can specify this as -1 since it corresponds to the last layer.
layer_idx = utils.find_layer_idx(model, `preds`)

# Swap softmax with linear
model.layers[layer_idx].activation = activations.linear
model = utils.apply_modifications(model)

# This is the output node we want to maximize.
filter_idx = 0
img = visualize_activation(model, layer_idx, filter_indices=filter_idx)
plt.imshow(img[..., 0])複製程式碼

for output_idx in np.arange(10):
   # Lets turn off verbose output this time to avoid clutter and just see the output.
   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])複製程式碼

heatmap）。這使得我們直觀地瞭解影像的哪些部分對於該模型而言的重要性，以便對實際類別進行明確的區分。

def iter_occlusion(image, size=8):
    # taken from https://www.kaggle.com/blargl/simple-occlusion-and-saliency-maps

   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 # for example
data = val_x[i]
correct_class = np.argmax(val_y[i])

# input tensor for model.predict
inp = data.reshape(1, 28, 28, 1)

# image data for matplotlib`s imshow
img = data.reshape(28, 28)

# occlusion
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 defaultdict
counters = 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複製程式碼

3. 基於梯度的方法

class_idx = 0
indices = np.where(val_y[:, class_idx] == 1.)[0]

# pick some random input from here.
idx = indices[0]

# Lets sanity check the picked image.
from matplotlib import pyplot as plt
%matplotlib inline
plt.rcParams[`figure.figsize`] = (18, 6)

plt.imshow(val_x[idx][..., 0])


from vis.visualization import visualize_saliency
from vis.utils import utils
from keras import activations

# Utility to search for layer index by name. 
# Alternatively we can specify this as -1 since it corresponds to the last layer.
layer_idx = utils.find_layer_idx(model, `preds`)

# Swap softmax with linear
model.layers[layer_idx].activation = activations.linear
model = utils.apply_modifications(model)

grads = visualize_saliency(model, layer_idx, filter_indices=class_idx, seed_input=val_x[idx])
# Plot with `jet` colormap to visualize as a heatmap.
plt.imshow(grads, cmap=`jet`)


# This corresponds to the Dense linear layer.
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`)複製程式碼

from vis.visualization import visualize_cam

# This corresponds to the Dense linear layer.
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`)複製程式碼

總結

作者：Faizan Shaikh，譯者：海棠，審閱：袁虎。

原文連結