File "/data/Phantom/gradio1.py", line 211, in inference
caption = model.generate({"image": image}, num_captions=1)[0]
File "/usr/local/lib/python3.10/site-packages/lavis/models/blip_models/blip_caption.py", line 188, in generate
decoder_out = self.text_decoder.generate_from_encoder(
File "/usr/local/lib/python3.10/site-packages/lavis/models/med.py", line 1360, in generate_from_encoder
outputs = self.generate(
File "/usr/local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/transformers/generation/utils.py", line 1797, in generate
return self.beam_search(
File "/usr/local/lib/python3.10/site-packages/transformers/generation/utils.py", line 3181, in beam_search
outputs = self(
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/lavis/models/med.py", line 1210, in forward
outputs = self.bert(
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/lavis/models/med.py", line 974, in forward
encoder_outputs = self.encoder(
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/lavis/models/med.py", line 592, in forward
layer_outputs = layer_module(
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/lavis/models/med.py", line 475, in forward
cross_attention_outputs = self.crossattention(
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/lavis/models/med.py", line 346, in forward
self_outputs = self.self(
File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.10/site-packages/lavis/models/med.py", line 219, in forward
attention_scores = torch.matmul(query_layer, key_layer.transpose(-1, -2))
RuntimeError: The size of tensor a (3) must match the size of tensor b (9) at non-singleton dimension 0