You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Dear author, NExT-Chat's capability of fine-grained image comprehension is really fascinating. But when I run bash eval_res.sh with param --per_device_eval_batch_size 2, an exception was raised. Here it is:
File "NExT-Chat/./mllm/models/sam/modeling_sam.py", line 1006, in forward
sparse_embeddings = torch.cat([sparse_embeddings, box_embeddings], dim=1)
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 2 but got size 4 for tensor number 1 in the list.
Sorry for its length, but I discovered that dimensions of sparse_embeddings and box_embeddings do not match. Any suggestion?
The text was updated successfully, but these errors were encountered:
Dear author, NExT-Chat's capability of fine-grained image comprehension is really fascinating. But when I run
bash eval_res.sh
with param--per_device_eval_batch_size 2
, an exception was raised. Here it is:Sorry for its length, but I discovered that dimensions of
sparse_embeddings
andbox_embeddings
do not match. Any suggestion?The text was updated successfully, but these errors were encountered: