In [5]:

    

import numpy as np
import time
import sys
sys.path.append('../tools/')
import my_io as my_io
import caffe
import os
import pickle
import itertools
from scipy.misc import imresize
import lasagne
from lasagne.layers import cuda_convnet
import theano
import theano.tensor as T

MEAN_FILE = '/media/raid_arr/data/ndsb/augment/testaug_mean.npy'
TRAIN_DB = '/media/raid_arr/data/ndsb/folds/train0_lmdb/'
TEST_DB = '/media/raid_arr/data/ndsb/folds/test0_lmdb/'

N = 20000   # Chunk size


    

In [ ]:

    

def build_model(input_width, input_height, output_dim,
                batch_size=BATCH_SIZE, dimshuffle=True):
    l_in = lasagne.layers.InputLayer(
        shape=(batch_size, 1, input_width, input_height),
    )

    if not dimshuffle:
        l_in = cuda_convnet.bc01_to_c01b(l_in)

    l_conv1 = cuda_convnet.Conv2DCCLayer(
        l_in,
        num_filters=32,
        filter_size=(5, 5),
        nonlinearity=lasagne.nonlinearities.rectify,
        W=lasagne.init.Uniform(),
        dimshuffle=dimshuffle,
    )
    l_pool1 = cuda_convnet.MaxPool2DCCLayer(
        l_conv1,
        ds=(2, 2),
        dimshuffle=dimshuffle,
    )

    l_conv2 = cuda_convnet.Conv2DCCLayer(
        l_pool1,
        num_filters=32,
        filter_size=(5, 5),
        nonlinearity=lasagne.nonlinearities.rectify,
        W=lasagne.init.Uniform(),
        dimshuffle=dimshuffle,
    )
    l_pool2 = cuda_convnet.MaxPool2DCCLayer(
        l_conv2,
        ds=(2, 2),
        dimshuffle=dimshuffle,
    )

    if not dimshuffle:
        l_pool2 = cuda_convnet.c01b_to_bc01(l_pool2)

    l_hidden1 = lasagne.layers.DenseLayer(
        l_pool2,
        num_units=256,
        nonlinearity=lasagne.nonlinearities.rectify,
        W=lasagne.init.Uniform(),
    )

    l_hidden1_dropout = lasagne.layers.DropoutLayer(l_hidden1, p=0.5)


    l_out = lasagne.layers.DenseLayer(
        l_hidden1_dropout,
        num_units=output_dim,
        nonlinearity=lasagne.nonlinearities.softmax,
        W=lasagne.init.Uniform(),
    )

    return l_out