-
I was prompted with the following information during the training process：
Please check your arguments if you have upgraded adabelief-pytorch from version 0.0.5.
Modifications to default arguments:
…
-
### Your current environment information
Traceback (most recent call last):
File "/home/shadeform/miniconda3/envs/miner/lib/python3.10/site-packages/onediff/utils/import_utils.py", line 16, in c…
-
### 🐛 Describe the bug
Running
```
import torch
cfn = torch.compile(torch.sin, mode='reduce-overhead')
cfn2 = torch.compile(torch.cos, mode='reduce-overhead')
for _ in range(2):
x = cfn2(to…
-
### 🐛 Describe the bug
Looking at the FSDP API, I was expecting that we could use the torch meta device in conjunction with the `param_init_fn` and `sync_module_states` arguments to `FSDP` to instant…
-
### 🐛 Describe the bug
I tried to reproduce the result of ConvNeXt-Tiny's pretraining reported [here](https://pytorch.org/vision/main/models/generated/torchvision.models.convnext_tiny.html#torchvis…
-
## Environment
```bash
Collecting system information...
---------------------------------
System Environment Report
Created: 2023-08-21 17:44:51 CST
---------------------------------
…
-
# 本周完成的工作
1. 日常阅读一篇gan的文章，在网上记录了一个博客，DCGAN，BEGAN，等gan都进行了分析，但是还没写好，存在草稿里，将内容放在草稿箱里，在完成胡老师的任务之后，再进行下一次编辑。
2. 胡老师布置的CAM方法，是一个分类网络，在分类网络的最后一层中，将原来的Dense操作改为了Global average pool，我重新查看了一下几个pool，发现没有，经…
-
user@machine:/path_to/BRECQ# python main_imagenet.py --data_path /path_to/IMAGENET_2012/ --arch resnet18 --n_bits_w 2 --channel_wise --n_bits_a 4 --act_quant --test_before_calibration
You are using f…
-
## 🐛 Bug
`eig_backward` uses in-place operations, however `gradcheck` and `gradgradcheck` are happy.
Once a printing statement is introduced, an error is raised.
## To Reproduce
Simply add the…
-
### Branch
main branch (1.x version, such as `v1.0.0`, or `dev-1.x` branch)
### Prerequisite
- [X] I have searched [Issues](https://github.com/open-mmlab/mmaction2/issues) and [Discussions](https:/…