-
## Checklist
- [x] I'm reporting a bug in Sherlock's functionality
- [ ] The bug I'm reporting is not a false positive or a false negative
- [x] I've verified that I'm running the latest …
-
When i use bolt quantization to infer with file ppo_cnn_int8_q.bolt, i meet this problem.
[ERROR] thread 24754 file /home/xys/bolt-master/inference/engine/include/factory.hpp line 242: this librar…
-
### Description
tf version is 2.10
int8 tflite model has 4 Conv2DTranspose Layer.
int8 tflite model has uint8 input and output
edgetpu compiler version 16.x
When I edgetpu compile the tflite mo…
-
Hi, When I use advanced_ptq of mqbench to quantify my model, I get the keyvalue error problem in this place.
The adaround optimization operati…
-
Can you please let me know what's the cause of this issue
-
### Search before asking
- [X] I have searched the Yolov5_StrongSORT_OSNet [issues](https://github.com/mikel-brostrom/Yolov5_StrongSORT_OSNet/issues) and [discussions](https://github.com/mikel-bros…
-
Hello teams,
I try to quantize all the parameters of my model in a `per_tensor` way.
And I found that the final output quantization model still contains layers `per_channel`.
the `yaml` file is…
-
### Description
We have tested working industrial safety monitoring solution on a RPi and now need to port our TFlite model and inference solution to an industrial IMX8 gateway. By chasing the variou…
-
### 🐛 Describe the bug
I follow the guidelines in https://pytorch.org/blog/quantization-in-practice/#post-training-static-quantization-ptq and run the code snippet:
```
# Static quantization of …
-
## Description
Using the `pytorch-quantization` toolkit of TensorRT to do PTQ on a pytorch model, gives 0 scale values for some nodes, which causes ONNX parse error when trying to loading into Tens…