if category_name == 'n/a': category_name = category_id c_it = model_counter[category_id] if c_it < vis_n_outputs: data_vis_list.append({'category': category_name, 'it': c_it, 'data': data_vis}) model_counter[category_id] += 1 """ # Model model = config.get_model(cfg, device=device, dataset=train_dataset) # Intialize training optimizer = optim.Adam(model.parameters(), lr=1e-4) trainer = config.get_trainer(model, optimizer, cfg, device=device) checkpoint_io = CheckpointIO(out_dir, model=model, optimizer=optimizer) try: load_dict = checkpoint_io.load('model.pt') except FileExistsError: load_dict = dict() epoch_it = load_dict.get('epoch_it', -1) it = load_dict.get('it', -1) it0 = load_dict.get('it', -1) metric_val_best = load_dict.get('loss_val_best', -model_selection_sign * np.inf) # Generator generator = config.get_generator(model, cfg, device=device)
out_file = os.path.join(out_dir, 'eval_full.pkl') out_file_class = os.path.join(out_dir, 'eval.csv') # Dataset dataset = config.get_dataset('test', cfg, return_idx=True) model = config.get_model(cfg, device=device, dataset=dataset) checkpoint_io = CheckpointIO(out_dir, model=model) try: checkpoint_io.load(cfg['test']['model_file']) except FileExistsError: print('Model file does not exist. Exiting.') exit() # Trainer trainer = config.get_trainer(model, None, cfg, device=device) # Print model nparameters = sum(p.numel() for p in model.parameters()) print(model) print('Total number of parameters: %d' % nparameters) # Evaluate model.eval() eval_dicts = [] print('Evaluating networks...') test_loader = torch.utils.data.DataLoader( dataset, batch_size=1, shuffle=False,