-
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…
-
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:X64 Nvidia V100s
- 版本号/Version:Paddle:2.3.1 PaddleOCR:release 2.5 2909454fb121a…
-
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:cuda 11.2 cudnn:8.2.0 python 3.9
- 版本号/Version:Paddle:2.4.1 PaddleOCR: 问题相关组件/R…
-
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:
- 版本号/Version:Paddle: PaddleOCR: 问题相关组件/Related components:
- 运行指令/Command Cod…
-
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/…
-
se_cf in the mobilenetV3, what does this bias mean, only keep an activation function on the line, otherwise it reports an error
-
FastDeploy 版本:预编译版 0.6.0
OS:macOS 12.6 (Arm64)
语言:C++
模型:rvm_mobilenetv3_fp32.onnx
推理方式:CPU
编译运行 infer_demo,并使用固定的参数(CpuInfer) 。测试发现,经常出现这个异常(并不是每次)。
请问大致会是什么原因?
-
### 请提出你的问题 Please ask your question
[2023/05/05 11:14:23] ppocr INFO: Architecture :
[2023/05/05 11:14:23] ppocr INFO: Models :
[2023/05/05 11:14:23] ppocr INFO: Student :
[2023/05…
-
微博内容精选
-
将CRNN的backbone更换为了VGG,跑通后训练了很久acc一直很低,loss也不怎么下降,这种情况下一步应该考虑是什么问题?主干网络在宽高上是否有其他的限制呢?
![image](https://user-images.githubusercontent.com/58280508/190101066-09536912-2cde-4609-8bb3-f0cb01110e35.png)
!…