Last active
March 13, 2021 13:58
-
-
Save Abhishek-Shaw-Kolkata/13053763328864156f7d18a55f0e268b to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import tensorflow as tf | |
from tensorflow import keras | |
def get_CheXNet_model(HEIGHT,WIDTH,N_CHANNELS): | |
base_model = keras.applications.DenseNet121( | |
weights=None, | |
include_top=False, | |
input_shape=(HEIGHT,WIDTH,N_CHANNELS), pooling="avg" | |
) | |
predictions = keras.layers.Dense(14, activation='sigmoid', name='predictions')(base_model.output) | |
base_model = keras.Model(inputs=base_model.input, outputs=predictions,name='CheXNet') | |
base_model.load_weights("brucechou1983_CheXNet_Keras_0.3.0_weights.h5") | |
base_model.layers.pop() | |
#base_model.trainable = False | |
return base_model | |
tf.random.set_seed(100) # Set global seed | |
keras.backend.clear_session() # For easy reset of notebook state. | |
base_model = get_CheXNet_model(IMG_HEIGHT,IMG_WIDTH,N_CHANNELS) | |
x = Dense(1024, activation=LeakyReLU(),kernel_initializer='he_normal', kernel_regularizer=regularizers.l2(0.0001))(base_model.output) | |
x = Dropout(0.2)(x) | |
x = Dense(512, activation=LeakyReLU(),kernel_initializer='he_normal', kernel_regularizer=regularizers.l2(0.0001))(x) | |
x = Dropout(0.2)(x) | |
x = Dense(256, activation=LeakyReLU(), kernel_initializer='he_normal',kernel_regularizer=regularizers.l2(0.0001))(x) | |
x = Dropout(0.2)(x) | |
x = Dense(128, activation=LeakyReLU(), kernel_initializer='he_normal',kernel_regularizer=regularizers.l2(0.0001))(x) | |
x = Dropout(0.2)(x) | |
x = Dense(64, activation=LeakyReLU(), kernel_initializer='he_normal',kernel_regularizer=regularizers.l2(0.0001))(x) | |
x = Dropout(0.2)(x) | |
x = Dense(32, activation=LeakyReLU(),kernel_initializer='he_normal', kernel_regularizer=regularizers.l2(0.0001))(x) | |
x = Dropout(0.2)(x) | |
predictions = Dense(2, activation='softmax',name='Final')(x) | |
model = keras.models.Model(inputs=base_model.input, outputs=predictions) | |
model.compile(optimizer=tf.keras.optimizers.Adam(lr=0.0001), | |
loss='categorical_crossentropy', | |
metrics=[keras.metrics.Recall()]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment