-
### Describe the issue
Can not run import model (exported by pytorch.onnx.export) by onnx run time method ort.InferenceSession.
Below error is generated:
 in loading state_dict for FOTSModel:
Missing key(s) in state_dict: "sharedConv.backbone.conv1.weight", "sharedConv.backbone.bn1.weight", "sharedConv.backbone.bn1.bias", "share…
-
Hi,
Thanks for your open-source of the AdaptivFloat. It is an impressive paper.
I implemented your code in Resnet-50 model with imageNet dataset.(https://github.com/pytorch/vision/blob/master/t…
-
Hi, I'm trying to train the underline backbone with detector_pretrain_net.py. But for approximately 50% of the weights I'm getting 'NO-MATCHING of current module'.
Is this something to fix or is this…
-
Hello all,
I am trying to use a different savefile which was generated for CULane [here](https://github.com/koyeongmin/PINet_new/tree/master/CULane). I have changed parameters.py and test.py files…
-
RuntimeError: Error(s) in loading state_dict for PoseNet_2branch:
Missing key(s) in state_dict: "backbone.conv1.weight", "backbone.bn1.weight", "backbone.bn1.bias", "backbone.bn1.running_mean…
-
when I use the commend "python tools/train.py configs/ReDet/ReDet_re50_refpn_1x_dota15.py" train DOTA dataset I meet the follow error,how I can do to solve it. Thank you!
ReResNet Orientation: 8 Fi…
-
```
What steps will reproduce the problem?
1.Create 2 shape in layer1
2.New layer2, add picture into layer2
3.At layer 2, i want to choice shape in layer1 and active layer1
What is the expected outpu…