-
As reported in the paper of ECO, pretrained 2D BNInception and 3D resnet-18 models on Kinetics dataset are not enough to get a good result, training the ECO model for another 10 epochs on Kinectics wo…
-
At test_configs/I3D_RGB/i3d_kinetics400_3d_rgb_inception_v1_seg1_f64s1.py, I find out the mean and std is
` img_norm_cfg = dict(
mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], t…
-
Using the `demo_interference.py` works fine for me.
However, when using the script `demo_3d_interference.py` the error `TypeError("forward() got an unexpected keyword argument 'flip_test'")` occurs…
-
I am grateful for your works first. I get some problems when I load pretrained model file to R(2+1)D model. I used this command:
```
python main.py --root_path ../ --video_path ucf101_videos/jpg --a…
-
With pytorch0.3.0 and python3,
I am trying the validation.py with provided pre-trained resnet50/101 ckpts, to see its performance on kinetics validation set, and I got the zero accuracy, here is the…
-
Hello. Thanks for the awesome paper. I would like to know if you had experimented with other backbones such as ResNet based architectures instead of Global pool former ?
-
Hi,
I tried to reproduce table 8 without pre-trained ResNet-50 weights of xiao2018simple.
My training command is `python train.py --amp --gpu 0 --cfg ../assets/yaml/3dpw_crowd.yml`
and the config…
-
My structure of data directories is the following:
/data
…………/UCF_jpg
……………………/(directories of class names)
………………………………/(directories of video names)
…………………………………………/(jpg files)
…………/result
…
-
Traceback (most recent call last):
File "D:\Moore-AnimateAnyone\Moore-AnimateAnyone-for-windows\venv\lib\site-packages\gradio\routes.py", line 488, in run_predict
output = await app.get_blocks…
-
Hey thanks for the repo!! Can you share the pretrained model if its possible for you. Otherwise atleast share the link to download dataset.
Thank You.