facebookresearch / facebookresearch/detectron2

can not export model with dcn operation to onnx!

Open

#4,444 opened on Aug 1, 2022 1 comment 0 reactions 0 assignees View on GitHub

Dominant language: Python
Stars: 34.7k
Forks: 7.9k
PR merge metrics: No merged PRs in 30d

Description

## Instructions To Reproduce the 🐛 Bug:
1. Full runnable code or full changes you made:
```
If making changes to the project itself, please use output of the following command:
git rev-parse HEAD; git diff

```
2. What exact command you run:
python tools/deploy/export_model.py
3. __Full logs__ or other relevant
```
[32m[08/01 12:48:09 detectron2]:
[32m[08/01 12:48:12 d2.checkpoint.c
| Names in Model
|:----------------------------------
| backbone.bottom_up.res2.0.conv1.*
| backbone.bottom_up.res2.0.conv2.*
| backbone.bottom_up.res2.0.conv3.*
| backbone.bottom_up.res2.0.shortcut.*
| backbone.bottom_up.res2.1.conv1.*
| backbone.bottom_up.res2.1.conv2.*
| backbone.bottom_up.res2.1.conv3.*
| backbone.bottom_up.res2.2.conv1.*
| backbone.bottom_up.res2.2.conv2.*
| backbone.bottom_up.res2.2.conv3.*
| backbone.bottom_up.res3.0.conv1.*
| backbone.bottom_up.res3.0.conv2.*
| backbone.bottom_up.res3.0.conv2_offset.*
| backbone.bottom_up.res3.0.conv3.*
| backbone.bottom_up.res3.0.shortcut.*
| backbone.bottom_up.res3.1.conv1.*
| backbone.bottom_up.res3.1.conv2.*
| backbone.bottom_up.res3.1.conv2_offset.*
| backbone.bottom_up.res3.1.conv3.*
| backbone.bottom_up.res3.2.conv1.*
| backbone.bottom_up.res3.2.conv2.*
| backbone.bottom_up.res3.2.conv2_offset.*
| backbone.bottom_up.res3.2.conv3.*
| backbone.bottom_up.res3.3.conv1.*
| backbone.bottom_up.res3.3.conv2.*
| backbone.bottom_up.res3.3.conv2_offset.*
| backbone.bottom_up.res3.3.conv3.*
| backbone.bottom_up.res4.0.conv1.*
| backbone.bottom_up.res4.0.conv2.*
| backbone.bottom_up.res4.0.conv2_offset.*
| backbone.bottom_up.res4.0.conv3.*
| backbone.bottom_up.res4.0.shortcut.*
| backbone.bottom_up.res4.1.conv1.*
| backbone.bottom_up.res4.1.conv2.*
| backbone.bottom_up.res4.1.conv2_offset.*
| backbone.bottom_up.res4.1.conv3.*
| backbone.bottom_up.res4.10.conv1.*
| backbone.bottom_up.res4.10.conv2.*
| backbone.bottom_up.res4.10.conv2_offset.*
| backbone.bottom_up.res4.10.conv3.*
| backbone.bottom_up.res4.11.conv1.*
| backbone.bottom_up.res4.11.conv2.*
| backbone.bottom_up.res4.11.conv2_offset.*
| backbone.bottom_up.res4.11.conv3.*
| backbone.bottom_up.res4.12.conv1.*
| backbone.bottom_up.res4.12.conv2.*
| backbone.bottom_up.res4.12.conv2_offset.*
| backbone.bottom_up.res4.12.conv3.*
| backbone.bottom_up.res4.13.conv1.*
| backbone.bottom_up.res4.13.conv2.*
| backbone.bottom_up.res4.13.conv2_offset.*
| backbone.bottom_up.res4.13.conv3.*
| backbone.bottom_up.res4.14.conv1.*
| backbone.bottom_up.res4.14.conv2.*
| backbone.bottom_up.res4.14.conv2_offset.*
| backbone.bottom_up.res4.14.conv3.*
| backbone.bottom_up.res4.15.conv1.*
| backbone.bottom_up.res4.15.conv2.*
| backbone.bottom_up.res4.15.conv2_offset.*
| backbone.bottom_up.res4.15.conv3.*
| backbone.bottom_up.res4.16.conv1.*
| backbone.bottom_up.res4.16.conv2.*
| backbone.bottom_up.res4.16.conv2_offset.*
| backbone.bottom_up.res4.16.conv3.*
| backbone.bottom_up.res4.17.conv1.*
| backbone.bottom_up.res4.17.conv2.*
| backbone.bottom_up.res4.17.conv2_offset.*
| backbone.bottom_up.res4.17.conv3.*
| backbone.bottom_up.res4.18.conv1.*
| backbone.bottom_up.res4.18.conv2.*
| backbone.bottom_up.res4.18.conv2_offset.*
| backbone.bottom_up.res4.18.conv3.*
| backbone.bottom_up.res4.19.conv1.*
| backbone.bottom_up.res4.19.conv2.*
| backbone.bottom_up.res4.19.conv2_offset.*
| backbone.bottom_up.res4.19.conv3.*
| backbone.bottom_up.res4.2.conv1.*
| backbone.bottom_up.res4.2.conv2.*
| backbone.bottom_up.res4.2.conv2_offset.*
| backbone.bottom_up.res4.2.conv3.*
| backbone.bottom_up.res4.20.conv1.*
| backbone.bottom_up.res4.20.conv2.*
| backbone.bottom_up.res4.20.conv2_offset.*
| backbone.bottom_up.res4.20.conv3.*
| backbone.bottom_up.res4.21.conv1.*
| backbone.bottom_up.res4.21.conv2.*
| backbone.bottom_up.res4.21.conv2_offset.*
| backbone.bottom_up.res4.21.conv3.*
| backbone.bottom_up.res4.22.conv1.*
| backbone.bottom_up.res4.22.conv2.*
| backbone.bottom_up.res4.22.conv2_offset.*
| backbone.bottom_up.res4.22.conv3.*
| backbone.bottom_up.res4.3.conv1.*
| backbone.bottom_up.res4.3.conv2.*
| backbone.bottom_up.res4.3.conv2_offset.*
| backbone.bottom_up.res4.3.conv3.*
| backbone.bottom_up.res4.4.conv1.*
| backbone.bottom_up.res4.4.conv2.*
| backbone.bottom_up.res4.4.conv2_offset.*
| backbone.bottom_up.res4.4.conv3.*
| backbone.bottom_up.res4.5.conv1.*
| backbone.bottom_up.res4.5.conv2.*
| backbone.bottom_up.res4.5.conv2_offset.*
| backbone.bottom_up.res4.5.conv3.*
| backbone.bottom_up.res4.6.conv1.*
| backbone.bottom_up.res4.6.conv2.*
| backbone.bottom_up.res4.6.conv2_offset.*
| backbone.bottom_up.res4.6.conv3.*
| backbone.bottom_up.res4.7.conv1.*
| backbone.bottom_up.res4.7.conv2.*
| backbone.bottom_up.res4.7.conv2_offset.*
| backbone.bottom_up.res4.7.conv3.*
| backbone.bottom_up.res4.8.conv1.*
| backbone.bottom_up.res4.8.conv2.*
| backbone.bottom_up.res4.8.conv2_offset.*
| backbone.bottom_up.res4.8.conv3.*
| backbone.bottom_up.res4.9.conv1.*
| backbone.bottom_up.res4.9.conv2.*
| backbone.bottom_up.res4.9.conv2_offset.*
| backbone.bottom_up.res4.9.conv3.*
| backbone.bottom_up.res5.0.conv1.*
| backbone.bottom_up.res5.0.conv2.*
| backbone.bottom_up.res5.0.conv2_offset.*
| backbone.bottom_up.res5.0.conv3.*
| backbone.bottom_up.res5.0.shortcut.*
| backbone.bottom_up.res5.1.conv1.*
| backbone.bottom_up.res5.1.conv2.*
| backbone.bottom_up.res5.1.conv2_offset.*
| backbone.bottom_up.res5.1.conv3.*
| backbone.bottom_up.res5.2.conv1.*
| backbone.bottom_up.res5.2.conv2.*
| backbone.bottom_up.res5.2.conv2_offset.*
| backbone.bottom_up.res5.2.conv3.*
| backbone.bottom_up.stem.conv1.*
| backbone.fpn_lateral2.*
| backbone.fpn_lateral3.*
| backbone.fpn_lateral4.*
| backbone.fpn_lateral5.*
| backbone.fpn_output2.*
| backbone.fpn_output3.*
| backbone.fpn_output4.*
| backbone.fpn_output5.*
| proposal_generator.rpn_head.anchor_deltas.*
| proposal_generator.rpn_head.conv.*
| proposal_generator.rpn_head.objectness_logits.*
| roi_heads.box_head.fc1.*
| roi_heads.box_head.fc2.*
| roi_heads.box_predictor.bbox_pred.*
| roi_heads.box_predictor.cls_score.*
| roi_heads.mask_head.deconv.*
| roi_heads.mask_head.mask_fcn1.*
| roi_heads.mask_head.mask_fcn2.*
| roi_heads.mask_head.mask_fcn3.*
| roi_heads.mask_head.mask_fcn4.*
| roi_heads.mask_head.predictor.*
sample_inputs shape is: torch.Size([3,
```
4. please simplify the steps
run, such as a private dataset. --format "onnx" --export-method "tracing" --sample-image "./tools/deploy/new_302.jpg" --output "onnxdir/" observations: [0mCommand line arguments: Namespace(format='onnx', export_method='tracing', config_file='./configs/COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x_dconv.yaml', sample_image='./tools/deploy/new_302.jpg', run_eval=False, output='onnxdir/', opts=[]) 2_model_loading]: [0mFollowing weights matched with model: | Names in Checkpoint | Shapes | --------------|:-----------------------------------------------------------------------------------------------------|:------------------------------------------------| | backbone.bottom_up.res2.0.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (64,) (64,) (64,) (64,) (64,64,1,1) | | backbone.bottom_up.res2.0.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (64,) (64,) (64,) (64,) (64,64,3,3) | | backbone.bottom_up.res2.0.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,64,1,1) | | backbone.bottom_up.res2.0.shortcut.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,64,1,1) | | backbone.bottom_up.res2.1.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (64,) (64,) (64,) (64,) (64,256,1,1) | | backbone.bottom_up.res2.1.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (64,) (64,) (64,) (64,) (64,64,3,3) | | backbone.bottom_up.res2.1.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,64,1,1) | | backbone.bottom_up.res2.2.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (64,) (64,) (64,) (64,) (64,256,1,1) | | backbone.bottom_up.res2.2.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (64,) (64,) (64,) (64,) (64,64,3,3) | | backbone.bottom_up.res2.2.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,64,1,1) | | backbone.bottom_up.res3.0.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (128,) (128,) (128,) (128,) (128,256,1,1) | | backbone.bottom_up.res3.0.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (128,) (128,) (128,) (128,) (128,128,3,3) | | backbone.bottom_up.res3.0.conv2_offset.{bias,weight} | (18,) (18,128,3,3) | | backbone.bottom_up.res3.0.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (512,) (512,) (512,) (512,) (512,128,1,1) | | backbone.bottom_up.res3.0.shortcut.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (512,) (512,) (512,) (512,) (512,256,1,1) | | backbone.bottom_up.res3.1.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (128,) (128,) (128,) (128,) (128,512,1,1) | | backbone.bottom_up.res3.1.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (128,) (128,) (128,) (128,) (128,128,3,3) | | backbone.bottom_up.res3.1.conv2_offset.{bias,weight} | (18,) (18,128,3,3) | | backbone.bottom_up.res3.1.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (512,) (512,) (512,) (512,) (512,128,1,1) | | backbone.bottom_up.res3.2.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (128,) (128,) (128,) (128,) (128,512,1,1) | | backbone.bottom_up.res3.2.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (128,) (128,) (128,) (128,) (128,128,3,3) | | backbone.bottom_up.res3.2.conv2_offset.{bias,weight} | (18,) (18,128,3,3) | | backbone.bottom_up.res3.2.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (512,) (512,) (512,) (512,) (512,128,1,1) | | backbone.bottom_up.res3.3.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (128,) (128,) (128,) (128,) (128,512,1,1) | | backbone.bottom_up.res3.3.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (128,) (128,) (128,) (128,) (128,128,3,3) | | backbone.bottom_up.res3.3.conv2_offset.{bias,weight} | (18,) (18,128,3,3) | | backbone.bottom_up.res3.3.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (512,) (512,) (512,) (512,) (512,128,1,1) | | backbone.bottom_up.res4.0.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,512,1,1) | | backbone.bottom_up.res4.0.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.0.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.0.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.0.shortcut.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,512,1,1) | | backbone.bottom_up.res4.1.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.1.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.1.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.1.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.10.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.10.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.10.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.10.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.11.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.11.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.11.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.11.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.12.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.12.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.12.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.12.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.13.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.13.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.13.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.13.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.14.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.14.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.14.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.14.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.15.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.15.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.15.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.15.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.16.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.16.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.16.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.16.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.17.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.17.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.17.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.17.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.18.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.18.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.18.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.18.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.19.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.19.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.19.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.19.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.2.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.2.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.2.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.2.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.20.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.20.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.20.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.20.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.21.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.21.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.21.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.21.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.22.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.22.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.22.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.22.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.3.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.3.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.3.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.3.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.4.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.4.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.4.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.4.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.5.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.5.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.5.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.5.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.6.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.6.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.6.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.6.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.7.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.7.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.7.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.7.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.8.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.8.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.8.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.8.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res4.9.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,1024,1,1) | | backbone.bottom_up.res4.9.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (256,) (256,) (256,) (256,) (256,256,3,3) | | backbone.bottom_up.res4.9.conv2_offset.{bias,weight} | (18,) (18,256,3,3) | | backbone.bottom_up.res4.9.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (1024,) (1024,) (1024,) (1024,) (1024,256,1,1) | | backbone.bottom_up.res5.0.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (512,) (512,) (512,) (512,) (512,1024,1,1) | | backbone.bottom_up.res5.0.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (512,) (512,) (512,) (512,) (512,512,3,3) | | backbone.bottom_up.res5.0.conv2_offset.{bias,weight} | (18,) (18,512,3,3) | | backbone.bottom_up.res5.0.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (2048,) (2048,) (2048,) (2048,) (2048,512,1,1) | | backbone.bottom_up.res5.0.shortcut.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (2048,) (2048,) (2048,) (2048,) (2048,1024,1,1) | | backbone.bottom_up.res5.1.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (512,) (512,) (512,) (512,) (512,2048,1,1) | | backbone.bottom_up.res5.1.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (512,) (512,) (512,) (512,) (512,512,3,3) | | backbone.bottom_up.res5.1.conv2_offset.{bias,weight} | (18,) (18,512,3,3) | | backbone.bottom_up.res5.1.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (2048,) (2048,) (2048,) (2048,) (2048,512,1,1) | | backbone.bottom_up.res5.2.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (512,) (512,) (512,) (512,) (512,2048,1,1) | | backbone.bottom_up.res5.2.conv2.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (512,) (512,) (512,) (512,) (512,512,3,3) | | backbone.bottom_up.res5.2.conv2_offset.{bias,weight} | (18,) (18,512,3,3) | | backbone.bottom_up.res5.2.conv3.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (2048,) (2048,) (2048,) (2048,) (2048,512,1,1) | | backbone.bottom_up.stem.conv1.{norm.bias,norm.running_mean,norm.running_var,norm.weight,weight} | (64,) (64,) (64,) (64,) (64,3,7,7) | | backbone.fpn_lateral2.{bias,weight} | (256,) (256,256,1,1) | | backbone.fpn_lateral3.{bias,weight} | (256,) (256,512,1,1) | | backbone.fpn_lateral4.{bias,weight} | (256,) (256,1024,1,1) | | backbone.fpn_lateral5.{bias,weight} | (256,) (256,2048,1,1) | | backbone.fpn_output2.{bias,weight} | (256,) (256,256,3,3) | | backbone.fpn_output3.{bias,weight} | (256,) (256,256,3,3) | | backbone.fpn_output4.{bias,weight} | (256,) (256,256,3,3) | | backbone.fpn_output5.{bias,weight} | (256,) (256,256,3,3) | | proposal_generator.rpn_head.anchor_deltas.{bias,weight} | (12,) (12,256,1,1) | | proposal_generator.rpn_head.conv.{bias,weight} | (256,) (256,256,3,3) | | proposal_generator.rpn_head.objectness_logits.{bias,weight} | (3,) (3,256,1,1) | | roi_heads.box_head.fc1.{bias,weight} | (1024,) (1024,12544) | | roi_heads.box_head.fc2.{bias,weight} | (1024,) (1024,1024) | | roi_heads.box_predictor.bbox_pred.{bias,weight} | (20,) (20,1024) | | roi_heads.box_predictor.cls_score.{bias,weight} | (6,) (6,1024) | | roi_heads.mask_head.deconv.{bias,weight} | (256,) (256,256,2,2) | | roi_heads.mask_head.mask_fcn1.{bias,weight} | (256,) (256,256,3,3) | | roi_heads.mask_head.mask_fcn2.{bias,weight} | (256,) (256,256,3,3) | | roi_heads.mask_head.mask_fcn3.{bias,weight} | (256,) (256,256,3,3) | | roi_heads.mask_head.mask_fcn4.{bias,weight} | (256,) (256,256,3,3) | | roi_heads.mask_head.predictor.{bias,weight} | (5,) (5,256,1,1) | 2048, 2048]) as much as possible so they do not require additional resources to

## Expected behavior:
export maskrcnn_r101_fpn_3x_dcn model to onnx file

## Environment:

Provide your environment information using the following command:
```
sys.platform linux
Python 3.10.5 | packaged by conda-forge | (main, Jun 14 2022, 07:06:46) [GCC 10.3.0]
numpy 1.22.3
detectron2 0.6 @/home/wt-yjy/project/code/new_d2/detectron2/detectron2
Compiler GCC 7.5
CUDA compiler CUDA 11.3
detectron2 arch flags 8.6
DETECTRON2_ENV_MODULE
PyTorch 1.12.0 @/home/wt-yjy/anaconda3/envs/new_d2/lib/python3.10/site-packages/torch
PyTorch debug build False
GPU available Yes
GPU 0,1,2,3,4,5,6,7 NVIDIA GeForce RTX 3090 (arch=8.6)
Driver version 515.48.07
CUDA_HOME /usr/local/cuda-11.3
Pillow 9.2.0
torchvision 0.13.0 @/home/wt-yjy/anaconda3/envs/new_d2/lib/python3.10/site-packages/torchvision
torchvision arch flags 3.5, 5.0, 6.0, 7.0, 7.5, 8.0, 8.6
fvcore 0.1.5.post20220512
iopath 0.1.9
cv2 4.6.0
---------------------- -----------------------------------------------------------------------------------
PyTorch built with:
- GCC 9.3
- C++ Version: 201402
- Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- LAPACK is enabled (usually provided by MKL)
- NNPACK is enabled
- CPU capability usage: AVX2
- CUDA Runtime 11.3
- NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37
- CuDNN 8.3.2 (built against CUDA 11.5)
- Magma 2.5.2
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.12.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF,

Testing NCCL connectivity ... this should not hang.
NCCL succeeded.
```

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

can not export model with dcn operation to onnx!

Description

Contributor guide

Assessment

Get new issues in your inbox