facebookresearch/hiera

Issues

• Does this repo fix the bug from "WINDOW ATTENTION IS BUGGED" ?

  #36 opened a month ago by tcourat
  1

• COCO pretrained weights

  #35 opened 2 months ago by tkhe
  0

• Training scripts

  #28 opened 7 months ago by VGrondin
  6

• Is it possible to replace the backbone from hiera to other hierarchical models like Swin Transformer or CAFormer?

  #33 opened 3 months ago by Andy-Ko-0620
  5

• Hiera available on 🤗 Transformers!

  #34 opened 3 months ago by EduardoPach
  3

• n_output_channels

  #32 opened 4 months ago by liushawn618
  14

• hiera_mae returns the feature map from the last layer.

  #31 opened 4 months ago by tapohongchen
  5

• Video pretrained checkpoints with 8 frames?

  #24 opened 10 months ago by MLDeS
  2

• Pretrained Weights for Something Something V2

  #30 opened 5 months ago by edessa
  0

• Table 13. Settings for AVA. learning rate=3.6?

  #27 opened 7 months ago by justzhanghong
  2

• inference guide for ava.v2.2 dataset

  #20 opened a year ago by faezehprb
  1

• Visualizing MAE predictions?

  #17 opened a year ago by Wiqzard
  3

• Release of models for COCO object detection and segmentation

  #18 opened a year ago by hector-gr
  2

• Request for training script

  #13 opened a year ago by omchakrabarty
  5

• Doubt regarding Batch Size

  #22 opened a year ago by owaisCS
  2

• Changing the temporal dimension

  #23 opened a year ago by MLDeS
  0

• how to change number of classes from kinetics to other multiclass dataset?

  #21 opened a year ago by mbilalshaikh
  1

• When will release mae pretrained weights?

  #14 opened a year ago by shi-lt
  8

• Adding position embedding to the intermediate hiera features

  #19 opened a year ago by MLDeS
  1

• Hiera for Feature extraction

  #4 opened a year ago by mbilalshaikh
  6

• How to save the model ? Since the training code has not been released yet , So I want to train the model myself. I am wondering how should I save the model correctly. Looking forward to your reply!

  #16 opened a year ago by sulizhi
  2

• In the inference.ipynb, each video is extracted to a length of 5s, but how to deal with if the video sizes are different and some videos are short than 5s?

  #15 opened a year ago by sulizhi
  2

• How fine-tune the model?

  #12 opened a year ago by SalvatoreRa
  1

• Getting error with Hiera Inference (Image)

  #11 opened a year ago by sudhir2016
  4

• When will release hiera_small_16x224 pretrained weights?

  #10 opened a year ago by junwenxiong
  1

• How do we drop tokens?

  #5 opened a year ago by luke-mcdermott-mi
  2

• Example notebook for video task

  #7 opened a year ago by itsprakhar
  1

• comparision with yowo model

  #8 opened a year ago by ChethanN01
  1

• temporal action recongnition

  #9 opened a year ago by ChethanN01
  0

• Typo in Readme

  #6 opened a year ago by luke-mcdermott-mi
  1

• Nice work! Look forward to the pre-training code!

  #3 opened a year ago by youcaiSUN
  0

• Weird inference time

  #1 opened a year ago by alexcbb
  3

• Add keypoint detection

  #2 opened a year ago by vincentmin
  0