Mercurial > ift6266
changeset 248:7e6fecabb656
Optimized the call of ConvOp by specifying additional parameters. Specified image shape of the da_conv layer.
| author | humel |
|---|---|
| date | Tue, 16 Mar 2010 14:46:25 -0400 |
| parents | 4d109b648c31 |
| children | 1bf046c0c84a 966272e7f14b |
| files | deep/convolutional_dae/stacked_convolutional_dae.py |
| diffstat | 1 files changed, 19 insertions(+), 9 deletions(-) [+] |
line wrap: on
line diff
--- a/deep/convolutional_dae/stacked_convolutional_dae.py Tue Mar 16 13:16:28 2010 -0400 +++ b/deep/convolutional_dae/stacked_convolutional_dae.py Tue Mar 16 14:46:25 2010 -0400 @@ -14,6 +14,9 @@ from ift6266 import datasets from ift6266.baseline.log_reg.log_reg import LogisticRegression +batch_size = 100 + + class SigmoidalLayer(object): def __init__(self, rng, input, n_in, n_out): @@ -67,7 +70,7 @@ self.tilde_x = theano_rng.binomial( self.x.shape, 1, 1 - corruption_level,dtype=theano.config.floatX) * self.x conv1_out = conv.conv2d(self.tilde_x, self.W, filter_shape=filter_shape, - image_shape=image_shape, border_mode='valid') + image_shape=image_shape, unroll_kern=4,unroll_batch=4, border_mode='valid') self.y = T.tanh(conv1_out + self.b.dimshuffle('x', 0, 'x', 'x')) @@ -75,6 +78,7 @@ da_filter_shape = [ filter_shape[1], filter_shape[0], filter_shape[2],\ filter_shape[3] ] + da_image_shape = [ image_shape[0], filter_shape[0], image_shape[2]-filter_shape[2]+1, image_shape[3]-filter_shape[3]+1 ] initial_W_prime = numpy.asarray( numpy.random.uniform( \ low = -numpy.sqrt(6./(fan_in+fan_out)), \ high = numpy.sqrt(6./(fan_in+fan_out)), \ @@ -82,7 +86,9 @@ self.W_prime = theano.shared(value = initial_W_prime, name = "W_prime") conv2_out = conv.conv2d(self.y, self.W_prime, - filter_shape = da_filter_shape, + filter_shape = da_filter_shape,\ + image_shape = da_image_shape, \ + unroll_kern=4,unroll_batch=4, \ border_mode='full') self.z = (T.tanh(conv2_out + self.b_prime.dimshuffle('x', 0, 'x', 'x'))+center) / scale @@ -107,7 +113,7 @@ self.b = theano.shared(value=b_values) conv_out = conv.conv2d(input, self.W, - filter_shape=filter_shape, image_shape=image_shape) + filter_shape=filter_shape, image_shape=image_shape, unroll_kern=4,unroll_batch=4) fan_in = numpy.prod(filter_shape[1:]) @@ -214,12 +220,11 @@ def sgd_optimization_mnist( learning_rate=0.1, pretraining_epochs = 1, \ pretrain_lr = 0.1, training_epochs = 1000, \ - kernels = [ [2,5,5] , [2,3,3] ], mlp_layers=[500], \ - corruption_levels = [ 0.2, 0.2, 0.2], \ + kernels = [ [4,5,5] , [4,3,3] ], mlp_layers=[500], \ + corruption_levels = [ 0.2, 0.2, 0.2], batch_size = batch_size, \ max_pool_layers = [ [2,2] , [2,2] ], \ dataset=datasets.nist_digits): - batch_size = 100 # size of the minibatch # allocate symbolic variables for the data index = T.lscalar() # index to a [mini]batch @@ -231,15 +236,20 @@ rng = numpy.random.RandomState(1234) conv_layers=[] - init_layer = [ [ kernels[0][0],1,kernels[0][1],kernels[0][2] ], None, max_pool_layers[0] ] + init_layer = [ [ kernels[0][0],1,kernels[0][1],kernels[0][2] ],\ + [ batch_size , 1, 32, 32 ], + max_pool_layers[0] ] conv_layers.append(init_layer) + conv_n_out = (32-kernels[0][2]+1)/max_pool_layers[0][0] for i in range(1,len(kernels)): - layer = [ [ kernels[i][0],kernels[i-1][0],kernels[i][1],kernels[i][2] ], None, max_pool_layers[i] ] + layer = [ [ kernels[i][0],kernels[i-1][0],kernels[i][1],kernels[i][2] ],\ + [ batch_size, kernels[i-1][0], conv_n_out,conv_n_out ], + max_pool_layers[i] ] conv_layers.append(layer) conv_n_out = (conv_n_out - kernels[i][2]+1)/max_pool_layers[i][0] - + print layer [1] network = SdA(input = layer0_input, n_ins_mlp = kernels[-1][0]*conv_n_out**2, conv_hidden_layers_sizes = conv_layers, mlp_hidden_layers_sizes = mlp_layers,