Error reporting issue when adding batchformerv2 to other class detr models

[cbn3]

Sorry to bother you.The error message is as follows. How can I resolve it？
root@i-r5mjznu9:/workspace/cbn/DINO# /opt/conda/lib/python3.8/site-packages/torch/tensor.py:559: UserWarning: floor_divide is deprecated, and will be removed in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values.
To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). (Triggered internally at ../aten/src/ATen/native/BinaryOps.cpp:335.)
return torch.floor_divide(self, other)
Traceback (most recent call last):
File "main.py", line 423, in
main(args)
File "main.py", line 309, in main
train_stats = train_one_epoch(
File "/workspace/cbn/DINO/engine.py", line 48, in train_one_epoch
outputs = model(samples, targets)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in call_impl
result = self.forward(*input, **kwargs)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/parallel/distributed.py", line 707, in forward
output = self.module(*inputs[0], **kwargs[0])
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in call_impl
result = self.forward(*input, **kwargs)
File "/workspace/cbn/DINO/models/dino/dino.py", line 270, in forward
hs, reference, hs_enc, ref_enc, init_box_proposal = self.transformer(srcs, masks, input_query_bbox, poss,input_query_label,attn_mask)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in call_impl
result = self.forward(*input, **kwargs)
File "/workspace/cbn/DINO/models/dino/deformable_transformer.py", line 343, in forward
output_memory, output_proposals = gen_encoder_output_proposals(memory, mask_flatten, spatial_shapes, input_hw)
File "/workspace/cbn/DINO/models/dino/utils.py", line 31, in gen_encoder_output_proposals
mask_flatten = memory_padding_mask[:, cur:(cur + H * W)].view(N, H, W_, 1)
RuntimeError: shape '[8, 92, 92, 1]' is invalid for input of size 33856
/opt/conda/lib/python3.8/site-packages/torch/tensor.py:559: UserWarning: floor_divide is deprecated, and will be removed in a future version of pytorch. It currently rounds toward 0 (like the 'trunc' function NOT 'floor'). This results in incorrect rounding for negative values.
To keep the current behavior, use torch.div(a, b, rounding_mode='trunc'), or for actual floor division, use torch.div(a, b, rounding_mode='floor'). (Triggered internally at ../aten/src/ATen/native/BinaryOps.cpp:335.)
return torch.floor_divide(self, other)
Traceback (most recent call last):
File "main.py", line 423, in
main(args)
File "main.py", line 309, in main
train_stats = train_one_epoch(
File "/workspace/cbn/DINO/engine.py", line 48, in train_one_epoch
outputs = model(samples, targets)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in call_impl
result = self.forward(*input, **kwargs)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/parallel/distributed.py", line 707, in forward
output = self.module(*inputs[0], **kwargs[0])
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in call_impl
result = self.forward(*input, **kwargs)
File "/workspace/cbn/DINO/models/dino/dino.py", line 270, in forward
hs, reference, hs_enc, ref_enc, init_box_proposal = self.transformer(srcs, masks, input_query_bbox, poss,input_query_label,attn_mask)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in call_impl
result = self.forward(*input, **kwargs)
File "/workspace/cbn/DINO/models/dino/deformable_transformer.py", line 343, in forward
output_memory, output_proposals = gen_encoder_output_proposals(memory, mask_flatten, spatial_shapes, input_hw)
File "/workspace/cbn/DINO/models/dino/utils.py", line 31, in gen_encoder_output_proposals
mask_flatten = memory_padding_mask[:, cur:(cur + H * W)].view(N, H, W_, 1)
RuntimeError: shape '[8, 139, 96, 1]' is invalid for input of size 53376

[zhihou7]

Do you set the value of N to 8? it might be 4.

[cbn3]

Do you set the value of N to 8? it might be 4.

Thank you for your prompt response. After trying your suggestion, the following error was reported. How can I resolve it？
Traceback (most recent call last):
File "main.py", line 424, in
main(args)
File "main.py", line 233, in main
model_without_ddp.load_state_dict(checkpoint['model'])
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1223, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for DINO:
Missing key(s) in state_dict: "transformer.bf.0.self_attn.in_proj_weight", "transformer.bf.0.self_attn.in_proj_bias", "transformer.bf.0.self_attn.out_proj.weight", "transformer.bf.0.self_attn.out_proj.bias", "transformer.bf.0.linear1.weight", "transformer.bf.0.linear1.bias", "transformer.bf.0.linear2.weight", "transformer.bf.0.linear2.bias", "transformer.bf.0.norm1.weight", "transformer.bf.0.norm1.bias", "transformer.bf.0.norm2.weight", "transformer.bf.0.norm2.bias", "transformer.encoder.bf.0.self_attn.in_proj_weight", "transformer.encoder.bf.0.self_attn.in_proj_bias", "transformer.encoder.bf.0.self_attn.out_proj.weight", "transformer.encoder.bf.0.self_attn.out_proj.bias", "transformer.encoder.bf.0.linear1.weight", "transformer.encoder.bf.0.linear1.bias", "transformer.encoder.bf.0.linear2.weight", "transformer.encoder.bf.0.linear2.bias", "transformer.encoder.bf.0.norm1.weight", "transformer.encoder.bf.0.norm1.bias", "transformer.encoder.bf.0.norm2.weight", "transformer.encoder.bf.0.norm2.bias".
size mismatch for transformer.encoder.layers.0.self_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.encoder.layers.0.self_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.encoder.layers.0.self_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.encoder.layers.0.self_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.encoder.layers.1.self_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.encoder.layers.1.self_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.encoder.layers.1.self_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.encoder.layers.1.self_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.encoder.layers.2.self_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.encoder.layers.2.self_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.encoder.layers.2.self_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.encoder.layers.2.self_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.encoder.layers.3.self_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.encoder.layers.3.self_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.encoder.layers.3.self_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.encoder.layers.3.self_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.encoder.layers.4.self_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.encoder.layers.4.self_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.encoder.layers.4.self_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.encoder.layers.4.self_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.encoder.layers.5.self_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.encoder.layers.5.self_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.encoder.layers.5.self_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.encoder.layers.5.self_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.decoder.layers.0.cross_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.decoder.layers.0.cross_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.decoder.layers.0.cross_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.decoder.layers.0.cross_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.decoder.layers.1.cross_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.decoder.layers.1.cross_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.decoder.layers.1.cross_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.decoder.layers.1.cross_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.decoder.layers.2.cross_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.decoder.layers.2.cross_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.decoder.layers.2.cross_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.decoder.layers.2.cross_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.decoder.layers.3.cross_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.decoder.layers.3.cross_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.decoder.layers.3.cross_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.decoder.layers.3.cross_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.decoder.layers.4.cross_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.decoder.layers.4.cross_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.decoder.layers.4.cross_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.decoder.layers.4.cross_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.decoder.layers.5.cross_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.decoder.layers.5.cross_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.decoder.layers.5.cross_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.decoder.layers.5.cross_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
Traceback (most recent call last):
File "main.py", line 424, in
main(args)
File "main.py", line 233, in main
model_without_ddp.load_state_dict(checkpoint['model'])
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1223, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for DINO:
Missing key(s) in state_dict: "transformer.bf.0.self_attn.in_proj_weight", "transformer.bf.0.self_attn.in_proj_bias", "transformer.bf.0.self_attn.out_proj.weight", "transformer.bf.0.self_attn.out_proj.bias", "transformer.bf.0.linear1.weight", "transformer.bf.0.linear1.bias", "transformer.bf.0.linear2.weight", "transformer.bf.0.linear2.bias", "transformer.bf.0.norm1.weight", "transformer.bf.0.norm1.bias", "transformer.bf.0.norm2.weight", "transformer.bf.0.norm2.bias", "transformer.encoder.bf.0.self_attn.in_proj_weight", "transformer.encoder.bf.0.self_attn.in_proj_bias", "transformer.encoder.bf.0.self_attn.out_proj.weight", "transformer.encoder.bf.0.self_attn.out_proj.bias", "transformer.encoder.bf.0.linear1.weight", "transformer.encoder.bf.0.linear1.bias", "transformer.encoder.bf.0.linear2.weight", "transformer.encoder.bf.0.linear2.bias", "transformer.encoder.bf.0.norm1.weight", "transformer.encoder.bf.0.norm1.bias", "transformer.encoder.bf.0.norm2.weight", "transformer.encoder.bf.0.norm2.bias".
size mismatch for transformer.encoder.layers.0.self_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.encoder.layers.0.self_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.encoder.layers.0.self_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.encoder.layers.0.self_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.encoder.layers.1.self_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.encoder.layers.1.self_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.encoder.layers.1.self_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.encoder.layers.1.self_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.encoder.layers.2.self_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.encoder.layers.2.self_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.encoder.layers.2.self_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.encoder.layers.2.self_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.encoder.layers.3.self_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.encoder.layers.3.self_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.encoder.layers.3.self_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.encoder.layers.3.self_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.encoder.layers.4.self_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.encoder.layers.4.self_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.encoder.layers.4.self_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.encoder.layers.4.self_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.encoder.layers.5.self_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.encoder.layers.5.self_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.encoder.layers.5.self_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.encoder.layers.5.self_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.decoder.layers.0.cross_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.decoder.layers.0.cross_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.decoder.layers.0.cross_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.decoder.layers.0.cross_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.decoder.layers.1.cross_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.decoder.layers.1.cross_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.decoder.layers.1.cross_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.decoder.layers.1.cross_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.decoder.layers.2.cross_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.decoder.layers.2.cross_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.decoder.layers.2.cross_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.decoder.layers.2.cross_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.decoder.layers.3.cross_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.decoder.layers.3.cross_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.decoder.layers.3.cross_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.decoder.layers.3.cross_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.decoder.layers.4.cross_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.decoder.layers.4.cross_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.decoder.layers.4.cross_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.decoder.layers.4.cross_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).
size mismatch for transformer.decoder.layers.5.cross_attn.sampling_offsets.weight: copying a param with shape torch.Size([256, 256]) from checkpoint, the shape in current model is torch.Size([128, 256]).
size mismatch for transformer.decoder.layers.5.cross_attn.sampling_offsets.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([128]).
size mismatch for transformer.decoder.layers.5.cross_attn.attention_weights.weight: copying a param with shape torch.Size([128, 256]) from checkpoint, the shape in current model is torch.Size([64, 256]).
size mismatch for transformer.decoder.layers.5.cross_attn.attention_weights.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([64]).

[zhihou7]

N in This line

mask_flatten = memory_padding_mask[:, cur:(cur + H * W)].view(N, H, W_, 1)

[cbn3]

N in This line

mask_flatten = memory_padding_mask[:, cur:(cur + H * W)].view(N, H, W_, 1)

Sorry to bother you.When I add default=[] to the parameter insert_idx and run main.py without assigning insert_idx a value of 0, the initial error is not reported. However, in this case, has batchformerv2 been successfully added to the model?

[zhihou7]

Hi, Sorry for getting you late. According to the code, in detr, I set the default value in here