LiUzHiAn

python -m jittor.test.test_cudnn_op failed

4

Hi, thanks for your great work! When I try to install Jittor with CUDA enabled, the following problem was raised. I'd appreciate it if you can give me some ideas...

Hi, When I tried to resume the training process, I was told that `'initial_lr' is not specified in param_groups[0] when resuming an optimizer`. So, I guess we have to feed...

The running speed on 3090 is much slower than 2060

18

Hi I install the `tsnecuda` in two machines, the first is `RTX 2060 GPU, cuda10.0, python 3.6`, the second is `RTX 3090 GPU, cuda11.0, python 3.6`. I tested the performance...

Set5 test set evaluation result

6

Hi, I used the model you pretrained with 200 epochs and evaluated the model on Set5 test set. But I only got ~25.5 average PSNR which is somewhat poor. Anybody...

Hi, there is a bug in ColorJitter as posted in issue #8. I've fixed here.

Hi, 在这里推荐一个偏底层的项目——[从零实现一个toy DBMS](https://github.com/LiUzHiAn/simpleDB-gitbook)。 这是“Database Design And Implementation”书中的核心内容，这个项目可以真正熟悉并掌握数据库中的大量原理和技术，我在学习的同时将原作翻译成了中文。

A question about memory initialization.

1

Hi, I am a bit confused about how we save memory states in DNC. To be more specific, at the starting point of training, we have to initialize the memory...

@kdrivas Hi, Thanks for sharing your great work. As I dive into the details of the code, I seem to find some potential issues or bugs for which I want...

工程伦理在刷某个视频时阻塞

2

有的视频一直卡着... ``` 6.3 建设管理人员的职业伦理，尚未学习，现在开始自动学习 {} 学习进度为：19.71%/100% last_point: 1000 {} 学习进度为：20.11%/100% last_point: 2000 {} 学习进度为：40.31%/100% last_point: 3000 {} 学习进度为：40.71%/100% last_point: 4000 {} 学习进度为：60.91%/100% last_point: 5000 {"message":"Partial data anomaly","code":200,"data":{}} 学习进度为：60.91%/100% last_point: 6000...

@jhaux hi, I am a little bit confused about the function of `channel_norm` layer. Specifically, in class `ZConverter`,after sampling from the latent space, why you use the channel_norm layer to...