Simply converts an integer to a one-hot vector of the same size as out_axis """ return ng.one_hot(x, axis=out_axis) # parse the command line arguments parser = NeonArgparser(__doc__) parser.add_argument('--use_embedding', default=False, dest='use_embedding', action='store_true', help='If given, embedding layer is used as the first layer') parser.add_argument('--seq_len', type=int, help="Number of time points in each input sequence", default=32) parser.add_argument('--recurrent_units', type=int, help="Number of recurrent units in the network", default=256) parser.set_defaults(num_iterations=20000) args = parser.parse_args() use_embedding = args.use_embedding recurrent_units = args.recurrent_units batch_size = args.batch_size seq_len = args.seq_len num_iterations = args.num_iterations # Ratio of the text to use for training train_ratio = 0.95 # Define initialization method of neurons in the network init_uni = UniformInit(-0.1, 0.1) # Create the object that includes the sample text shakes = Shakespeare(train_split=train_ratio)
import neon as ng import neon.transformers as ngt from contextlib import closing from neon.frontend import NeonArgparser, ArrayIterator from neon.frontend import XavierInit, UniformInit from neon.frontend import Affine, Convolution, Pooling, Sequential from neon.frontend import Rectlin, Softmax, GradientDescentMomentum from neon.frontend import ax from neon.frontend import make_bound_computation, make_default_callbacks, loop_train # noqa np.seterr(all='raise') parser = NeonArgparser(description=__doc__) # Default batch_size for convnet-googlenet is 128. parser.set_defaults(batch_size=128, num_iterations=100) args = parser.parse_args() # Setup data provider image_size = 224 X_train = np.random.uniform(-1, 1, (args.batch_size, 3, image_size, image_size)) y_train = np.ones(shape=(args.batch_size), dtype=np.int32) train_data = { 'image': { 'data': X_train, 'axes': ('N', 'C', 'H', 'W') }, 'label': { 'data': y_train, 'axes': ('N', )
# parse the command line arguments parser = NeonArgparser(__doc__) parser.add_argument('--predict_seq', default=False, dest='predict_seq', action='store_true', help='If given, seq_len future timepoints are predicted') parser.add_argument('--look_ahead', type=int, help="Number of time steps to start predicting from", default=1) parser.add_argument('--seq_len', type=int, help="Number of time points in each input sequence", default=32) parser.set_defaults() args = parser.parse_args() # Plot the inference / generation results do_plots = True try: imp.find_module('matplotlib') except ImportError: do_plots = False # Feature dimension of the input (for Lissajous curve, this is 2) feature_dim = 2 # Output feature dimension (for Lissajous curve, this is 2) output_dim = 2 # Number of recurrent units in the network recurrent_units = 32