FanZhang
FanZhang
Good luck Svito-zar, I hope the war will stop soon. Take care of yourself!
Hi, I soluted the problem, however, it must be restarted after modifying the docker. it took a long time to restart.
How to fix the Bug? :( I have tried many days....
Maybe you could rebuild the requirements.txt file with all the packages information so we could import the right version.
dear sir。 i got an error that could not find the file 0000000.npz when run the savezcompress function
Found the cache /home/zf223669/Mount/S2AG/data/ted_db/lmdb_test_s2ag_v2_cache_mfcc_14 building a language model... loaded from /home/zf223669/Mount/S2AG/data/ted_db/vocab_models_s2ag/vocab_cache.pkl Saved key 200037. Traceback (most recent call last): File "/home/zf223669/Mount/S2AG/speech2affective_gestures/main_v2.py", line 121, in train_data_ted, val_data_ted, test_data_ted = loader.load_ted_db_data(data_path, s2ag_config_args,...
Hi, It could work now!I found that the save_cache() could not create the npz-train npz-test npz-val automatically, so I create the fould manually , commend the "if not os.path.exists(train_dir_nam/val_dir_name/test_dir_name) ,...
> I think a lot of bugs in this project are caused by incorrect paths and mismatched versions of dependencies.
Hi, i use 64 batches. I use a savgol_filter to reduce the problem. The training time is quit fast.
> I train the model with the default config. The training process takes only about 20 minutes. The generated motion jitters heavily. How many batches of data are in one...