y_train,
x_test=x_test,
y_test=y_test,
epochs=epochs,
batch_size=64,
verbose=1,
patience=patience)
t_used = timeit.default_timer() - t_start
print('\nTime used for training CNN: {}'.format(t_used))
# save cNN
# cnn.model.save(os.path.join(savepath,f_name+'.h5'))
# cnn.save(savepath,f_name)
cnn.model.save_weights(os.path.join(savepath, f_name + '.h5'))
# select some gradients to evaluate and compare
logLik = lambda x: loglik(cnn.model(x))
import timeit
t_used = np.zeros(2)
import matplotlib.pyplot as plt
fig, axes = plt.subplots(nrows=1,
ncols=2,
sharex=True,
sharey=True,
figsize=(12, 6),
facecolor='white')
plt.ion()
n_dif = 100
dif = np.zeros((n_dif, 2))
loaded = np.load(file=os.path.join(
folder, algs[alg_no] + '_ensbl' + str(ensbl_sz) + '_training_XimgY' +
'.npz'))
'latent': tf.keras.layers.PReLU(),
'output': 'linear'
}
latent_dim = 128
droprate = .5
optimizer = tf.keras.optimizers.Adam(learning_rate=0.001)
cnn = CNN(x_train.shape[1:],
y_train.shape[1],
num_filters=num_filters,
latent_dim=latent_dim,
droprate=droprate,
activations=activations,
optimizer=optimizer)
f_name = 'cnn_' + algs[alg_no] + str(ensbl_sz)
try:
cnn.model = load_model(os.path.join(folder, f_name + '.h5'),
custom_objects={'loss': None})
# cnn.model.load_weights(os.path.join(folder,f_name+'.h5'))
print(f_name + ' has been loaded!')
except Exception as err:
print(err)
print('Train CNN...\n')
epochs = 200
patience = 0
import timeit
t_start = timeit.default_timer()
cnn.train(x_train,
y_train,
x_test=x_test,
y_test=y_test,
epochs=epochs,
batch_size=64,
'output': 'linear'
}
latent_dim = 128
droprate = .25
optimizer = tf.keras.optimizers.Adam(learning_rate=0.001)
cnn = CNN(x_train,
y_train,
num_filters=num_filters,
x_test=x_test,
y_test=y_test,
latent_dim=latent_dim,
activations=activations,
droprate=droprate,
optimizer=optimizer)
try:
cnn.model = load_model(os.path.join(folder, 'cnn_' + algs[alg_no] + '.h5'))
print('cnn_' + algs[alg_no] + '.h5' + ' has been loaded!')
except Exception as err:
print(err)
print('Train CNN...\n')
epochs = 100
import timeit
t_start = timeit.default_timer()
cnn.train(epochs, batch_size=64, verbose=1)
t_used = timeit.default_timer() - t_start
print('\nTime used for training CNN: {}'.format(t_used))
# save CNN
# cnn.model.save('./result/cnn_model.h5')
cnn.save(folder, 'cnn_' + algs[alg_no])
# how to laod model
# from tensorflow.keras.models import load_model