vtddggg

A mistake in the code

1

when I run `sh val_imagenet_full.sh` An error happened. `NameError: name 'inceptionv3_spg' is not defined` I saw you define `inception3_spg` in `models/google/inception3_spg.py` So [here](https://github.com/xiaomengyc/SPG/blob/5e6debdcb059d7d001174d7ae3fbff2202ae77ec/scripts/val_imagenet_full.sh#L10) the `--arch` should be `inception3_spg`

How to finetune on larger input image size？

6

If I pre-train Swin-T for 224 input image size. How can I finetune it and get Swin-T for 320 input image size? In your paper, you claimed 384^2 input models...

您好，模型下载链接失效了

4

如题，可否提供一个新的，麻烦了，谢谢！

Question about "ApexScaler_SAM"

1

I found you have implemented a SAM-based ApexScaler in [here](https://github.com/NVlabs/FAN/blob/6467085dbc6a410a616e17a36fdfa375d21770bc/utils/scaler.py#L10) Is it useable now? Can we use this SAM-based ApexScaler to train FAN?

Linear prob evaluation on ImageNet

4

Thanks for your wonderful work! I have some questions about linear prob evaluation on ImageNet: 1) how do you conduct linear prob evaluation on ImageNet? using `sklearn.linear_model.LogisticRegression` or finetuning fc...

the GPU consumption trained on ImageNet

15

when training on 1000 classes imagenet, the GPU memory of prompts seems very large and results in the Out Of Memory error on 16GB GPU Card. How to solve this...

Hello Leslie Rice and Eric Wong, Congratulations on your significant work！！ I found the model is always set to `training` mode during adversarial training period. However, I think when we...

For training from scratch, do I need to download all 100M videos clips?

2

Are there any pre-extracted features of 100M video clips provided for training? If not, I think I must download all videos after submit this [form](https://forms.gle/hztrfnFQUJWBtiki8)..., and then extract features using...

Get errors when running at 26

1

Hello Shashank Kotyan, Nice work and helpful code for me! It seems that some error happens when run `run_evolution.py` I got `AttributeError: 'dict' object has no attribute 'graph'`, when the...

Some questions about your code

2

Thank you for sharing!! I found that you get `color_image` through bluring : `batch_colors = np.array([self.imageblur(ba,True) for ba in batch]) / 255.0` Bluring is a good way to get color...