search

aimagelab / meshed-memory-transformer

Meshed-Memory Transformer for Image Captioning. CVPR 2020
BSD 3-Clause "New" or "Revised" License
517 stars 136 forks source link

I meet error but i can't solve,please help #8

Closed bean-point closed 4 years ago

bean-point commented 4 years ago

PS D:\meshed-memory-transformer-master> python train.py --exp_name m2_transformer --batch_size 50 --m 40 --head 8 --warmup 10000 --features_path meshed_memory_transformer.pth --annotation_folder annotations Namespace(annotation_folder='annotations', batch_size=50, exp_name='m2_transformer', features_path='meshed_memory_transformer.pth', head=8, logs_folder='tensorboard_logs', m=40, resume_best=False, resume_last=False, warmup=10000, workers=0) Meshed-Memory Transformer Training Traceback (most recent call last): File "train.py", line 186, in cider_train = Cider(PTBTokenizer.tokenize(ref_caps_train)) File "D:\meshed-memory-transformer-master\evaluation\tokenizer.py", line 48, in tokenize p_tokenizer = subprocess.Popen(cmd, cwd=path_to_jar_dirname,stdout=subprocess.PIPE, stderr=open(os.devnull, 'w')) File "D:\soft\Anaconda3\lib\subprocess.py", line 709, in init restore_signals, start_new_session) File "D:\soft\Anaconda3\lib\subprocess.py", line 997, in _execute_child startupinfo)

marcellacornia commented 4 years ago

Hi @bean-point, thanks for your interest in our work.

Did you create the conda environment that we provided before running the code?