description='''Convert gpu pickle pynet model to cpu pickle pynet model''')
parser.add_argument('--gpu_model',
metavar='Path',
required=True,
help='the path to the gpu model pickle file')
parser.add_argument('--cpu_model',
metavar='Path',
required=True,
help='''path to save the cpu model pickle file''')
args = parser.parse_args()
print('loading gpu mlp..')
fin = open(args.gpu_model)
gpu_model = cPickle.load(fin)
mlp = MLP(input_dim=gpu_model.input_dim)
for layer in gpu_model.layers:
layerW = T._shared(np.array(layer.W.get_value(), floatX),
name=layer.W.name,
borrow=False)
layerb = T._shared(np.array(layer.b.get_value(), floatX),
name=layer.b.name,
borrow=False)
mlp_layer = getattr(layers, layer.__class__.__name__)(dim=layer.dim,
name=layer.name,
W=layerW,
b=layerb)
mlp.add_layer(mlp_layer)
print 'mlp layer', mlp_layer.name, mlp_layer.dim
print 'layers', mlp.layers
def mlp():
# build dataset
data = Mnist(preprocessor=None, train_valid_test_ratio=[5, 1, 1])
# build mlp
mlp = MLP(input_dim=data.feature_size())
W1 = GaussianWeight(prev_dim=mlp.input_dim, this_dim=1000)
hidden1 = PRELU(dim=1000,
name='h1_layer',
W=W1(mean=0, std=0.1),
b=None,
dropout_below=None)
mlp.add_layer(hidden1)
W2 = XavierWeight(prev_dim=hidden1.dim, this_dim=data.target_size())
output = Softmax(dim=data.target_size(),
name='output_layer',
W=W2(),
b=None,
dropout_below=None)
mlp.add_layer(output)
# build learning method
learning_method = AdaGrad(learning_rate=0.1, momentum=0.9)
# set the learning rules
learning_rule = LearningRule(max_col_norm=10,
L1_lambda=None,
L2_lambda=None,
training_cost=Cost(type='mse'),
learning_rate_decay_factor=None,
stopping_criteria={
'max_epoch': 300,
'epoch_look_back': 10,
'cost': Cost(type='error'),
'percent_decrease': 0.01
})
# (optional) build the logging object
log = Log(experiment_name='mnist',
description='This is tutorial example',
save_outputs=True,
save_learning_rule=True,
save_model=True,
save_epoch_error=True,
save_to_database={
'name': 'Example.db',
'records': {
'Dataset':
data.__class__.__name__,
'max_col_norm':
learning_rule.max_col_norm,
'Weight_Init_Seed':
mlp.rand_seed,
'Dropout_Below':
str([layer.dropout_below for layer in mlp.layers]),
'Batch_Size':
data.batch_size,
'Layer_Dim':
str([layer.dim for layer in mlp.layers]),
'Layer_Types':
str([layer.__class__.__name__ for layer in mlp.layers]),
'Preprocessor':
data.preprocessor.__class__.__name__,
'Learning_Rate':
learning_method.learning_rate,
'Momentum':
learning_method.momentum,
'Training_Cost':
learning_rule.cost.type,
'Stopping_Cost':
learning_rule.stopping_criteria['cost'].type
}
}) # end log
# put everything into the train object
train_object = TrainObject(model=mlp,
dataset=data,
learning_rule=learning_rule,
learning_method=learning_method,
log=log)
# finally run the code
train_object.run()
