On the issue of features_arr_concat

[GoodMorningAndGoodEvening]

Hi dipika, First of all, thank you very much for your excellent work! When I experimented with the GTEA dataset, it generated the following error:

Traceback (most recent call last): File "E:\pycharm2021.3\pythonProject\Semi-supervised\ICC-Semi-Supervised-TAS-main\runcodes\unsupervised_traineval.py", line 600, in model = model_pipeline(args) File "E:\pycharm2021.3\pythonProject\Semi-supervised\ICC-Semi-Supervised-TAS-main\runcodes\unsupervised_traineval.py", line 251, in model_pipeline train(model, train_loader, criterion, optimizer, args, test_loader, postprocessor) File "E:\pycharm2021.3\pythonProject\Semi-supervised\ICC-Semi-Supervised-TAS-main\runcodes\unsupervised_traineval.py", line 571, in train acc, all_result = get_linear_acc(args.label_id_csv, dump_dir, args.ground_truth_files_dir, args.perdata, File "E:\pycharm2021.3\pythonProject\Semi-supervised\ICC-Semi-Supervised-TAS-main\utility\perform_linear.py", line 263, in get_linear_acc feat_labels_videoids_dict = get_gathered_features_labels_videoids(ground_truth_dir, feature_dump_dir, File "E:\pycharm2021.3\pythonProject\Semi-supervised\ICC-Semi-Supervised-TAS-main\utility\perform_linear.py", line 43, in get_gathered_features_labels_videoids features_arr_concat = np.concatenate(features_arr_concat, axis=0) ValueError: all the input array dimensions except for the concatenation axis must match exactly, but along dimension 1, the array at index 0 has size 943 and the array at index 1 has size 1178

I printed out the features_arr_concat and found that they are matrices of different sizes, so they cannot be connected. How can I solve this problem? Best wishes Thanks.

[ee2110]

Hi @GoodMorningAndGoodEvening , I was wondering if you have found any solution or workaround for the issue? It would be really helpful to know how you approached it, thank you!