Created
May 31, 2019 08:00
-
-
Save saurabhpal97/df345d3ebba15f4b64903eb1eddaaaf3 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
from keras.models import Sequential | |
from keras.layers import Input,Conv2D,BatchNormalization,MaxPooling2D,Dropout,Activation,Flatten | |
from keras import regularizers | |
from keras import models | |
from keras.callbacks import ModelCheckpoint | |
num_classes = 10 | |
weight_decay = 1e-4 | |
img_input = Input(shape=(32,32,3)) | |
x = Conv2D(32, (3,3), padding='same', input_shape=x_train.shape[1:])(img_input) | |
x = SqueezeExcite(x,name='se1') | |
x = Activation('elu')(x) | |
x = BatchNormalization()(x) | |
x = Conv2D(32, (3,3), padding='same')(x) | |
x = SqueezeExcite(x,name='se2') | |
x = Activation('elu')(x) | |
x = BatchNormalization()(x) | |
x = MaxPooling2D(pool_size=(2,2))(x) | |
x = Dropout(0.2)(x) | |
x = Conv2D(64, (3,3), padding='same')(x) | |
x = SqueezeExcite(x,name='se3') | |
x = Activation('elu')(x) | |
x = BatchNormalization()(x) | |
x = Conv2D(64, (3,3), padding='same')(x) | |
x = SqueezeExcite(x,name='se4') | |
x = Activation('elu')(x) | |
x = BatchNormalization()(x) | |
x = MaxPooling2D(pool_size=(2,2))(x) | |
x = Dropout(0.3)(x) | |
x = Conv2D(128, (3,3), padding='same')(x) | |
x = SqueezeExcite(x,name='se5') | |
x = Activation('elu')(x) | |
x = BatchNormalization()(x) | |
x = Conv2D(128, (3,3), padding='same')(x) | |
x = SqueezeExcite(x,name='se6') | |
x = Activation('elu')(x) | |
x = BatchNormalization()(x) | |
x = MaxPooling2D(pool_size=(2,2))(x) | |
x = Dropout(0.4)(x) | |
x = Flatten()(x) | |
x = Dense(num_classes, activation='softmax')(x) | |
model = models.Model(img_input, x, name='test_model') | |
#define format for saving weight files | |
filepath="weights-improvement-{epoch:02d}-{val_acc:.2f}.hdf5" | |
checkpoint = ModelCheckpoint(filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max') | |
callbacks_list = [checkpoint] | |
model.compile(optimizer='adam',loss='categorical_crossentropy',metrics=['accuracy']) | |
#train the model | |
model.fit(x_train,y_train,validation_data=(x_val,y_val),epochs=150,callbacks=callbacks_list) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment