def save(self,filename,start_layer = 0,max_layer_num = -1,withfinal=True):
nnet_dict = {}
if max_layer_num == -1:
max_layer_num = self.n_layers
for i in range(start_layer, max_layer_num):
dict_a = str(i) + ' W'
if i == 0:
nnet_dict[dict_a] = _array2string((1.0 - self.input_dropout_factor) * (
self.layers[i].params[0].get_value()))
else:
nnet_dict[dict_a] = _array2string((1.0 - self.dropout_factor[i - 1])* (
self.layers[i].params[0].get_value()))
dict_a = str(i) + ' b'
nnet_dict[dict_a] = _array2string(self.layers[i].params[1].get_value())
if withfinal:
dict_a = 'logreg W'
nnet_dict[dict_a] = _array2string((1.0 - self.dropout_factor[-1])* (
self.logLayer.params[0].get_value()))
dict_a = 'logreg b'
nnet_dict[dict_a] = _array2string(self.logLayer.params[1].get_value())
with open(filename, 'wb') as fp:
json.dump(nnet_dict, fp, indent=2, sort_keys = True)
fp.flush()
def save_cnn2dict(self):
n_layers = self.conv_layer_num
cnn_dict = {}
for i in xrange(n_layers):
conv_layer = self.conv_layers[i]
filter_shape = conv_layer.filter_shape
for next_X in xrange(filter_shape[0]):
for this_X in xrange(filter_shape[1]):
dict_a = 'W ' + str(i) + ' ' + str(next_X) + ' ' + str(this_X)
cnn_dict[dict_a] = _array2string((conv_layer.W.get_value())[next_X, this_X])
dict_a = 'b ' + str(i)
cnn_dict[dict_a] = _array2string(conv_layer.b.get_value())
return cnn_dict;
def save_cnn2dict(self):
n_layers = self.conv_layer_num
cnn_dict = {}
for i in xrange(n_layers):
conv_layer = self.conv_layers[i]
filter_shape = conv_layer.filter_shape
for X_0 in xrange(filter_shape[0]):
for X_1 in xrange(filter_shape[1]):
for X_2 in xrange(filter_shape[2]):
dict_a = 'W ' + str(i) + ' ' + str(X_0) + ' ' + str(X_1) + ' ' + str(X_2)
cnn_dict[dict_a] = _array2string((conv_layer.W.get_value())[X_0, X_1, X_2])
dict_a = 'b ' + str(i)
cnn_dict[dict_a] = _array2string(conv_layer.b.get_value())
return cnn_dict;
def save_mlp2dict(self,withfinal=True,max_layer_num=-1):
if max_layer_num == -1:
max_layer_num = self.hidden_layer_num
mlp_dict = {}
for i in range(max_layer_num):
dict_a = str(i) +' W'
mlp_dict[dict_a] = _array2string(self.mlp_layers[i].params[0].get_value())
dict_a = str(i) + ' b'
mlp_dict[dict_a] = _array2string(self.mlp_layers[i].params[1].get_value())
if withfinal:
dict_a = 'logreg W'
mlp_dict[dict_a] = _array2string(self.logLayer.params[0].get_value())
dict_a = 'logreg b'
mlp_dict[dict_a] = _array2string(self.logLayer.params[1].get_value())
return mlp_dict
def save_mlp2dict(self,withfinal=True,max_layer_num=-1):
if max_layer_num == -1:
max_layer_num = self.hidden_layer_num
mlp_dict = {}
for i in range(max_layer_num):
dict_a = str(i) +' W'
mlp_dict[dict_a] = _array2string(self.mlp_layers[i].params[0].get_value())
dict_a = str(i) + ' b'
mlp_dict[dict_a] = _array2string(self.mlp_layers[i].params[1].get_value())
if withfinal:
dict_a = 'logreg W'
mlp_dict[dict_a] = _array2string(self.logLayer.params[0].get_value())
dict_a = 'logreg b'
mlp_dict[dict_a] = _array2string(self.logLayer.params[1].get_value())
return mlp_dict
def save_cnn2dict(self):
n_layers = self.conv_layer_num
cnn_dict = {}
for i in xrange(n_layers):
conv_layer = self.conv_layers[i]
filter_shape = conv_layer.filter_shape
for X_0 in xrange(filter_shape[0]):
for X_1 in xrange(filter_shape[1]):
for X_2 in xrange(filter_shape[2]):
dict_a = 'W ' + str(i) + ' ' + str(X_0) + ' ' + str(
X_1) + ' ' + str(X_2)
cnn_dict[dict_a] = _array2string(
(conv_layer.W.get_value())[X_0, X_1, X_2])
dict_a = 'b ' + str(i)
cnn_dict[dict_a] = _array2string(conv_layer.b.get_value())
return cnn_dict
def save_mlp2dict(self,withfinal=True,max_layer_num=-1):
if max_layer_num == -1:
max_layer_num = self.hidden_layer_num
mlp_dict = {}
for i in range(max_layer_num):
dict_a = str(i) +' W'
if i == 0:
mlp_dict[dict_a] = _array2string((1.0 - self.input_dropout_factor) *self.mlp_layers[i].params[0].get_value())
else:
mlp_dict[dict_a] = _array2string((1.0 - self.dropout_factor[i - 1]) * self.mlp_layers[i].params[0].get_value())
dict_a = str(i) + ' b'
mlp_dict[dict_a] = _array2string(self.mlp_layers[i].params[1].get_value())
if withfinal:
dict_a = 'logreg W'
mlp_dict[dict_a] = _array2string((1.0 - self.dropout_factor[-1])*self.logLayer.params[0].get_value())
dict_a = 'logreg b'
mlp_dict[dict_a] = _array2string(self.logLayer.params[1].get_value())
return mlp_dict