saharudra / graph_table_recognition Goto Github PK

when I prepare ALL the data and code and running trainers/trainer_multi.py
I encounter a problem:
but I dont know where is going wrong.
can auther give me some guide?
thanks very much!

*** STARTING TRAINING LOOP ***
Traceback (most recent call last):
File "trainers/trainer_col_only.py", line 251, in
main(config=namespace_config_dict)
File "trainers/trainer_col_only.py", line 87, in main
train_loss = train(model, optimizer, train_loader, loss_criteria)
File "trainers/trainer_col_only.py", line 131, in train
for idx, data in enumerate(train_loader):
File "/home/ywx/anaconda3/envs/GTR/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 363, in next
data = self._next_data()
File "/home/ywx/anaconda3/envs/GTR/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 403, in _next_data
data = self._dataset_fetcher.fetch(index) # may raise StopIteration
File "/home/ywx/anaconda3/envs/GTR/lib/python3.6/site-packages/torch/utils/data/_utils/fetch.py", line 47, in fetch
return self.collate_fn(data)
File "/home/ywx/anaconda3/envs/GTR/lib/python3.6/site-packages/torch_geometric/data/dataloader.py", line 34, in call
return self.collate(batch)
File "/home/ywx/anaconda3/envs/GTR/lib/python3.6/site-packages/torch_geometric/data/dataloader.py", line 15, in collate
return Batch.from_data_list(batch, self.follow_batch)
File "/home/ywx/anaconda3/envs/GTR/lib/python3.6/site-packages/torch_geometric/data/batch.py", line 123, in from_data_list
batch[key] = torch.cat(items, ref_data.cat_dim(key, item))
RuntimeError: Sizes of tensors must match except in dimension 0. Got 357 and 238 in dimension 2 (The offending index is 1)