[2]
%load_ext watermark
%watermark -a "Romell D.Z." -u -d -p numpy,pandas,matplotlib,keras
The watermark extension is already loaded. To reload it, use: %reload_ext watermark Romell D.Z. last updated: 2019-02-22 numpy 1.16.1 pandas 0.23.4 matplotlib 2.2.2 keras 2.2.4

Filters with KERAS Preprocessing

[1]
%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
[4]
from keras.applications.vgg16 import VGG16, preprocess_input, decode_predictions
from keras.models import Model
from keras.preprocessing import image
from keras.optimizers import SGD
[5]
path_photo_a = 'snapshot/teamA.jpg'
photo_a = image.load_img(path_photo_a,target_size=(224,224))
plt.imshow(photo_a)
<matplotlib.image.AxesImage at 0x10c497978>
[6]
vgg16_model = VGG16(weights='imagenet', include_top=True)
sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
vgg16_model.compile(optimizer=sgd, loss='categorical_crossentropy')
[7]
vgg16_model.summary()
_________________________________________________________________ Layer (type) Output Shape Param # ================================================================= input_1 (InputLayer) (None, 224, 224, 3) 0 _________________________________________________________________ block1_conv1 (Conv2D) (None, 224, 224, 64) 1792 _________________________________________________________________ block1_conv2 (Conv2D) (None, 224, 224, 64) 36928 _________________________________________________________________ block1_pool (MaxPooling2D) (None, 112, 112, 64) 0 _________________________________________________________________ block2_conv1 (Conv2D) (None, 112, 112, 128) 73856 _________________________________________________________________ block2_conv2 (Conv2D) (None, 112, 112, 128) 147584 _________________________________________________________________ block2_pool (MaxPooling2D) (None, 56, 56, 128) 0 _________________________________________________________________ block3_conv1 (Conv2D) (None, 56, 56, 256) 295168 _________________________________________________________________ block3_conv2 (Conv2D) (None, 56, 56, 256) 590080 _________________________________________________________________ block3_conv3 (Conv2D) (None, 56, 56, 256) 590080 _________________________________________________________________ block3_pool (MaxPooling2D) (None, 28, 28, 256) 0 _________________________________________________________________ block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160 _________________________________________________________________ block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808 _________________________________________________________________ block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808 _________________________________________________________________ block4_pool (MaxPooling2D) (None, 14, 14, 512) 0 _________________________________________________________________ block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808 _________________________________________________________________ block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808 _________________________________________________________________ block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808 _________________________________________________________________ block5_pool (MaxPooling2D) (None, 7, 7, 512) 0 _________________________________________________________________ flatten (Flatten) (None, 25088) 0 _________________________________________________________________ fc1 (Dense) (None, 4096) 102764544 _________________________________________________________________ fc2 (Dense) (None, 4096) 16781312 _________________________________________________________________ predictions (Dense) (None, 1000) 4097000 ================================================================= Total params: 138,357,544 Trainable params: 138,357,544 Non-trainable params: 0 _________________________________________________________________
[8]
photo_a = image.img_to_array(photo_a)
photo_a = np.expand_dims(photo_a, axis=0)
photo_a = preprocess_input(photo_a)
[9]
model = Model(input=vgg16_model.input, 
              output=vgg16_model.get_layer('block1_pool').output)
model.compile(optimizer=sgd, loss='categorical_crossentropy')

pool_features1 = model.predict(photo_a)
pool_features1.shape
/Users/romelldominguez/anaconda3/lib/python3.6/site-packages/ipykernel_launcher.py:2: UserWarning: Update your `Model` call to the Keras 2 API: `Model(inputs=Tensor("in..., outputs=Tensor("bl...)` 
(1, 112, 112, 64)
[15]
fig, axes = plt.subplots(8, 8, figsize=(15, 15))
axes = np.ravel(axes)
for i in range(pool_features1.shape[3]):
    axes[i].imshow(255-pool_features1[0, :, :, i], interpolation="nearest")
    axes[i].set_xticks([])
    axes[i].set_yticks([])
plt.xticks([])
plt.yticks([])
plt.tight_layout()
plt.show()