I have trained the model I want through Pytorch and exported the. pth file.
Now I want to convert it to TensorRT to be able to deploy to my Jetson device.
Can torch2trt do it?
I’ve been trying for days but still can’t do it, please help! Many thanks in advance !!!
Hi,
You can do it in the following ways.
https://pytorch.org/tutorials/advanced/super_resolution_with_onnxruntime.html
Thank you.
Thank you for your reply! I am still fighting for it.
I tried a lot these days, but when I run model_trt = torch2trt(model, ), always have different bugs come up…
The model is trained by detectron2, and I have already load the weights in. But i still struggled to transfer it to TensorRT by torch2trt.
Do we have any succeesful examples? About how to transfer a detectron2 trained model to TensorRT by torch2trt?
I really need to achieve it soon. Please help me!!!
Have you tried the above method?
Please refer to the following sample.
Thank you.
I am trying Pytorch model → ONNX model → TensorRT as well, but stucked too.
I’ve been trying for days to use torch.onnx.export() to convert my trained detectron2 model to onnx.
The detectron2 model is a GeneralizedRCNN model, It is also the ideal model that took me a long time to train, using my own data set.
Now I want to convert it to onnx to deploy it, but there are always various errors.
When I read the official document today, I found that it seems that the model of type “recurrent network” cannot be converted with torch.onnx.export()? It is said that torch.jit.trace() cannot convert it.
Sincerely and eagerly requesting an answer, is it possible to use torch.onnx.export() to complete the conversion of the detectron2 trained GeneralizedRCNN model?
I have been tortured for many days, please help me dear experts!
Please try building the TRT engine from the Detectron2 model using the following official sample.
If you still face an issue, please share with us complete verbose logs and the issue repro model for better debugging.
Thank you.
Dear Moderator, I tried this official sample, but at the step of " Model Conversion", I met an issue: KeyError: ‘UNKNOWN_SCALAR’ .
Here are the complete verbose logs and the issue repro model :
%run detectron2/tools/deploy/export_model.py \
--sample-image /home/nvidia/Downloads/Laparoscopic_Left_Hepatectomy/test/00000030_1344x1344.jpg \
--config-file output_onnx.yaml \
--export-method tracing \
--format onnx \
--output /home/nvidia/Downloads/output_onnx \
MODEL.WEIGHTS /home/nvidia/Downloads/output/model_final.pth \
MODEL.DEVICE cuda
[02/05 14:32:42 detectron2]: Command line arguments: Namespace(config_file='output_onnx.yaml', export_method='tracing', format='onnx', opts=['MODEL.WEIGHTS', '/home/nvidia/Downloads/output/model_final.pth', 'MODEL.DEVICE', 'cuda'], output='/home/nvidia/Downloads/output_onnx', run_eval=False, sample_image='/home/nvidia/Downloads/Laparoscopic_Left_Hepatectomy/test/00000030_1344x1344.jpg')
[W init.cpp:756] Warning: Use _jit_set_fusion_strategy, bailout depth is deprecated. Setting to (STATIC, 1) (function operator())
[02/05 14:32:45 d2.checkpoint.c2_model_loading]: Following weights matched with model:
| Names in Model | Names in Checkpoint | Shapes |
|:------------------------------------------------|:-----------------------------------------------------------------------------------------------------|:------------------------------------------------|
| backbone.bottom_up.res2.0.conv1.* | 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.* | 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.* | 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.* | 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.* | 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.* | 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.* | 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.* | 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.* | 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.* | 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.* | 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.* | 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.conv3.* | 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.* | 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.* | 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.* | 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.conv3.* | 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.* | 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.* | 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.conv3.* | 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.* | 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.* | 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.conv3.* | 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.* | 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.* | 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.conv3.* | 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.* | 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.* | 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.* | 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.conv3.* | 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.res4.2.conv1.* | 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.* | 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.conv3.* | 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.res4.3.conv1.* | 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.* | 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.conv3.* | 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.* | 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.* | 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.conv3.* | 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.* | 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.* | 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.conv3.* | 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.res5.0.conv1.* | 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.* | 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.conv3.* | 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.* | 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.* | 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.* | 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.conv3.* | 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.* | 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.* | 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.conv3.* | 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.* | 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.* | backbone.fpn_lateral2.{bias,weight} | (256,) (256,256,1,1) |
| backbone.fpn_lateral3.* | backbone.fpn_lateral3.{bias,weight} | (256,) (256,512,1,1) |
| backbone.fpn_lateral4.* | backbone.fpn_lateral4.{bias,weight} | (256,) (256,1024,1,1) |
| backbone.fpn_lateral5.* | backbone.fpn_lateral5.{bias,weight} | (256,) (256,2048,1,1) |
| backbone.fpn_output2.* | backbone.fpn_output2.{bias,weight} | (256,) (256,256,3,3) |
| backbone.fpn_output3.* | backbone.fpn_output3.{bias,weight} | (256,) (256,256,3,3) |
| backbone.fpn_output4.* | backbone.fpn_output4.{bias,weight} | (256,) (256,256,3,3) |
| backbone.fpn_output5.* | backbone.fpn_output5.{bias,weight} | (256,) (256,256,3,3) |
| proposal_generator.rpn_head.anchor_deltas.* | proposal_generator.rpn_head.anchor_deltas.{bias,weight} | (12,) (12,256,1,1) |
| proposal_generator.rpn_head.conv.* | proposal_generator.rpn_head.conv.{bias,weight} | (256,) (256,256,3,3) |
| proposal_generator.rpn_head.objectness_logits.* | proposal_generator.rpn_head.objectness_logits.{bias,weight} | (3,) (3,256,1,1) |
| roi_heads.box_head.fc1.* | roi_heads.box_head.fc1.{bias,weight} | (1024,) (1024,12544) |
| roi_heads.box_head.fc2.* | roi_heads.box_head.fc2.{bias,weight} | (1024,) (1024,1024) |
| roi_heads.box_predictor.bbox_pred.* | roi_heads.box_predictor.bbox_pred.{bias,weight} | (4,) (4,1024) |
| roi_heads.box_predictor.cls_score.* | roi_heads.box_predictor.cls_score.{bias,weight} | (2,) (2,1024) |
| roi_heads.mask_head.deconv.* | roi_heads.mask_head.deconv.{bias,weight} | (256,) (256,256,2,2) |
| roi_heads.mask_head.mask_fcn1.* | roi_heads.mask_head.mask_fcn1.{bias,weight} | (256,) (256,256,3,3) |
| roi_heads.mask_head.mask_fcn2.* | roi_heads.mask_head.mask_fcn2.{bias,weight} | (256,) (256,256,3,3) |
| roi_heads.mask_head.mask_fcn3.* | roi_heads.mask_head.mask_fcn3.{bias,weight} | (256,) (256,256,3,3) |
| roi_heads.mask_head.mask_fcn4.* | roi_heads.mask_head.mask_fcn4.{bias,weight} | (256,) (256,256,3,3) |
| roi_heads.mask_head.predictor.* | roi_heads.mask_head.predictor.{bias,weight} | (1,) (1,256,1,1) |
/home/nvidia/Downloads/detectron2/detectron2/structures/image_list.py:85: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert t.shape[:-2] == tensors[0].shape[:-2], t.shape
/home/nvidia/Downloads/detectron2/detectron2/structures/boxes.py:155: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert tensor.dim() == 2 and tensor.size(-1) == 4, tensor.size()
/home/nvidia/Downloads/detectron2/detectron2/structures/boxes.py:155: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert tensor.dim() == 2 and tensor.size(-1) == 4, tensor.size()
/home/nvidia/Downloads/detectron2/detectron2/modeling/proposal_generator/proposal_utils.py:106: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if not valid_mask.all():
/home/nvidia/Downloads/detectron2/detectron2/structures/boxes.py:191: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert torch.isfinite(self.tensor).all(), "Box tensor contains infinite or NaN!"
/home/nvidia/Downloads/detectron2/detectron2/structures/boxes.py:192: TracerWarning: Iterating over a tensor might cause the trace to be incorrect. Passing a tensor of different shape won't change the number of iterations executed (and might lead to errors or silently give incorrect results).
h, w = box_size
/home/nvidia/Downloads/detectron2/detectron2/layers/nms.py:15: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert boxes.shape[-1] == 4
/home/nvidia/.local/lib/python3.8/site-packages/torch/__init__.py:772: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert condition, message
/home/nvidia/Downloads/detectron2/detectron2/layers/roi_align.py:55: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert rois.dim() == 2 and rois.size(1) == 5
/home/nvidia/Downloads/detectron2/detectron2/modeling/roi_heads/fast_rcnn.py:138: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if not valid_mask.all():
/home/nvidia/Downloads/detectron2/detectron2/modeling/roi_heads/fast_rcnn.py:143: UserWarning: __floordiv__ is deprecated, and its behavior will change 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').
num_bbox_reg_classes = boxes.shape[1] // 4
/home/nvidia/Downloads/detectron2/detectron2/structures/boxes.py:155: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert tensor.dim() == 2 and tensor.size(-1) == 4, tensor.size()
/home/nvidia/Downloads/detectron2/detectron2/structures/boxes.py:191: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert torch.isfinite(self.tensor).all(), "Box tensor contains infinite or NaN!"
/home/nvidia/Downloads/detectron2/detectron2/structures/boxes.py:192: TracerWarning: Iterating over a tensor might cause the trace to be incorrect. Passing a tensor of different shape won't change the number of iterations executed (and might lead to errors or silently give incorrect results).
h, w = box_size
/home/nvidia/Downloads/detectron2/detectron2/modeling/roi_heads/fast_rcnn.py:155: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if num_bbox_reg_classes == 1:
/home/nvidia/Downloads/detectron2/detectron2/layers/nms.py:15: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert boxes.shape[-1] == 4
/home/nvidia/.local/lib/python3.8/site-packages/torch/__init__.py:772: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert condition, message
/home/nvidia/Downloads/detectron2/detectron2/layers/roi_align.py:55: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
assert rois.dim() == 2 and rois.size(1) == 5
/home/nvidia/Downloads/detectron2/detectron2/modeling/roi_heads/mask_head.py:139: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if cls_agnostic_mask:
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
File ~/Downloads/detectron2/tools/deploy/export_model.py:228
226 elif args.export_method == "tracing":
227 sample_inputs = get_sample_inputs(args)
--> 228 exported_model = export_tracing(torch_model, sample_inputs)
230 # run evaluation with the converted model
231 if args.run_eval:
File ~/Downloads/detectron2/tools/deploy/export_model.py:132, in export_tracing(torch_model, inputs)
130 elif args.format == "onnx":
131 with PathManager.open(os.path.join(args.output, "model.onnx"), "wb") as f:
--> 132 torch.onnx.export(traceable_model, (image,), f, opset_version=STABLE_ONNX_OPSET_VERSION)
133 logger.info("Inputs schema: " + str(traceable_model.inputs_schema))
134 logger.info("Outputs schema: " + str(traceable_model.outputs_schema))
File ~/.local/lib/python3.8/site-packages/torch/onnx/__init__.py:305, in export(model, args, f, export_params, verbose, training, input_names, output_names, operator_export_type, opset_version, do_constant_folding, dynamic_axes, keep_initializers_as_inputs, custom_opsets, export_modules_as_functions)
39 r"""
40 Exports a model into ONNX format. If ``model`` is not a
41 :class:`torch.jit.ScriptModule` nor a :class:`torch.jit.ScriptFunction`, this runs
(...)
301 model to the file ``f`` even if this is raised.
302 """
304 from torch.onnx import utils
--> 305 return utils.export(model, args, f, export_params, verbose, training,
306 input_names, output_names, operator_export_type, opset_version,
307 do_constant_folding, dynamic_axes,
308 keep_initializers_as_inputs, custom_opsets,
309 export_modules_as_functions)
File ~/.local/lib/python3.8/site-packages/torch/onnx/utils.py:118, in export(model, args, f, export_params, verbose, training, input_names, output_names, operator_export_type, opset_version, do_constant_folding, dynamic_axes, keep_initializers_as_inputs, custom_opsets, export_modules_as_functions)
115 else:
116 operator_export_type = OperatorExportTypes.ONNX
--> 118 _export(model, args, f, export_params, verbose, training, input_names, output_names,
119 operator_export_type=operator_export_type, opset_version=opset_version,
120 do_constant_folding=do_constant_folding, dynamic_axes=dynamic_axes,
121 keep_initializers_as_inputs=keep_initializers_as_inputs,
122 custom_opsets=custom_opsets, export_modules_as_functions=export_modules_as_functions)
File ~/.local/lib/python3.8/site-packages/torch/onnx/utils.py:719, in _export(model, args, f, export_params, verbose, training, input_names, output_names, operator_export_type, export_type, opset_version, do_constant_folding, dynamic_axes, keep_initializers_as_inputs, fixed_batch_size, custom_opsets, add_node_names, onnx_shape_inference, export_modules_as_functions)
715 dynamic_axes = {}
716 _validate_dynamic_axes(dynamic_axes, model, input_names, output_names)
718 graph, params_dict, torch_out = \
--> 719 _model_to_graph(model, args, verbose, input_names,
720 output_names, operator_export_type,
721 val_do_constant_folding,
722 fixed_batch_size=fixed_batch_size,
723 training=training,
724 dynamic_axes=dynamic_axes)
726 # TODO: Don't allocate a in-memory string for the protobuf
727 defer_weight_export = export_type is not ExportTypes.PROTOBUF_FILE
File ~/.local/lib/python3.8/site-packages/torch/onnx/utils.py:503, in _model_to_graph(model, args, verbose, input_names, output_names, operator_export_type, do_constant_folding, _disable_torch_constant_prop, fixed_batch_size, training, dynamic_axes)
499 graph, params, torch_out, module = _create_jit_graph(model, args)
501 params_dict = _get_named_param_dict(graph, params)
--> 503 graph = _optimize_graph(graph, operator_export_type,
504 _disable_torch_constant_prop=_disable_torch_constant_prop,
505 fixed_batch_size=fixed_batch_size, params_dict=params_dict,
506 dynamic_axes=dynamic_axes, input_names=input_names,
507 module=module)
508 from torch.onnx.symbolic_helper import _onnx_shape_inference
509 if isinstance(model, torch.jit.ScriptModule) or isinstance(model, torch.jit.ScriptFunction):
File ~/.local/lib/python3.8/site-packages/torch/onnx/utils.py:232, in _optimize_graph(graph, operator_export_type, _disable_torch_constant_prop, fixed_batch_size, params_dict, dynamic_axes, input_names, module)
230 torch._C._jit_pass_onnx_set_dynamic_input_shape(graph, dynamic_axes, input_names)
231 torch._C._jit_pass_onnx_lint(graph)
--> 232 graph = torch._C._jit_pass_onnx(graph, operator_export_type)
233 torch._C._jit_pass_onnx_lint(graph)
234 torch._C._jit_pass_lint(graph)
File ~/.local/lib/python3.8/site-packages/torch/onnx/__init__.py:354, in _run_symbolic_function(*args, **kwargs)
352 def _run_symbolic_function(*args, **kwargs):
353 from torch.onnx import utils
--> 354 return utils._run_symbolic_function(*args, **kwargs)
File ~/.local/lib/python3.8/site-packages/torch/onnx/utils.py:1061, in _run_symbolic_function(g, block, n, inputs, env, operator_export_type)
1059 return None
1060 attrs = {k: n[k] for k in n.attributeNames()}
-> 1061 return symbolic_fn(g, *inputs, **attrs)
1063 elif ns == "prim":
1064 if op_name == "Constant" and not n.mustBeNone():
File ~/.local/lib/python3.8/site-packages/torch/onnx/symbolic_opset9.py:2065, in to(g, self, *args)
2062 if sym_help._is_value(dtype) or isinstance(dtype, torch.Tensor):
2063 # aten::to(Tensor, Tensor, bool, bool, memory_format)
2064 dtype = args[0].type().scalarType()
-> 2065 return g.op("Cast", self, to_i=sym_help.cast_pytorch_to_onnx[dtype])
2066 else:
2067 # aten::to(Tensor, ScalarType, bool, bool, memory_format)
2068 # memory_format is ignored
2069 return g.op("Cast", self, to_i=sym_help.scalar_type_to_onnx[dtype])
KeyError: 'UNKNOWN_SCALAR'
I searched this bug on internet and try to figure it out, but still can’t find a solution, please help me !
We recommend you to please reach out to Issues · NVIDIA/TensorRT · GitHub to get better help regarding the above error.
Thank you.