def my_model():
# prep layers
inp = layers.Input(shape=(32, 32, 3))
x = layers.Conv2D(64, 3, padding='same')(inp)
x = layers.BatchNormalization(momentum=0.8)(x)
x = layers.LeakyReLU(alpha=0.1)(x)
# layer1
x = layers.Conv2D(128, 3, padding='same')(x)
x = layers.MaxPool2D()(x)
x = layers.BatchNormalization(momentum=0.8)(x)
x = layers.LeakyReLU(alpha=0.1)(x)
x = layers.Add()([x, residual(x, 128)])
# layer2
x = layers.Conv2D(256, 3, padding='same')(x)
x = layers.MaxPool2D()(x)
x = layers.BatchNormalization(momentum=0.8)(x)
x = layers.LeakyReLU(alpha=0.1)(x)
# layer3
x = layers.Conv2D(512, 3, padding='same')(x)
x = layers.MaxPool2D()(x)
x = layers.BatchNormalization(momentum=0.8)(x)
x = layers.LeakyReLU(alpha=0.1)(x)
x = layers.Add()([x, residual(x, 512)])
# layers4
x = layers.GlobalMaxPool2D()(x)
x = layers.Flatten()(x)
x = layers.Dense(10)(x)
x = layers.Activation('softmax', dtype='float32')(x)
model = tf.keras.Model(inputs=inp, outputs=x)
return model
def ResNet9(input_size: Tuple[int, int, int] = (32, 32, 3),
classes: int = 10) -> tf.keras.Model:
"""A small 9-layer ResNet Tensorflow model for cifar10 image classification.
The model architecture is from https://github.com/davidcpage/cifar10-fast
Args:
input_size: The size of the input tensor (height, width, channels).
classes: The number of outputs the model should generate.
Raises:
ValueError: Length of `input_size` is not 3.
ValueError: `input_size`[0] or `input_size`[1] is not a multiple of 16.
Returns:
A TensorFlow ResNet9 model.
"""
_check_input_size(input_size)
# prep layers
inp = layers.Input(shape=input_size)
x = layers.Conv2D(64, 3, padding='same')(inp)
x = layers.BatchNormalization(momentum=0.8)(x)
x = layers.LeakyReLU(alpha=0.1)(x)
# layer1
x = layers.Conv2D(128, 3, padding='same')(x)
x = layers.MaxPool2D()(x)
x = layers.BatchNormalization(momentum=0.8)(x)
x = layers.LeakyReLU(alpha=0.1)(x)
x = layers.Add()([x, residual(x, 128)])
# layer2
x = layers.Conv2D(256, 3, padding='same')(x)
x = layers.MaxPool2D()(x)
x = layers.BatchNormalization(momentum=0.8)(x)
x = layers.LeakyReLU(alpha=0.1)(x)
# layer3
x = layers.Conv2D(512, 3, padding='same')(x)
x = layers.MaxPool2D()(x)
x = layers.BatchNormalization(momentum=0.8)(x)
x = layers.LeakyReLU(alpha=0.1)(x)
x = layers.Add()([x, residual(x, 512)])
# layers4
x = layers.GlobalMaxPool2D()(x)
x = layers.Flatten()(x)
x = layers.Dense(classes)(x)
x = layers.Activation('softmax', dtype='float32')(x)
model = tf.keras.Model(inputs=inp, outputs=x)
return model
def get_quantize_outputs_removal_test_model(input_shape):
# (input)
# / / \ \
# (conv1) (conv2) (conv3) (conv4)
# | | \ \
# | | \ \
# (flatten1) (flatten1) (flatten2) (GlobalMaxPool2D)
# \ | / /
# (keras_concat) /
# \ /
# (tf_concat)
# /
# (keras_reshape)
# /
# (tf_reshape)
inputs = tf.keras.Input(shape=input_shape[1:], name='input')
conv1 = layers.Conv2D(3, 8, name='conv1')
conv2 = layers.Conv2D(3, 8, name='conv2')
conv3 = layers.Conv2D(3, 8, name='conv3')
conv4 = layers.Conv2D(3, 8, name='conv4')
flatten1 = layers.Flatten()
flatten2 = layers.Flatten()
keras_concat = layers.Concatenate(name='keras_concat')
x1 = conv1(inputs)
x1 = flatten1(x1)
x2 = conv2(inputs)
x2 = flatten1(x2)
x3 = conv3(inputs)
x3 = flatten2(x3)
x4 = conv4(inputs)
x4 = layers.GlobalMaxPool2D()(x4)
x123 = keras_concat([x1, x2, x3])
x = tf.concat([x123, x4], -1, name='tf_concat')
x = layers.Reshape((-1, 4), name='keras_reshape')(x)
outputs = tf.reshape(x, (-1, 2, 2), name='tf_reshape')
return tf.keras.Model(inputs=inputs, outputs=outputs)
#-*-encoding:utf-8-*-
import numpy as np
import tensorflow as tf
from tensorflow.python.keras import layers
encode_input = tf.keras.Input(shape=(28, 28, 1), name='src_img')
h1 = layers.Conv2D(16, 3, activation=tf.nn.relu)(encode_input)
h1 = layers.Conv2D(32, 3, activation=tf.nn.relu)(h1)
h1 = layers.MaxPool2D(3)(h1)
h1 = layers.Conv2D(32, 3, activation='relu')(h1)
h1 = layers.Conv2D(16, 3, activation='relu')(h1)
encode_output = layers.GlobalMaxPool2D()(h1)
encode_model = tf.keras.Model(inputs=encode_input,
outputs=encode_output,
name='encoder')
encode_model.summary()
decode_input = tf.keras.Input(shape=(16, ), name='encoded_img')
h2 = layers.Reshape((4, 4, 1))(decode_input)
h2 = layers.Conv2DTranspose(16, 3, activation='relu')(h2)
h2 = layers.Conv2DTranspose(32, 3, activation='relu')(h2)
h2 = layers.UpSampling2D(3)(h2)
h2 = layers.Conv2DTranspose(16, 3, activation='relu')(h2)
decode_output = layers.Conv2DTranspose(1, 3, activation='relu')(h2)
decode_model = tf.keras.Model(inputs=decode_input,
outputs=decode_output,
name='decoder')
decode_model.summary()
autoencoder_input = tf.keras.Input(shape=(28, 28, 1), name='img')
h3 = encode_model(autoencoder_input)
autoencoder_output = decode_model(h3)