def extract_lstm(self,
input_name,
state_name,
output_name,
scope_id,
steps=-1,
scope_name="basic_lstm_cell"):
self.scopes[scope_id] = scope_name
self.scopes[scope_id + 1] = "kernel"
kernel_name = self.generate_name(self.scopes, scope_id + 2)
kernel = self.get_tensor(kernel_name)
self.scopes[scope_id + 1] = "bias"
bias_name = self.generate_name(self.scopes, scope_id + 2)
bias = self.get_tensor(bias_name)
layer = caffe_net.LayerParameter(name=output_name,
type='LSTM',
bottom=[input_name, state_name],
top=[output_name])
num_output_4 = len(kernel[0])
if (bias is not None):
if (len(bias) != num_output_4):
print("[ERROR] extract_lstm failed")
exit(0)
num_output = num_output_4 // 4
layer.lstm_param(num_output, steps)
layer.add_data(kernel.transpose([1, 0]), bias)
self.caffe_model.add_layer(layer)
self.data_dict[output_name], self.data_dict[
state_name] = Operators.lstm(self.data_dict[input_name],
self.data_dict[state_name], kernel,
bias, output_name, state_name)
return output_name
def extract_lstm(self,
input_name,
state_name,
output_name,
scope_id,
steps=-1,
scope_name="basic_lstm_cell",
use_proj=False,
zoneout_cell=0,
zoneout_output=0):
if (isinstance(scope_name, str)):
scope_name = [scope_name]
kernels = []
biases = []
projections = []
projection_biases = []
for i in range(len(scope_name)):
kernel, bias = self.get_weights(scope_id,
[scope_name[i], "kernel", "bias"])
projection_size = 0
projection = None
if (use_proj):
self.scopes[scope_id] = scope_name[i]
projection, projection_bias = self.get_weights(
scope_id + 1, ["projection", "kernel", "bias"])
projection_size = projection.shape[0]
num_output_4 = len(kernel[0])
if (bias is not None):
if (len(bias) != num_output_4):
print("[ERROR] extract_lstm failed")
exit(0)
if (use_proj):
num_output = projection.shape[1]
else:
num_output = num_output_4 // 4
kernels.append(kernel.transpose([1, 0]))
if (bias is None):
bias = np.zeros([num_output_4 // 2])
biases.append(bias)
if (use_proj):
projections.append(projection.transpose([1, 0]))
if (projection_bias is not None):
projection_bias = np.zeros(num_output)
projection_biases.append(projection_bias)
else:
projections.append(None)
projection_biases.append(None)
bottom = [input_name]
if (state_name is not None):
bottom.append(state_name)
layer = caffe_net.LayerParameter(name=output_name,
type='LSTM',
bottom=bottom,
top=[output_name])
layer.lstm_param(num_output, steps, projection_size, zoneout_cell,
zoneout_output)
if (use_proj):
layer.add_data(np.concatenate(kernels, axis=0),
np.concatenate(biases, axis=0),
np.concatenate(projections, axis=0),
np.concatenate(projection_biases, axis=0))
else:
layer.add_data(np.concatenate(kernels, axis=0),
np.concatenate(biases, axis=0))
self.caffe_model.add_layer(layer)
if (len(scope_name) == 1):
self.data_dict[
output_name], self.data_dict[state_name] = Operators.lstm(
self.data_dict[input_name], self.data_dict[state_name],
kernels[0], biases[0], projections[0],
projection_biases[0], zoneout_cell, zoneout_output,
output_name, state_name)
elif (len(scope_name) == 2):
self.data_dict[output_name] = Operators.bi_lstm(
self.data_dict[input_name], kernels, biases, projections,
projection_biases, zoneout_cell, zoneout_output, output_name)
return output_name
