train one-class dataset error, After following the instructions for custom datasets training. waiting for your advice. Thanks

[whlgstone2]

[rank1]: File "/root/download/D-FINE/src/zoo/dfine/hybrid_encoder.py", line 267, in forward
[rank1]: src, _ = self.self_attn(q, k, value=src, attn_mask=src_mask)
[rank1]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank1]: File "/root/miniconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1736, in _wrapped_call_impl
[rank1]: return self._call_impl(*args, **kwargs)
[rank1]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank1]: File "/root/miniconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1844, in _call_impl
[rank1]: return inner()
[rank1]: ^^^^^^^
[rank1]: File "/root/miniconda3/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790, in inner
[rank1]: result = forward_call(*args, **kwargs)
[rank1]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank1]: File "/root/miniconda3/lib/python3.12/site-packages/torch/nn/modules/activation.py", line 1368, in forward
[rank1]: attn_output, attn_output_weights = F.multi_head_attention_forward(
[rank1]: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
[rank1]: File "/root/miniconda3/lib/python3.12/site-packages/torch/nn/functional.py", line 6087, in multi_head_attention_forward
[rank1]: key.shape == value.shape
[rank1]: AssertionError: key shape torch.Size([400, 1, 256]) does not match value shape torch.Size([1, 1, 256])

[lz1004]

Have you tried starting your custom dataset annotations with category id 0 instead of 1?