def write_solver_file(solver_file, train_model, test_models, type, base_lr, momentum, weight_decay,
lr_policy, gamma, power, random_seed, max_iter, clip_gradients, snapshot_prefix,display=0):
'''Writes a solver prototxt file with parameters set to the
corresponding argument values. In particular, the train_net
parameter is set to train_model, and a test_net parameter is
added for each of test_models, which should be a list.'''
param = SolverParameter()
param.train_net = train_model
for test_model in test_models:
param.test_net.append(test_model)
param.test_iter.append(0) #don't test automatically
param.test_interval = max_iter
param.type = type
param.base_lr = base_lr
param.momentum = momentum
param.weight_decay = weight_decay
param.lr_policy = lr_policy
param.gamma = gamma
param.power = power
param.display = display #don't print solver iterations unless requested
param.random_seed = random_seed
param.max_iter = max_iter
if clip_gradients > 0:
param.clip_gradients = clip_gradients
param.snapshot_prefix = snapshot_prefix
print "WRITING",solver_file
with open(solver_file,'w') as f:
f.write(str(param))
def write_solver_file(solver_file, train_model, test_models, type, base_lr,
momentum, weight_decay, lr_policy, gamma, power,
random_seed, max_iter, clip_gradients, snapshot_prefix):
'''Writes a solver prototxt file with parameters set to the
corresponding argument values. In particular, the train_net
parameter is set to train_model, and a test_net parameter is
added for each of test_models, which should be a list.'''
param = SolverParameter()
param.train_net = train_model
for test_model in test_models:
param.test_net.append(test_model)
param.test_iter.append(0) #don't test automatically
param.test_interval = max_iter
param.type = type
param.base_lr = base_lr
param.momentum = momentum
param.weight_decay = weight_decay
param.lr_policy = lr_policy
param.gamma = gamma
param.power = power
param.display = 0 #don't print solver iterations
param.random_seed = random_seed
param.max_iter = max_iter
if clip_gradients > 0:
param.clip_gradients = clip_gradients
param.snapshot_prefix = snapshot_prefix
print "WRITING", solver_file
with open(solver_file, 'w') as f:
f.write(str(param))
def init_solver(self):
""" Helper method to initialize the solver. """
solver_param = SolverParameter()
solver_param.snapshot_prefix = self._hyperparams['weights_file_prefix']
solver_param.display = 0 # Don't display anything.
solver_param.base_lr = self._hyperparams['lr']
solver_param.lr_policy = self._hyperparams['lr_policy']
solver_param.momentum = self._hyperparams['momentum']
solver_param.weight_decay = self._hyperparams['weight_decay']
solver_param.type = self._hyperparams['solver_type']
solver_param.random_seed = self._hyperparams['random_seed']
# Pass in net parameter either by filename or protostring.
if isinstance(self._hyperparams['network_model'], basestring):
self.solver = caffe.get_solver(self._hyperparams['network_model'])
else:
network_arch_params = self._hyperparams['network_arch_params']
network_arch_params['dim_input'] = self._dO
network_arch_params['dim_output'] = self._dU
network_arch_params['batch_size'] = self.batch_size
network_arch_params['phase'] = TRAIN
solver_param.train_net_param.CopyFrom(
self._hyperparams['network_model'](**network_arch_params)
)
# For running forward in python.
network_arch_params['batch_size'] = 1
network_arch_params['phase'] = TEST
solver_param.test_net_param.add().CopyFrom(
self._hyperparams['network_model'](**network_arch_params)
)
# For running forward on the robot.
network_arch_params['batch_size'] = 1
network_arch_params['phase'] = 'deploy'
solver_param.test_net_param.add().CopyFrom(
self._hyperparams['network_model'](**network_arch_params)
)
# These are required by Caffe to be set, but not used.
solver_param.test_iter.append(1)
solver_param.test_iter.append(1)
solver_param.test_interval = 1000000
f = tempfile.NamedTemporaryFile(mode='w+', delete=False)
f.write(MessageToString(solver_param))
f.close()
self.solver = caffe.get_solver(f.name)
def init_solver(self):
""" Helper method to initialize the solver. """
solver_param = SolverParameter()
solver_param.snapshot_prefix = self._hyperparams['weights_file_prefix']
solver_param.display = 0 # Don't display anything.
solver_param.base_lr = self._hyperparams['lr']
solver_param.lr_policy = self._hyperparams['lr_policy']
solver_param.momentum = self._hyperparams['momentum']
solver_param.weight_decay = self._hyperparams['weight_decay']
solver_param.type = self._hyperparams['solver_type']
solver_param.random_seed = self._hyperparams['random_seed']
# Pass in net parameter either by filename or protostring.
if isinstance(self._hyperparams['network_model'], basestring):
self.solver = caffe.get_solver(self._hyperparams['network_model'])
else:
network_arch_params = self._hyperparams['network_arch_params']
network_arch_params['dim_input'] = self._dO
network_arch_params['dim_output'] = self._dU
network_arch_params['batch_size'] = self.batch_size
network_arch_params['phase'] = TRAIN
solver_param.train_net_param.CopyFrom(
self._hyperparams['network_model'](**network_arch_params)
)
# For running forward in python.
network_arch_params['batch_size'] = 1
network_arch_params['phase'] = TEST
solver_param.test_net_param.add().CopyFrom(
self._hyperparams['network_model'](**network_arch_params)
)
# For running forward on the robot.
network_arch_params['batch_size'] = 1
network_arch_params['phase'] = 'deploy'
solver_param.test_net_param.add().CopyFrom(
self._hyperparams['network_model'](**network_arch_params)
)
# These are required by Caffe to be set, but not used.
solver_param.test_iter.append(1)
solver_param.test_iter.append(1)
solver_param.test_interval = 1000000
f = tempfile.NamedTemporaryFile(mode='w+', delete=False)
f.write(MessageToString(solver_param))
f.close()
self.solver = caffe.get_solver(f.name)
def _init_solver(self): """ Helper method to initialize the solver. """ solver_param = SolverParameter() solver_param.display = 0 # Don't display anything. solver_param.base_lr = self._hyperparams['lr'] solver_param.lr_policy = self._hyperparams['lr_policy'] solver_param.momentum = self._hyperparams['momentum'] solver_param.weight_decay = self._hyperparams['weight_decay'] solver_param.type = self._hyperparams['solver_type'] solver_param.random_seed = self._hyperparams['random_seed'] # Pass in net parameter by protostring (could add option to input prototxt file). network_arch_params = self._hyperparams['network_arch_params'] network_arch_params['dim_input'] = self._dO network_arch_params['demo_batch_size'] = self._hyperparams['demo_batch_size'] network_arch_params['sample_batch_size'] = self._hyperparams['sample_batch_size'] network_arch_params['T'] = self._T network_arch_params['phase'] = TRAIN solver_param.train_net_param.CopyFrom( self._hyperparams['network_model'](**network_arch_params) ) # For running forward in python. network_arch_params['phase'] = TEST solver_param.test_net_param.add().CopyFrom( self._hyperparams['network_model'](**network_arch_params) ) network_arch_params['phase'] = 'forward_feat' solver_param.test_net_param.add().CopyFrom( self._hyperparams['network_model'](**network_arch_params) ) # These are required by Caffe to be set, but not used. solver_param.test_iter.append(1) solver_param.test_iter.append(1) solver_param.test_interval = 1000000 f = tempfile.NamedTemporaryFile(mode='w+', delete=False) f.write(MessageToString(solver_param)) f.close() self.solver = caffe.get_solver(f.name)