EVA

EVA copied to clipboard

I would like to do fine tuning of the EVA-02 Object Detection model with google colab, but the tutorial here does not allow me to do so due to google...

ryosuzaki

Where is Shinji

1

where is our beloved shinji ku???

power0341

Dear author, thanks for your excellent work. I have been trying to reproduce the performance of EVA-01 LVIS det & ins seg recently. In the table of Readme, the performance...

yhcao6

Thanks for the great work! I have extracted image features by eva_clip_psz14, but I am still looking for an advanced object detector to extract region features for downstream tasks. Thanks!

PolarisHsu

What are the differences between your paper and dBot(Exploring target representations for masked autoencoders)

gengenkai

Thanks for your great work. May you provide some examples on images where width is not equal to height. Thanks.

synsin0

Why no ViT-Adapter for semantic segmentation on ADE20K for EVA02?

5

Title says it all

tommiekerssies

Hi, Thanks for your great works! I'm currently trying to reproduce EVA-02 Pre-training stage (Vit-B, 4 nodes x 8 40GB A100) and I find it takes 13~ hours to finish...

memoiry


tommiekerssies

Hi all , @Quan-Sun , @Yuxin-CV , Thank you for this repository. I am trying to train the model using a custom dataset for instance segmentation for config : https://github.com/baaivision/EVA/blob/master/EVA-02/det/projects/ViTDet/configs/eva2_mim_to_coco/eva2_coco_cascade_mask_rcnn_vitdet_b_4attn_1024_lrd0p7.py...

rgkannan676