#################################################################### #################################################################### time_start = 0 best_valid = inf # main loop # ------------------------------------------------------------------------------ lr_decay_epoch = 0 n_lr_decays = 0 train_ce, valid_ce = [], [] flag=True global insp_ insp_ = None res_dir = save_results(train_ce, valid_ce, res_dir, params=params) save_params(params, res_dir) lr.decay = 1 for epoch in xrange(tr.n_epochs): ce = [] print_params(params) #################################################################### #################################################################### print "\n%s\n\t epoch %d \n%s"%('-'*30, epoch, '-'*30) #################################################################### #################################################################### time_start = time() for i in range(loader.n_iter_train): #load data time_start_iter = time()
apply_updates, train_model, test_model = net_convnet3d_grbm_early_fusion.build_finetune_functions(x_, y_int32, x_skeleton_,learning_rate) ###################################################################### print "\n%s\n\ttraining\n%s"%(('-'*30,)*2) time_start = 0 best_valid = inf lr_decay_epoch = 0 n_lr_decays = 0 train_ce, valid_ce = [], [] out_mean_all, out_std_all = [], [] res_dir = save_results(train_ce, valid_ce, res_dir, params=net_convnet3d_grbm_early_fusion.params) save_params(net_convnet3d_grbm_early_fusion.params, res_dir) # default learning rate lr.start = 0.0001 lr.stop = 0.00001 # Wudi makes thie to explicity control the learning rate learning_rate_map = linspace(lr.start, lr.stop, tr.n_epochs) for epoch in xrange(tr.n_epochs): learning_rate.set_value(float32(learning_rate_map[epoch])) ce = [] out_mean_train = [] out_std_train = [] print_params(net_convnet3d_grbm_early_fusion.params) ####################################################################
#################################################################### #################################################################### time_start = 0 best_valid = inf # main loop # ------------------------------------------------------------------------------ lr_decay_epoch = 0 n_lr_decays = 0 train_ce, valid_ce = [], [] flag = True global insp_ insp_ = None res_dir = save_results(train_ce, valid_ce, res_dir, params=params) save_params(params, res_dir) lr.decay = 1 for epoch in xrange(tr.n_epochs): ce = [] print_params(params) #################################################################### #################################################################### print "\n%s\n\t epoch %d \n%s" % ('-' * 30, epoch, '-' * 30) #################################################################### #################################################################### time_start = time() for i in range(loader.n_iter_train): #load data time_start_iter = time()
###################################################################### print "\n%s\n\ttraining\n%s" % (('-' * 30, ) * 2) time_start = 0 best_valid = inf lr_decay_epoch = 0 n_lr_decays = 0 train_ce, valid_ce = [], [] out_mean_all, out_std_all = [], [] res_dir = save_results(train_ce, valid_ce, res_dir, params=net_convnet3d_grbm_early_fusion.params) save_params(net_convnet3d_grbm_early_fusion.params, res_dir) # default learning rate lr.start = 0.0001 lr.stop = 0.00001 # Wudi makes thie to explicity control the learning rate learning_rate_map = linspace(lr.start, lr.stop, tr.n_epochs) for epoch in xrange(tr.n_epochs): learning_rate.set_value(float32(learning_rate_map[epoch])) ce = [] out_mean_train = [] out_std_train = [] print_params(net_convnet3d_grbm_early_fusion.params) ####################################################################