-
Thank you for the amazing work. I was able to setup the BEVFusion inference using the model files given in the readme.
I want to use this pipeline for BEVFusion trained on my dataset, so as per the […
-
1> python quant_ptq.py
2> error log:
Traceback (most recent call last):
File "quant_ptq.py", line 27, in
import quant_utils as quant
File "/home/work/YOLOv8_PTQ/quant_utils.py", line…
-
I have used PTQ for int8 export from pytorch model and despite attempts at calibration, there is a significant drop in detection accuracy.
I am moving to quantization aware training to improve the…
-
# PTQ | Download video bằng tool ffmpeg trên Windows
Đây là 1 bài chia sẻ vui! Dành cho bạn nào chưa biết thì ffmpeg là cái tool xịn xò dùng để tải video ở những nơi…không thể tải bằng cách thông thư…
-
### 🐛 Describe the bug
fp32 static shape default wrapper
suite
name
thread
batch_size_new
speed_up_new
inductor_new
eager_new
compi…
-
**Describe the bug**
I used docker to run onnxruntime transformers optimizer and met this error, but I can successfully run it on my local ubuntu machine. Could you give any suggestion?
![image](htt…
-
Completed parsing of ONNX file
Building an engine from file /home/zhaomt/com/yolov5int8/yolov5/yolov5s.onnx; this may take a while...
wrong
[04/25/2024-17:36:20] [TRT] [E] 1: Unexpected exception _…
-
### 🐛 Describe the bug
from torch.ao.quantization.quantizer import (
XNNPACKQuantizer,
get_symmetric_quantization_config,
)
the code abve report error:
ImportError: cannot import name 'X…
-
### 请提出你的问题
使用paddleslim 量化unimo时报错:Operator (fusion_unified_decoding) is not registered.
转为静态图后好像不支持’fusion_unified_decoding‘算子,有什么办法可以支持该算子(例如如何register)?
> Preparation stage, Run batch:| …
-
Firstly, thanks to all of you for the bravo project!
Currently, the model seems like does not support int8 quantization. Any plan on it?