-
I would like your help to make clear an issue with the number of dims of the extracted features.
It is said in the Readme that "In the feature mode, this code outputs features of 512 dims (after glo…
-
-
When I run the Single-Person demo code, it shows a problem.
The cuda is 9.0.176 and cudnn is 7.4.2.24
(tensorflow) bfs@zty2:~/pose-tensorflow-master$ TF_CUDNN_USE_AUTOTUNE=0 python3 demo/singleper…
-
Improve the [current flood segmentation model](https://github.com/cc-ai/deeplab-pytorch) , see #62
We report below a comparison of a first series of flood segmentation models using mIoU on our han…
-
Really excellent work!
In fact, we have tried to integerate the ResNeSt backbone in our own code-base [openseg.pytorch](https://github.com/openseg-group/openseg.pytorch).
Here is the backbone co…
-
**Describe the bug**
Inference breaking onnxruntime-gpu/CUDA error when attempting to use ONNX model converted from tensorflow .pb file. Model works fine on CPU. Tensorflow model itself works fine on…
-
i just can get the resnet-101 model here
-
Trying to build deeplabv3 from PyTorch to deploy on top of Xilinx EDGE device - zcu104. Facing some issues while quantizing. For good metrics as suggested in https://github.com/Xilinx/pyxir/issues/33#…
-
It seems that the current model is only valid for the test data set you provide, I used some random monitoring images of the Internet to test, the effect is very inaccurate, any suggestions to solve?
…
-
I used python script to generate three json files of UCF101, they are ucf101_01.json,ucf101_01.json,ucf101_03.json
I run the main function to train resnet
python main.py --root_path ./data --vide…