-
when running Spatio-Temporal Action Detection on my cutom ava-style dataset, I got following error:
```python
2021-11-22 08:49:08,117 - mmaction - INFO - Distributed training: False
2021-11-22 08…
-
I'm training detectoRS with resent50 backbone on a custom dataset.
I customized the train pipeline (input size for the net : `1024x768px`, all my images are of these dimensions),
When I train wit…
joihn updated
3 years ago
-
I trained Swin Transformers Cityscapes Instance Segmentation from pretrained Swin Base on ImageNet 22K.
During training, evaluations are very normal.
E.g:
```
2021-06-29 00:57:35,334 - mmdet - INF…
-
I was trying out inferencing of a few Computer Vision based models on Android devices. I was able to successfully run the inference on a Linux PC using the pre-built onnx (cpp) library that was readil…
-
When trying to reproduce results of meta-rcnn and TFA, under 1 shot setting of split1, I find that reproduced results of meta-rcnn is much higher, which is confusing.In paper of meta-rcnn(this 19.9 is…
-
Installing collected packages: termcolor, tabulate, Shapely, absl-py, markdown, grpcio, oauthlib, requests-oauthlib, google-auth-oauthlib, tensorboard-plugin-wit, tensorboard, portalocker, dl-lib
R…
-
Hi. when i used faster rcnn model, I got 2 errors about "Reduce Max" and failed of importing onnx model.
Barracuda version: 1.2.0
Opset version: 11
onnx model: faster r-cnn ( mobilNet backbone)
…
-
I encountered a runtime error `RuntimeError: Could not run 'aten::thnn_conv2d_forward' with arguments from the 'QuantizedCPU' backend.` when I tried exporting a [COCO object detection model](https://g…
-
When I run the code ,I met the following problem" RuntinmeError:Not compiled with GPU support " dose anyone meet the same problem? my environment is pytorch1.71 cuda 10.1 GRX 2080Ti
-
Hi there,
I've run the dockerised installation and I hit this issue whenever I try to import a model.
Otherwise everything works fine. Does anyone have any ideas about what is going on here? L…