-
Steps to reproduce:
1. Open https://tensorflow.github.io/tfjs/e2e/benchmarks/local-benchmark/index.html
2. Choose `MobileNetV3` and `wasm` backend, click `Test correctness`.
Expect `Prediction m…
qjia7 updated
2 years ago
-
Hello, When I try to export the PyTorch model as an ONNX model with accuracy of FLOAT16, in the ONNX structure diagram, the input is float16, but the output is still float32, as shown below, and an er…
-
背景：在参加飞桨中文轻量级文字识别大赛，使用配置文件rec_chinese_lite_train_v2.0.yml，在ai-stidio可以正常训练，到24epoch左右acc有0.39左右；但是自己服务器上配置飞桨环境，训练了很多次，500epoch后acc只有0.005左右。
同时，我又在自己服务器上试过rec_chinese_common_train_v2.0.yml，是可以正常训练的。
…
-
I was able to use the weights 2 hours ago, I changed computer, now when I try to use the model as:
model = mobilenetv3.MobileNetV3Large100(pretrained="miil_21k")
>>>> No pretrained available, mo…
-
Hi, In **PaddleOCR**, inappropriate dependency versioning constraints can cause risks.
Below are the dependencies and version constraints that the project is using
```
shapely
scikit-image
imga…
-
环境:ubuntu18 python3.7 paddle版本 2.2.2 paddleclas版本 release-2.4
GPU有多个2080Ti，但运行eval.py时应该只调用了第一个GPU
同样的环境同一时间连续2次运行python tools/eval.py -c ./ppcls/configs/ImageNet/MobileNetV3/MobileNetV3_large_…
-
这个是报的错
这个是配置文件的截图
![image](https://user-images.githubusercontent.com/81000191/18762…
-
train的准确率很高，但是val的非常低，数据集是ICDAR2015
训练命令
`python3 -m paddle.distributed.launch --log_dir=./debug/ --gpus '0' tools/train.py -c /home/cat/Desktop/PaddleOCR-release-2.4/configs/rec/rec_icdar15_tra…
-
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
- 系统环境/System Environment：window、 python3.9
- 版本号/Version：Paddle：2.2.1 PaddleOCR： 2.4
- 问题相关组件/Rela…
-
padddleslim使用的develop版本
paddle版本是paddle2.4rc0
自动化压缩使用的是PaddleSlim-develop/example/auto_compression/image_classification/run.py
配置文件是PaddleSlim-develop/example/auto_compression/image_classification/…