예제 #1
0
 def stream():
     stream = data_io.random_select_stream(*[
         data_io.stream_file('data/train.%02d.pklgz' % i)
         for i in xrange(1, 20)
     ])
     stream = data_io.buffered_sort(stream, key=lambda x: x[1].shape[0], buffer_items=128)
     batched_stream = reader.batch_and_pad(stream, batch_size=16, mean=mean, std=std)
     batched_stream = data_io.buffered_random(batched_stream, buffer_items=4)
     return batched_stream
예제 #2
0
    def validate():
        stream = data_io.stream_file('data/train.%02d.pklgz' % 0)
        stream = data_io.buffered_sort(stream, key=lambda x: x[1].shape[0], buffer_items=128)
        batched_stream = reader.batch_and_pad(stream, batch_size=32, mean=mean, std=std)

        total_cost = 0
        total_frames = 0
        for data, lengths in batched_stream:
            batch_avg_cost = test(data,lengths)
            batch_frames = np.sum(lengths)
            total_cost += batch_avg_cost * batch_frames
            total_frames += batch_frames
        return total_cost / total_frames
예제 #3
0
 def stream():
     stream = data_io.random_select_stream(*[
         data_io.stream_file('data/train.%02d.pklgz' % i)
         for i in xrange(1, 20)
     ])
     stream = data_io.buffered_sort(stream,
                                    key=lambda x: x[1].shape[0],
                                    buffer_items=128)
     batched_stream = reader.batch_and_pad(stream,
                                           batch_size=16,
                                           mean=mean,
                                           std=std)
     batched_stream = data_io.buffered_random(batched_stream,
                                              buffer_items=4)
     return batched_stream
예제 #4
0
    def validate():
        stream = data_io.stream_file('data/train.%02d.pklgz' % 0)
        stream = data_io.buffered_sort(stream,
                                       key=lambda x: x[1].shape[0],
                                       buffer_items=128)
        batched_stream = reader.batch_and_pad(stream,
                                              batch_size=32,
                                              mean=mean,
                                              std=std)

        total_cost = 0
        total_frames = 0
        for data, lengths in batched_stream:
            batch_avg_cost = test(data, lengths)
            batch_frames = np.sum(lengths)
            total_cost += batch_avg_cost * batch_frames
            total_frames += batch_frames
        return total_cost / total_frames