In [ ]:
Visualization of Convolutional Filters¶
In [1]:
%tensorflow_version 1.x
# load vgg model
from keras.applications.vgg16 import VGG16
# load the model
model = VGG16()
from keras.applications.vgg16 import preprocess_input
TensorFlow 1.x selected.
Using TensorFlow backend.
WARNING:tensorflow:From /tensorflow-1.15.2/python3.7/tensorflow_core/python/ops/resource_variable_ops.py:1630: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version. Instructions for updating: If using Keras pass *_constraint arguments to layers. WARNING:tensorflow:From /tensorflow-1.15.2/python3.7/keras/backend/tensorflow_backend.py:4070: The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead. Downloading data from https://github.com/fchollet/deep-learning-models/releases/download/v0.1/vgg16_weights_tf_dim_ordering_tf_kernels.h5 553467904/553467096 [==============================] - 13s 0us/step
In [2]:
# summarize the model
model.summary()
Model: "vgg16" _________________________________________________________________ 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 _________________________________________________________________
In [3]:
# summarize filter shapes
for layer in model.layers:
# check for convolutional layer
if 'conv' not in layer.name:
continue
# get filter weights
filters, biases = layer.get_weights()
print(layer.name, filters.shape)
block1_conv1 (3, 3, 3, 64) block1_conv2 (3, 3, 64, 64) block2_conv1 (3, 3, 64, 128) block2_conv2 (3, 3, 128, 128) block3_conv1 (3, 3, 128, 256) block3_conv2 (3, 3, 256, 256) block3_conv3 (3, 3, 256, 256) block4_conv1 (3, 3, 256, 512) block4_conv2 (3, 3, 512, 512) block4_conv3 (3, 3, 512, 512) block5_conv1 (3, 3, 512, 512) block5_conv2 (3, 3, 512, 512) block5_conv3 (3, 3, 512, 512)
In [4]:
# retrieve weights from the second hidden layer
filters, biases = model.layers[1].get_weights()
In [5]:
# normalize filter values to 0-1 so we can visualize them
f_min, f_max = filters.min(), filters.max()
filters = (filters - f_min) / (f_max - f_min)
In [6]:
import matplotlib.pyplot as plt
# plot first few filters
n_filters, ix = 6, 1
for i in range(n_filters):
# get the filter
f = filters[:, :, :, i]
# plot each channel separately
for j in range(3):
# specify subplot and turn of axis
ax = plt.subplot(n_filters, 3, ix)
ax.set_xticks([])
ax.set_yticks([])
# plot filter channel in grayscale
plt.imshow(f[:, :, j], cmap='gray')
ix += 1
# show the figure
plt.show()
In [7]:
from google.colab import drive
drive.mount('/content/drive')
Mounted at /content/drive
In [8]:
# plot feature map of first conv layer for given image
from keras.applications.vgg16 import preprocess_input
from keras.preprocessing.image import load_img
from keras.preprocessing.image import img_to_array
from keras.models import Model
import matplotlib.pyplot as plt
from numpy import expand_dims
In [9]:
# load the model
model = VGG16()
# redefine model to output right after the first hidden layer
model = Model(inputs=model.inputs, outputs=model.layers[15].output)
model.summary()
Model: "model_1" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= input_2 (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 ================================================================= Total params: 9,995,072 Trainable params: 9,995,072 Non-trainable params: 0 _________________________________________________________________
In [11]:
# load the image with the required shape
img = load_img('/content/drive/MyDrive/CommonFiles/MUSA650-Data/bird.jpg', target_size=(224, 224))
# convert the image to an array
img = img_to_array(img)
# expand dimensions so that it represents a single 'sample'
img = expand_dims(img, axis=0)
img.shape
Out[11]:
(1, 224, 224, 3)
In [12]:
# prepare the image (e.g. scale pixel values for the vgg)
img = preprocess_input(img)
img.shape
Out[12]:
(1, 224, 224, 3)
In [13]:
plt.imshow(img.squeeze())
Clipping input data to the valid range for imshow with RGB data ([0..1] for floats or [0..255] for integers).
Out[13]:
<matplotlib.image.AxesImage at 0x7ff7938ba450>
In [14]:
# get feature map for first hidden layer
feature_maps = model.predict(img)
WARNING:tensorflow:From /tensorflow-1.15.2/python3.7/keras/backend/tensorflow_backend.py:422: The name tf.global_variables is deprecated. Please use tf.compat.v1.global_variables instead.
In [15]:
feature_maps.shape
Out[15]:
(1, 14, 14, 512)
In [16]:
square = 8
ix = 1
plt.figure(figsize=(15,15))
for _ in range(square):
for _ in range(square):
# specify subplot and turn of axis
ax = plt.subplot(square, square, ix)
ax.set_xticks([])
ax.set_yticks([])
# plot filter channel in grayscale
plt.imshow(feature_maps[0, :, :, ix-1], cmap='gray')
ix += 1
# show the figure
plt.show()
