Shun Lu

Sorry, I did not found a solution. I needed the denseflow for the video dataset processing in Video-Swin-Transformer, but later I found that it also provided a method to process...

> > Hi, > > Thanks for the authors' nice work ! > > However, when I used the pre-defined efficientnet-b3 model, I have managed to export the onnx model...

One year has passed. Have you solved this problem?

I used to meet the same problem but I found that it may be the loss that was too large.

> This is due to that your labels aren't in the correct format. From the README: > > ``` > sudo pip install cityscapesscripts > export CITYSCAPES_DATASET= > csCreateTrainIdLabelImgs >...

> i have the same problem,when i have successfully trained my own dataset, next when I run the evaluate.py an error occurred like this: > > InvalidArgumentError (see above for...

Hello, Great thanks for your nice work. I wonder if you will release NetAdaptV2? Best, Shun Lu

> > Any update of few-shot results? > > Hi there, first, sorry for the late reply. Recently, I am doing a full-time job and am busy with work. Also,...

@Pcyslist Thanks for your constructive suggestions. I concur with you that different `edge_to_split` may yield different results as Kendall’s Tau is really sensitive according to my experience. After checking the...

@Pcyslist Sorry but I have to clarify that you might have some misunderstandings about my training. I followed the official instructions [here](https://github.com/aoiang/few-shot-NAS/tree/27b9735226f3d0a45dbe7bc3cce7c15db9b544f9/Few-Shot_NasBench201/supernet) to conduct the few-shot training rather than the...