-
Hello, do you have RGB images and optical flow images extracted from UCF101 and HMDB51?
I have downloaded the images processed by Feichtenhofer using google colab but it seems the zip file is broken…
-
when I use distribution training on GPUs, the process ids are the same and the GPU utilization rate is zero.
![rate](https://user-images.githubusercontent.com/42733639/112492954-b1b92100-8dbc-11eb-9…
-
Thank you for your wonderful work! I have a little puzzle about the original acc of the six video models. Specifically, I run reference_ucf101.py to test original acc and get the results, i.e., {"i3d_…
-
## 🚀 Feature
Add download functionality if available to all datasets.
## Motivation
Currently, the following datasets have no option to download them directly:
- `Cityscapes`
- `Coco(Dete…
-
When i used the pretrain model of ucf101_rgb.pth, there is an error "size mismatch for new_fc.weight: copying a param with shape torch.Size([101, 1024]) from checkpoint, the shape in current model is …
-
Excuse me. I would like to ask if the accuracy 81.6% you gave on UCF101 dataset is the top1 or the top5?
Since I only have one piece of 1070Ti, my batchsize can only be set to 6.
I trained from scra…
-
hi,Dear,
glad to see the project,
but a little confused,
when I run
`bash ./list/convert_video_to_images.sh .../UCF101 5`
error
```
./list/convert_video_to_images.sh: line 2: $'\r': command no…
-
Hi,
So far,
* downloaded 30000 videos from sports 1-M dataset per category 60 videos. Then I decoded the videos grabbing up to 50 frames from each video.
* saved them exactly like UCF101 datas…
-
-
Dear Dongfeng,
I get an error as : IndexError: index 5 is out of bounds for axis 1 with size 5 when I run the program. I would be most obliged if you can help me to solve this error. Thank you