<Yun>

I have a similar issue but not this repo. debug MMdet-related code is almost impossible, they encapsulate everything and it is not worth the time to debug, you may use...

> maybe an typing error, btw, did you have any color difference in you experiment? i think the error is trivial and I did not observe a significant difference in...

how you generate the invoice number and also data of exposure???

nvm i solve the problem On Tue, Nov 12, 2019 at 4:09 AM Mihail Altinin wrote: > how you generate the invoice number and also data of exposure??? > >...

自己训练一个需要很久吗？别人帮你写好了代码已经很不错了。。。

> > Hi, have you solved the problem? Thanks for you reply! > > no Hi, do you mind to share your system configuration? I use 3090 and the latest...

> So when MDSR is training, the data_generator function should randomly select a scale to train the model. This feature need a custom dataloader function(See dataloader.py line 37-45). but why...

Thanks for your reply. I revisited your code and paper, and now I understand. Thanks!

I just rent an AWS instance and calculated the ZCA matrix of CIFAR10: the result is different from yours: my one(calculated based on the whole dataset, i.e. 50K images): [[...

@chunweit the PretrainModel file(not the ImageNet one) given I think is wrong: in **Experiement.py**, if you print out the model parameters: ``` encoder.encoder.conv1.weight encoder.encoder.bn1.weight encoder.encoder.bn1.bias encoder.encoder.layer1.0.conv1.weight encoder.encoder.layer1.0.bn1.weight encoder.encoder.layer1.0.bn1.bias ... ```...