-
### 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。
- [X] I want to train my custom dataset, and I have read the …
-
Does Minicpmv2.6 currently support int8/fp8 quantization?
thanks~
-
# PaddleSlim量化
PaddleSlim主要包含三种量化方法：量化训练(Quant Aware Training, QAT)、动态离线量化(Post Train…
-
b'j\x8d\xf2\xf1\xab\x95\x06\xd4\x0f\x95\xc6\x1f\xe7\xf3i\xc17Z\x04\x82
-
Hi Team,
Thanks for the great tool for model compression research.
As it is stated that you guys are planning to add PTQ or capability to export the quantized model to ONNX, would be greatly in…
nik13 updated
4 years ago
-
hi你好，我在使用ptq后得到了量化模型，我也开启了onnx_format，但在paddle2onnx的过程中遇到如下报错：
请问怎么才能让他生成对应的量化校准表呢，非常感…
-
您好，我在量化RepVGG到INT8时遇到一些问题：
完全按照您在README中提到的量化流程，先插入BN后QAT量化，掉点非常严重。以大模型（b3g4）为例，在ImageNet分类任务上量化后仅有20左右的accuracy。
但假如将https://github.com/DingXiaoH/RepVGG/blob/ce669bad170bf5d7c2a9eb060e90f39e7e10913…
-
**Is your feature request related to a problem? Please describe.**
Google coral sicks can be used to do Deep learning tasks .
Here we have to folow coral tutorials to do :
![image](https://user-ima…
-
**Describe the bug**
非常痛苦 动态shape根本转不出来
**To Reproduce**
```python
import nncase
import numpy as np
import onnx
import onnxsim
# from nncase_base_func import model_simplify, read_model_fil…
-
Firstly, thanks to all of you for the bravo project!
Currently, the model seems like does not support int8 quantization. Any plan on it?