def test(self, input_matrix, teacher_matrix):
"""Function to test the network
@param input_matrix -- matrix consisting of input
data to the network.
@param teacher_matrix -- matrix consisting of labels
of input data .
"""
number_of_pictures = input_matrix.shape[-1]
mse = 0
squared_errors = cp.dev_matrix_cmf(self.neuron_layer[-1].deltas.h,
self.neuron_layer[-1].deltas.w)
for batch in xrange(number_of_pictures/self.batch_size):
index_begin = self.batch_size * batch
index_end = index_begin + self.batch_size
self.neuron_layer[0].activations = cp.push( input_matrix[:,
index_begin:index_end].astype('float32').copy('F'))
teachbatch = cp.push(teacher_matrix[:,
index_begin:index_end].astype('float32').copy('F'))
for i in xrange(self.number_of_layers):
self.weight_layer[i].forward()
cp.apply_binary_functor(squared_errors, self.neuron_layer[-1].deltas,
cp.binary_functor.COPY)
cp.apply_scalar_functor(squared_errors, cp.scalar_functor.SQUARE)
mse += cp.sum(squared_errors)
teachbatch.dealloc()
print "MSE: ", (mse/number_of_pictures)
squared_errors.dealloc()
def gray_test(ni):
src = cp.push(to_cmuc(np.tile(ni,(1,4))))
dst = cp.dev_matrix_cmf(src.h,src.w)
cp.fill(dst,0)
cp.image_move(dst,src,128,128,1,-10,-4)
res = cp.pull(dst)
#set_trace()
plt.matshow(res[0:128**2,0].reshape(128,128))
plt.colorbar()
plt.show()
def gray_test(ni):
src = cp.push(to_cmuc(np.tile(ni, (1, 4))))
dst = cp.dev_matrix_cmf(src.h, src.w)
cp.fill(dst, 0)
cp.image_move(dst, src, 128, 128, 1, -10, -4)
res = cp.pull(dst)
#set_trace()
plt.matshow(res[0:128**2, 0].reshape(128, 128))
plt.colorbar()
plt.show()
def color_test(ni):
ts = 128
src = cp.push(to_cmuc(np.tile(ni,(1,4))))
dst = cp.dev_matrix_cmf(ts**2*3,src.w)
cp.fill(dst,0)
cp.image_move(dst,src,128,ts,4,-10,-4)
res = cp.pull(dst)
plt.matshow(res[0:ts**2,0].reshape(ts,ts), cmap = plt.cm.bone_r)
plt.matshow(res[ts**2:2*ts**2,0].reshape(ts,ts), cmap = plt.cm.bone_r)
plt.matshow(res[2*ts**2:3*ts**2,0].reshape(ts,ts), cmap = plt.cm.bone_r)
plt.show()
def _tmp(dim1, dim2, value):
"""Function to create a filled matrix.
This demonstrates how CUV can be extended using python.
@param dim1 -- number of rows.
@param dim2 -- number of columns.
"""
mat = cp.dev_matrix_cmf(dim1, dim2)
cp.fill(mat, value)
return mat
def _tmp(dim1, dim2, value):
"""Function to create a filled matrix.
This demonstrates how CUV can be extended using python.
@param dim1 -- number of rows.
@param dim2 -- number of columns.
"""
mat = cp.dev_matrix_cmf(dim1, dim2)
cp.fill(mat, value)
return mat
def color_test(ni):
ts = 128
src = cp.push(to_cmuc(np.tile(ni, (1, 4))))
dst = cp.dev_matrix_cmf(ts**2 * 3, src.w)
cp.fill(dst, 0)
cp.image_move(dst, src, 128, ts, 4, -10, -4)
res = cp.pull(dst)
plt.matshow(res[0:ts**2, 0].reshape(ts, ts), cmap=plt.cm.bone_r)
plt.matshow(res[ts**2:2 * ts**2, 0].reshape(ts, ts), cmap=plt.cm.bone_r)
plt.matshow(res[2 * ts**2:3 * ts**2, 0].reshape(ts, ts),
cmap=plt.cm.bone_r)
plt.show()
def backward(self):
"""Backward pass, calculates the deltas of lower layer
and later updates the weights."""
cp.prod(self.source.deltas, self.weight, self.target.deltas,
't', 'n')
h = cp.dev_matrix_cmf(self.source.activations.h,
self.source.activations.w)
cp.apply_binary_functor(h, self.source.activations,
cp.binary_functor.COPY)
self.source.d_nonlinearity(h)
cp.apply_binary_functor(self.source.deltas, h,
cp.binary_functor.MULT)
h.dealloc()
self.weight_update()
def train(self, input_matrix, teacher_matrix, number_of_epochs):
"""Function to train the network
@param input_matrix -- matrix consisting of input data
to the network.
@param teacher_matrix -- matrix consisting of labels
of input data.
@param number_of_epochs -- number of rounds the network
is to be trained.
"""
number_of_pictures = input_matrix.shape[-1]
squared_errors = cp.dev_matrix_cmf(self.neuron_layer[-1].deltas.h,
self.neuron_layer[-1].deltas.w)
def weight_update(self, learnrate=0.01, decay=0.0):
"""Updates the weights and the bias
using source activations and target deltas.
@param learnrate how strongly the gradient influences the weights
@param decay large values result in a regularization with
to the squared weight value"""
batch_size=self.source.activations.w
h = cp.dev_matrix_cmf(self.weight.h, self.weight.w)
cp.prod(h, self.target.deltas, self.source.activations, 'n', 't')
cp.learn_step_weight_decay(self.weight, h, learnrate/batch_size, decay)
h.dealloc()
h = cp.get_filled_matrix(self.target.activations.h, 1, 0)
cp.reduce_to_col(h.vec, self.target.deltas)
cp.learn_step_weight_decay(self.bias, h, learnrate/batch_size, decay)
h.dealloc()
