-
**问题**
使用例程中的“编译uint8量化tflite模型”,模型使用的样例中的‘examples/20classes_yolo/model/20classes_yolo.tflite’,修改量化类型为int16,输出模型大小无任何变化,Netron查看ir_target_dep_after_quant下的pb文件,卷积核等各项参数仍然是uint8类型
compile_options.qu…
-
## Background
I am currently exploring the topic of deep learning model quantization techniques. In the official [NVIDIA's Tensor RT documentation](https://docs.nvidia.com/deeplearning/tensorrt/dev…
-
Thanks a lot for this awesome repro.
I have a question regarding quantization aware training. I am new in this area and want to know if you can share example to do quantization aware training for …
-
以MinMaxObserver, asymmetric模式为例,不论是PTQ还是QAT,当我们打开pot_scale设置时,scale经过pot_quantization之后,他的值发生了变化,我们是不是也应该相对应的同步修改zero_point得值才对
-
您好,我在读本实验论文的时候发现论文中提到了`calibration data`这个概念,这是不是意味着复现代码数据集不是原本的1k的imagenet数据集,我在哪里可以找到这个数据集呢?谢谢。
-
### 🐛 Describe the bug
I want to do qat (quantized aware training) with the following model, but I met the errors like below. In my opinion, the
```python
import torch
from torch import fx
fro…
-
### Before Asking
- [X] I have read the [README](https://github.com/meituan/YOLOv6/blob/main/README.md) carefully. 我已经仔细阅读了README上的操作指引。
- [ ] I want to train my custom dataset, and I have read the …
-
[24.08.2023 12:09:22] jasiu-rozowyczlowiek:
[24.08.2023 12:09:22] jasiu-rozowyczlowiek
-
## Bug Description
If a tensorrt calibrator implemented using TRT python API is passed to Torch-TRT compilation, it fails due to the object not being recognized.
Error :
```
============…
-
when I use PTQ of NNCF, a problem occured,
" File "D:\Software\anaconda3\envs\NNCF\lib\site-packages\onnx\__init__.py", line 40, in _save_bytes
with open(cast(str, f), 'wb') as writable:
Permi…