Chen Ma

How to fix the CUDA out of memory error when using Multi-Step Loss Optimization (MSL)?

1

Dear author: when I ran your code I found that https://github.com/AntreasAntoniou/HowToTrainYourMAMLPytorch/blob/master/few_shot_learning_system.py#L196 This line will cause the OOM error because each time the gradient of loss backprop w.r.t. the whole network's...

Does the batch dimension in roi_pooling_layer bottom[0] and bottom[1] equal?

1

in roi_pooling_layer.cpp in about line no: 78: ` const Dtype* batch_data = bottom_data + bottom[0]->offset(roi_batch_ind);` where roi_batch_ind is come from bottom_rois[0]. That means bottom conv layer's batch dim == ROI...

We have released our new research : AU R-CNN. [https://github.com/sharpstill/AU_R-CNN](https://github.com/sharpstill/AU_R-CNN) It achieves state-of-the-art AU detection performance and accuracy. For example, in BP4D 3-fold testing protocol, the result is 63% F1...

New CVPR paper for adversarial attack(Black-box attack)

1

Title : Simulating Unknown Target Models for Query-Efficient Black-box Attacks arXiv: https://arxiv.org/abs/2009.00960 (title will be changed in the revised version) Code: https://github.com/machanic/MetaSimulator Intro: We propose a method to train a...

AttributeError: 'NoneType' object has no attribute 'name' in FusedBatchNorm

3

Platform (like ubuntu 16.04/win10): ubuntu 16.04 Python version: 3.7.3 Source framework with version (like Tensorflow 1.4.1 with GPU): Tensorflow 1.4.0 Destination framework with version (like CNTK 2.3 with GPU): PyTorch...

这个框架支持深度学习的chainer框架吗？

1

chainer框架是日本做的，小巧好用，但是据我所知，并行分布式需要将梯度信息在多个机器上传输，这个框架支持这么做吗？

Very confusion. I search a lot about BP algorithm, Some notes says it is ok only to differential w.r.t. W(parameter) and use residual to get gradient ? Your example seems...

How to perform target attack using FGSM?

1

I notice that your code only have un-target attack part. But target-attack, where we can specify the target class mannually is loss/missing?

I look from introduction there is not implement in recently CycleGAN, DiscoGAN, DualGAN, Can support implement for them?

The `while True:` of https://github.com/ikostrikov/pytorch-a3c/blob/master/train.py#L35 cannot be break, because the only `break` statement is in https://github.com/ikostrikov/pytorch-a3c/blob/master/train.py#L79 which is used to break for-loop: https://github.com/ikostrikov/pytorch-a3c/blob/master/train.py#L50 How to terminate that forever while-loop in...