-
## 🚀 新功能/Feature
目前PaddleDetection已经有QAT量化方式,希望引入PTQ量化方式。
## 需求原因&示例/Motivation & Examples
正在进行应急场景下的目标检测项目,在无人机场景下进行目标检测模型部署,需要尽可能减小模型大小、提升模型推理速度。
目前已经测试了QAT量化,希望能够引入PTQ量化,特别是PaddleSlim的动态…
-
### 请提出你的问题
### 版本:
paddle-bfloat 0.1.7
paddle2onnx 1.0.0
paddlefsl 1.1.0
paddlehub 2.3.0
paddlenlp …
-
### 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 …
-
我在调试imagenet_example下的PTQ代码时,尝试使用AdaRound对Resnet18和Mobilenetv2进行后量化,均遇到了KeyError的问题,代码都是MQBench自带的代码,我没有动过。
AdaRound on MBV2:
![image](https://user-images.githubusercontent.com/26295078/167986557-35…
-
在我理解中,QAT应该是包含QAFT的?求解答
wmkai updated
2 years ago
-
I am using the following command at,
.../neural-compressor/examples/pytorch/image_recognition/torchvision_models/quantization/ptq/cpu/ipex/
python main.py -t --ipex -a mobilenet_v2 --pretrained /da…
-
code
```python
B = int(windows.shape[0] / (H * W / window_size / window_size))
```
error
```
TypeError: int() argument must be a string, a bytes-like object or a number, not 'Proxy'
```
-
Post training quantization for PyTorch saves the state file (collections.OrderedDict) instead of the model files.
This prevents conversion to other frameworks like onnx post quantization.
Is there a…
-
TL;DR: the `ch_axis` of ConvTransposeReLU2d cannot be set as 1 during the PTQ, which will cause errors.
During the PTQ, if we choose the `per-channel` mode, we are supposed to set the `ch_axis` o…
-
您好,我目前所做的项目训练好的.pth格式的目标检测模型有460兆左右,希望对其进行压缩处理。请问对于训练后的模型,如.pth模型文件,可以应用您的方法对其进行压缩吗?
如果是边训练边量化,我能否在一个基于MaskRcnn的而且是斜框检测的目标检测网络中应用您的方法去实现模型的压缩呢?非常希望您能回复我的问题,万分感谢!