aureosun
aureosun
求问你最后这个解决了么
@huangjun12 @chen1234520 @cloud-zZ 您好，现在ppTSMv2 和ppTSM模型转换的过程是怎么样的，我这边有些问题 paddle2onnx --model_dir inference/PPTSMv2 --model_filename ppTSMv2.pdmodel --params_filename ppTSMv2.pdiparams --save_file ppTSMv2.onnx --enable_dev_version True [Paddle2ONNX] Start to parse PaddlePaddle model... [Paddle2ONNX] Model file path: inference/PPTSMv2\ppTSMv2.pdmodel [Paddle2ONNX] Paramters file...
@FabianHertwig I'm still have the same problem as you, how to train the model for a new dataset？and in your mediapipe？
Hey Zehaos, I have trained mobilenet_v1_1.0_224 with the TF-Slim Classification library,but I when I tried to train mobilenet_v1_0.25_128,I find the code in Slim not work.Have you ever trained it? @Zehaos
@wywdahai 请问您后面这个是怎么解决的
@SAIL-LAB155 请问最后解决了么
[ppTSMv2.zip](https://github.com/Tencent/ncnn/files/9443058/ppTSMv2.zip) [ppTSMv2-sim.zip](https://github.com/Tencent/ncnn/files/9443088/ppTSMv2-sim.zip)
@wzyforgit 多谢，已经解决
@dandingbudanding 请问多张图输入应该怎么搞，最近再做视频方面的事情，需要处理多图输入，想咨询一下，多谢
@754467737 大佬，这部分pp-tsm转onnx使用这个工具怎么搞呀，从pytorch切过来几天不知道咋搞？求助