Efficient-Computing

Efficient-Computing copied to clipboard

关于实例感知动态量化神经网络的问题

1

非常感谢您分享您论文的实现代码，我想问一个比较愚蠢的问题：为什么全连接层的输出刚好就是比特候选中相应比特被选择的logits呢？

mlscsdn

How to load pretrained model for training?

xiaoyuan806

 my reconstruct res can’t see any userful information。  this is my log.txt i will appreciate for your quickly response！！

jasper-cell

【Gold-YOLO】热力图的实现。Realization of heat map。

1

如何使用gold-yolo框架实现热力图可视化呢？ How to use gold-yolo framework to realize the visualization of heat map?

Rosal-1998

Add PTQ4SR, accepeted by CVPR2023.

tuzhijun

[RPG] Regarding the accuracy measurement

4

https://github.com/huawei-noah/Efficient-Computing/issues/139#issuecomment-2165075615 I created a new issue because I can't reopen the existing issue. Hello, As mentioned in the link above, I successfully reimplemented CIFAR-10 using the best accuracy. I have...

Acasia

https://github.com/huawei-noah/Efficient-Computing/blob/master/Data-Efficient-Model-Compression/DAFL/DAFL-train.py#L179 loss_information_entropy = (softmax_o_T * torch.log10(softmax_o_T)).sum() RuntimeError: Function 'XlogyBackward0' returned nan values in its 1th output. 这里是不是会出现当softmax后概率过小或者为0的情况时，会出现nan的情况，当时你遇到过吗，如果遇到过，当时是怎么解决这个问题的。

li1changxing

No module named 'ipg_kit'

15

when i try the project IPG with this code:python exec.py --opt options/train_IPG_SR_x2.yml --eval_opt options/test_IPG_BasicSR_x2.yml --scale 2

just-dude1

作者你好，请问test数据集的文件结构是怎么来的，我下载的文件并不是这样，需要自己处理吗？感谢！

BruceTao-blog

Hello, author. Could you please provide the parameters of your SOTA model? I intend to cite IPG in my thesis. The parameter quantity of the x4 magnification I measured is...

gitlonglong