cfg = NetworkConfig(multi_label) cfg.parse_config_dnn(arguments, nnet_spec) cfg.init_data_reading(train_data_spec, valid_data_spec) # parse pre-training options # pre-training files and layer number (how many layers are set to the pre-training parameters) ptr_layer_number = 0; ptr_file = '' if arguments.has_key('ptr_file') and arguments.has_key('ptr_layer_number'): ptr_file = arguments['ptr_file'] ptr_layer_number = int(arguments['ptr_layer_number']) # check working dir to see whether it's resuming training resume_training = False if os.path.exists(wdir + '/nnet.tmp') and os.path.exists(wdir + '/training_state.tmp'): resume_training = True cfg.lrate = _file2lrate(wdir + '/training_state.tmp') log('> ... found nnet.tmp and training_state.tmp, now resume training from epoch ' + str(cfg.lrate.epoch)) numpy_rng = numpy.random.RandomState() theano_rng = RandomStreams(numpy_rng.randint(2 ** 30)) log('> ... building the model') # setup model if cfg.do_dropout: dnn = DNN_Dropout(numpy_rng=numpy_rng, theano_rng = theano_rng, cfg = cfg) else: dnn = DNN(numpy_rng=numpy_rng, theano_rng = theano_rng, cfg = cfg) # initialize model parameters # if not resuming training, initialized from the specified pre-training file # if resuming training, initialized from the tmp model file if (ptr_layer_number > 0) and (resume_training is False):
conv_nnet_spec = arguments['conv_nnet_spec'] nnet_spec = arguments['nnet_spec'] wdir = arguments['wdir'] # parse network configuration from arguments, and initialize data reading cfg = NetworkConfig() cfg.model_type = 'CNN_LACEA' cfg.parse_config_cnn(arguments, '10:' + nnet_spec, conv_nnet_spec) cfg.init_data_reading(train_data_spec, valid_data_spec) # check working dir to see whether it's resuming training resume_training = False if os.path.exists(wdir + '/nnet.tmp_CNN_LACEA') and os.path.exists( wdir + '/training_state.tmp_CNN_LACEA'): resume_training = True cfg.lrate = _file2lrate(wdir + '/training_state.tmp_CNN_LACEA') log('> ... found nnet.tmp_CNN_LACEA and training_state.tmp_CNN_LACEA, now resume training from epoch ' + str(cfg.lrate.epoch)) numpy_rng = numpy.random.RandomState(89677) theano_rng = RandomStreams(numpy_rng.randint(2**30)) log('> ... initializing the model') # construct the cnn architecture cnn = CNN_LACEA(numpy_rng=numpy_rng, theano_rng=theano_rng, cfg=cfg) # load the pre-training networks, if any, for parameter initialization if resume_training: _file2nnet(cnn, filename=wdir + '/nnet.tmp_CNN_LACEA') # get the training, validation and testing function for the model log('> ... getting the finetuning functions') train_fn, valid_fn = cnn.build_finetune_functions(
cfg = NetworkConfig() cfg.parse_config_dnn(arguments, nnet_spec) cfg.init_data_reading(train_data_spec, valid_data_spec) # parse pre-training options # pre-training files and layer number (how many layers are set to the pre-training parameters) ptr_layer_number = 0; ptr_file = '' if arguments.has_key('ptr_file') and arguments.has_key('ptr_layer_number'): ptr_file = arguments['ptr_file'] ptr_layer_number = int(arguments['ptr_layer_number']) # check working dir to see whether it's resuming training resume_training = False if os.path.exists(wdir + '/nnet.tmp') and os.path.exists(wdir + '/training_state.tmp'): resume_training = True cfg.lrate = _file2lrate(wdir + '/training_state.tmp') log('> ... found nnet.tmp and training_state.tmp, now resume training from epoch ' + str(cfg.lrate.epoch)) numpy_rng = numpy.random.RandomState(89677) theano_rng = RandomStreams(numpy_rng.randint(2 ** 30)) log('> ... building the model') # setup model if cfg.do_dropout: dnn = DNN_Dropout(numpy_rng=numpy_rng, theano_rng = theano_rng, cfg = cfg) else: dnn = DNN(numpy_rng=numpy_rng, theano_rng = theano_rng, cfg = cfg) # initialize model parameters # if not resuming training, initialized from the specified pre-training file # if resuming training, initialized from the tmp model file if (ptr_layer_number > 0) and (resume_training is False):
if n > 0: dnn_shared = dnn_array[0]; shared_layers = [m for m in xrange(shared_layers_num)] print shared_layers dnn = DNN_MTL(task_id=n,numpy_rng=numpy_rng, theano_rng = theano_rng, cfg = cfg, dnn_shared = dnn_shared, shared_layers = shared_layers) # get the training, validation and testing function for the model log('> ... getting the finetuning functions for task %d' % (n)) train_fn, valid_fn = dnn.build_finetune_functions((cfg.train_x, cfg.train_y), (cfg.valid_x, cfg.valid_y), batch_size=cfg.batch_size) # add dnn and the functions to the list dnn_array.append(dnn) train_fn_array.append(train_fn); valid_fn_array.append(valid_fn) # check the working dir to decide whether it's resuming training; if yes, load the tmp network files for initialization if os.path.exists(wdir + '/nnet.tmp.task' + str(n)) and os.path.exists(wdir + '/training_state.tmp.task' + str(n)): resume_training = True; resume_tasks.append(n) cfg.lrate = _file2lrate(wdir + '/training_state.tmp.task' + str(n)) log('> ... found nnet.tmp.task%d and training_state.tmp.task%d, now resume task%d training from epoch %d' % (n, n, n, cfg.lrate.epoch)) _file2nnet(dnn.layers, filename = wdir + '/nnet.tmp.task' + str(n)) # pre-training works only if we are NOT resuming training # we assume that we only pre-train the shared layers; thus we only use dnn_array[0] to load the parameters # because the parameters are shared across the tasks ptr_layer_number = 0; ptr_file = '' if arguments.has_key('ptr_file') and arguments.has_key('ptr_layer_number'): ptr_file = arguments['ptr_file']; ptr_layer_number = int(arguments['ptr_layer_number']) if (ptr_layer_number > 0) and (resume_training is False): _file2nnet(dnn_array[0].layers, set_layer_num = ptr_layer_number, filename = ptr_file) log('> ... finetuning the model') train_error_array = [[] for n in xrange(task_number)] active_tasks = [n for n in xrange(task_number)] # the tasks with 0 learning rate are not considered
cfg.parse_config_cnn(arguments, "10:" + nnet_spec, conv_nnet_spec) cfg.init_data_reading(train_data_spec, valid_data_spec) # parse pre-training options # pre-training files and layer number (how many layers are set to the pre-training parameters) ptr_layer_number = 0 ptr_file = "" if arguments.has_key("ptr_file") and arguments.has_key("ptr_layer_number"): ptr_file = arguments["ptr_file"] ptr_layer_number = int(arguments["ptr_layer_number"]) # check working dir to see whether it's resuming training resume_training = False if os.path.exists(wdir + "/nnet.tmp") and os.path.exists(wdir + "/training_state.tmp"): resume_training = True cfg.lrate = _file2lrate(wdir + "/training_state.tmp") log("> ... found nnet.tmp and training_state.tmp, now resume training from epoch " + str(cfg.lrate.epoch)) numpy_rng = numpy.random.RandomState(89677) theano_rng = RandomStreams(numpy_rng.randint(2 ** 30)) log("> ... initializing the model") # construct the cnn architecture cnn = CNN(numpy_rng=numpy_rng, theano_rng=theano_rng, cfg=cfg) # load the pre-training networks, if any, for parameter initialization if (ptr_layer_number > 0) and (resume_training is False): _file2nnet(cnn.layers, set_layer_num=ptr_layer_number, filename=ptr_file) if resume_training: _file2nnet(cnn.layers, filename=wdir + "/nnet.tmp") # get the training, validation and testing function for the model log("> ... getting the finetuning functions")
conv_nnet_spec = arguments['conv_nnet_spec'] nnet_spec = arguments['nnet_spec'] wdir = arguments['wdir'] # parse network configuration from arguments, and initialize data reading cfg = NetworkConfig() cfg.model_type = 'CNN' cfg.parse_config_cnn(arguments, '10:' + nnet_spec, conv_nnet_spec) cfg.init_data_reading(train_data_spec, valid_data_spec) # check working dir to see whether it's resuming training resume_training = False if os.path.exists(wdir + '/nnet.tmp_DENSENET') and os.path.exists( wdir + '/training_state.tmp_DENSENET'): resume_training = True cfg.lrate = _file2lrate(wdir + '/training_state.tmp_DENSENET') log('> ... found nnet.tmp_DENSENET and training_state.tmp_DENSENET, now resume training from epoch ' + str(cfg.lrate.epoch)) numpy_rng = numpy.random.RandomState(89677) theano_rng = RandomStreams(numpy_rng.randint(2**30)) log('> ... initializing the model') # construct the cnn architecture densenet = DENSENET(numpy_rng=numpy_rng, theano_rng=theano_rng, cfg=cfg) # load the pre-training networks, if any, for parameter initialization if resume_training: _file2nnet(densenet, filename=wdir + '/nnet.tmp_DENSENET') # get the training, validation and testing function for the model log('> ... getting the finetuning functions') train_fn, valid_fn = densenet.build_finetune_functions(
def dnn_run(arguments): required_arguments = ['train_data', 'valid_data', 'nnet_spec', 'wdir'] for arg in required_arguments: if arguments.has_key(arg) == False: print "Error: the argument %s has to be specified" % (arg); exit(1) train_data_spec = arguments['train_data'] valid_data_spec = arguments['valid_data'] nnet_spec = arguments['nnet_spec'] wdir = arguments['wdir'] cfg = NetworkConfig() cfg.parse_config_dnn(arguments, nnet_spec) cfg.init_data_reading(train_data_spec, valid_data_spec) # parse pre-training options # pre-training files and layer number (how many layers are set to the pre-training parameters) ptr_layer_number = 0; ptr_file = '' if arguments.has_key('ptr_file') and arguments.has_key('ptr_layer_number'): ptr_file = arguments['ptr_file'] ptr_layer_number = int(arguments['ptr_layer_number']) # check working dir to see whether it's resuming training resume_training = False if os.path.exists(wdir + '/nnet.tmp') and os.path.exists(wdir + '/training_state.tmp'): resume_training = True cfg.lrate = _file2lrate(wdir + '/training_state.tmp') log('> ... found nnet.tmp and training_state.tmp, now resume training from epoch ' + str(cfg.lrate.epoch)) numpy_rng = numpy.random.RandomState(89677) theano_rng = RandomStreams(numpy_rng.randint(2 ** 30)) log('> ... building the model') # setup model if cfg.do_dropout: dnn = DNN_Dropout(numpy_rng=numpy_rng, theano_rng = theano_rng, cfg = cfg) else: dnn = DNN(numpy_rng=numpy_rng, theano_rng = theano_rng, cfg = cfg) # initialize model parameters # if not resuming training, initialized from the specified pre-training file # if resuming training, initialized from the tmp model file if (ptr_layer_number > 0) and (resume_training is False): _file2nnet(dnn.layers, set_layer_num = ptr_layer_number, filename = ptr_file) if resume_training: _file2nnet(dnn.layers, filename = wdir + '/nnet.tmp') # get the training, validation and testing function for the model log('> ... getting the finetuning functions') train_fn, valid_fn = dnn.build_finetune_functions((cfg.train_x, cfg.train_y), (cfg.valid_x, cfg.valid_y), batch_size=cfg.batch_size) log('> ... finetuning the model') while (cfg.lrate.get_rate() != 0): # one epoch of sgd training train_error = train_sgd(train_fn, cfg) log('> epoch %d, training error %f ' % (cfg.lrate.epoch, 100*numpy.mean(train_error)) + '(%)') # validation valid_error = validate_by_minibatch(valid_fn, cfg) log('> epoch %d, lrate %f, validation error %f ' % (cfg.lrate.epoch, cfg.lrate.get_rate(), 100*numpy.mean(valid_error)) + '(%)') cfg.lrate.get_next_rate(current_error = 100*numpy.mean(valid_error)) # output nnet parameters and lrate, for training resume if cfg.lrate.epoch % cfg.model_save_step == 0: _nnet2file(dnn.layers, filename=wdir + '/nnet.tmp') _lrate2file(cfg.lrate, wdir + '/training_state.tmp') # save the model and network configuration if cfg.param_output_file != '': _nnet2file(dnn.layers, filename=cfg.param_output_file, input_factor = cfg.input_dropout_factor, factor = cfg.dropout_factor) log('> ... the final PDNN model parameter is ' + cfg.param_output_file) if cfg.cfg_output_file != '': _cfg2file(dnn.cfg, filename=cfg.cfg_output_file) log('> ... the final PDNN model config is ' + cfg.cfg_output_file)
def dnn_run(arguments): required_arguments = ['train_data', 'valid_data', 'nnet_spec', 'wdir'] for arg in required_arguments: if arguments.has_key(arg) == False: print "Error: the argument %s has to be specified" % (arg) exit(1) train_data_spec = arguments['train_data'] valid_data_spec = arguments['valid_data'] nnet_spec = arguments['nnet_spec'] wdir = arguments['wdir'] cfg = NetworkConfig() cfg.parse_config_dnn(arguments, nnet_spec) cfg.init_data_reading(train_data_spec, valid_data_spec) # parse pre-training options # pre-training files and layer number (how many layers are set to the pre-training parameters) ptr_layer_number = 0 ptr_file = '' if arguments.has_key('ptr_file') and arguments.has_key('ptr_layer_number'): ptr_file = arguments['ptr_file'] ptr_layer_number = int(arguments['ptr_layer_number']) # check working dir to see whether it's resuming training resume_training = False if os.path.exists(wdir + '/nnet.tmp') and os.path.exists(wdir + '/training_state.tmp'): resume_training = True cfg.lrate = _file2lrate(wdir + '/training_state.tmp') log('> ... found nnet.tmp and training_state.tmp, now resume training from epoch ' + str(cfg.lrate.epoch)) numpy_rng = numpy.random.RandomState(89677) theano_rng = RandomStreams(numpy_rng.randint(2**30)) log('> ... building the model') # setup model if cfg.do_dropout: dnn = DNN_Dropout(numpy_rng=numpy_rng, theano_rng=theano_rng, cfg=cfg) else: dnn = DNN(numpy_rng=numpy_rng, theano_rng=theano_rng, cfg=cfg) # initialize model parameters # if not resuming training, initialized from the specified pre-training file # if resuming training, initialized from the tmp model file if (ptr_layer_number > 0) and (resume_training is False): _file2nnet(dnn.layers, set_layer_num=ptr_layer_number, filename=ptr_file) if resume_training: _file2nnet(dnn.layers, filename=wdir + '/nnet.tmp') # get the training, validation and testing function for the model log('> ... getting the finetuning functions') train_fn, valid_fn = dnn.build_finetune_functions( (cfg.train_x, cfg.train_y), (cfg.valid_x, cfg.valid_y), batch_size=cfg.batch_size) log('> ... finetuning the model') while (cfg.lrate.get_rate() != 0): # one epoch of sgd training train_error = train_sgd(train_fn, cfg) log('> epoch %d, training error %f ' % (cfg.lrate.epoch, 100 * numpy.mean(train_error)) + '(%)') # validation valid_error = validate_by_minibatch(valid_fn, cfg) log('> epoch %d, lrate %f, validation error %f ' % (cfg.lrate.epoch, cfg.lrate.get_rate(), 100 * numpy.mean(valid_error)) + '(%)') cfg.lrate.get_next_rate(current_error=100 * numpy.mean(valid_error)) # output nnet parameters and lrate, for training resume if cfg.lrate.epoch % cfg.model_save_step == 0: _nnet2file(dnn.layers, filename=wdir + '/nnet.tmp') _lrate2file(cfg.lrate, wdir + '/training_state.tmp') # save the model and network configuration if cfg.param_output_file != '': _nnet2file(dnn.layers, filename=cfg.param_output_file, input_factor=cfg.input_dropout_factor, factor=cfg.dropout_factor) log('> ... the final PDNN model parameter is ' + cfg.param_output_file) if cfg.cfg_output_file != '': _cfg2file(dnn.cfg, filename=cfg.cfg_output_file) log('> ... the final PDNN model config is ' + cfg.cfg_output_file)