Can't train this model (ValueError: 'UNK' is not in list)

[Eom-taeseon]

I'm trying to follow ConvCap: Convolutional Image Captioning(README.md)
But it doesn't work

after I write the code
python main.py model_dir

It sends a error message like thie

[DEBUG] #words in wordlist: 9222
[DEBUG] Loading train data ... 3.029390 secs
C:\Users\410\anaconda3\envs\Image_Captioning\lib\site-packages\torch\optim\lr_scheduler.py:82: UserWarning: Detected call of lr_scheduler.step() before optimizer.step(). In PyTorch 1.1.0 and later, you should call them in the opposite order: optimizer.step() before lr_scheduler.step(). Failure to do this will result in PyTorch skipping the first value of the learning rate schedule.See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
"https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate", UserWarning)
0%| | 0/5664 [00:00<?, ?it/s]
Traceback (most recent call last):
File "main.py", line 89, in
main()
File "main.py", line 72, in main
train(args)
File "D:\2021\컴퓨터 비전\eval\이미지 캡셔닝\train.py", line 90, in train
tqdm(enumerate(train_data_loader), total=nbatches):
File "C:\Users\410\anaconda3\envs\Image_Captioning\lib\site-packages\tqdm\std.py", line 1180, in iter
for obj in iterable:
File "C:\Users\410\anaconda3\envs\Image_Captioning\lib\site-packages\torch\utils\data\dataloader.py", line 819, in next
return self._process_data(data)
File "C:\Users\410\anaconda3\envs\Image_Captioning\lib\site-packages\torch\utils\data\dataloader.py", line 846, in _process_data
data.reraise()
File "C:\Users\410\anaconda3\envs\Image_Captioning\lib\site-packages\torch_utils.py", line 369, in reraise
raise self.exc_type(msg)
ValueError: Caught ValueError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "C:\Users\410\anaconda3\envs\Image_Captioning\lib\site-packages\torch\utils\data_utils\worker.py", line 178, in _worker_loop
data = fetcher.fetch(index)
File "C:\Users\410\anaconda3\envs\Image_Captioning\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "C:\Users\410\anaconda3\envs\Image_Captioning\lib\site-packages\torch\utils\data_utils\fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "D:\2021\컴퓨터 비전\eval\이미지 캡셔닝\coco_loader.py", line 102, in getitem
wordclass[i, word_i] = self.wordlist.index(word)
ValueError: 'UNK' is not in list

How can I solve this?

[vakadanaveen]

I am having the exact same error.
To solve this error I simply added 'UNK' token to the wordlist.
In the program coco_loader.py , line number 40.
Replace the line
self.wordlist = ['EOS'] + sorted(wordlist)
with
self.wordlist = ['EOS'] + sorted(wordlist)+['UNK']

Then the program works.