def eight_class():
neural_net = ConvNet([ConvLayer(32, (128, 4), weight_scale=0.044, padding_mode=False),
ActivationLayer('leakyReLU'),
MaxPoolingLayerCUDA((1, 4)),
ConvLayer(32, (32, 4), weight_scale=0.088, padding_mode=False),
ActivationLayer('leakyReLU'),
MaxPoolingLayerCUDA((1, 2)),
ConvLayer(32, (32, 4), weight_scale=0.088, padding_mode=False),
ActivationLayer('leakyReLU'),
GlobalPoolingLayer(),
FullyConnectedLayer(32, weight_scale=0.125),
ActivationLayer('leakyReLU'),
FullyConnectedLayer(32, weight_scale=0.125),
ActivationLayer('leakyReLU'),
FullyConnectedLayer(8, weight_scale=0.17),
SoftmaxLayer()],
DataProvider(num_genres=8))
neural_net.init_params_from_file(conv_only=True)
time1 = time.time()
neural_net.train(learning_rate=0.005, num_iters=80, lrate_schedule=True)
time2 = time.time()
print('Time taken: %.1fs' % (time2 - time1))
print "\nRESULTS:\n"
for result in neural_net.results:
print result
for val in neural_net.results[result]:
print val
neural_net.serialise_params()
MaxPoolingLayerCUDA((1, 2)),
ConvLayer(32, (32, 4), weight_scale=0.088, padding_mode=False),
ActivationLayer('leakyReLU'),
GlobalPoolingLayer(),
FullyConnectedLayer(32, weight_scale=0.125),
ActivationLayer('leakyReLU'),
FullyConnectedLayer(32, weight_scale=0.125),
ActivationLayer('leakyReLU'),
FullyConnectedLayer(6, weight_scale=0.17),
SoftmaxLayer()],
DataProvider(num_genres=6))
neural_net.setup_layers((128, 599), (6, ))
neural_net.init_params_from_file()
genres = ['classical', 'metal', 'blues', 'disco', 'hiphop', 'reggae']
for genre in genres:
for layer_id in range(3):
activations_for_test_data = neural_net.test_data_activations_for_conv_layer(
layer_id + 1, genre)
for result in activations_for_test_data:
for filter_idx in range(result['filter_activations'].shape[0]):
x = np.arange(0, result['filter_activations'].shape[1], 1)
y = result['filter_activations'][filter_idx]
dir_path = './activations/6genres/conv_layer' + str(layer_id + 1) + '/filter' +\
str(filter_idx + 1)
