Issues
- 0
Any plans for releasing model weights of COCO-Stuff trained segmentation models with EVA-02 backbones
#146 opened by ankuPRK - 0
- 0
Is there any reason why you didn't use the EVA02 architecture for EVA-CLIP models larger than 4B?
#144 opened by stevenliu000 - 6
- 1
- 1
- 2
- 1
- 0
How to use EVA-02 detection models for inference?
#139 opened by Franklin905 - 3
Inference Code for Detection Model
#101 opened by mmaaz60 - 1
- 0
- 0
Robust accuracy on ObjectNet dataset.
#136 opened by sunrise6513 - 0
CUDA out of memory when inference
#134 opened by zhaozhen2333 - 8
About export model
#117 opened by Egorundel - 1
Under the same validation set, the evaluation results of the EMA model after loading are inconsistent with those during training.
#133 opened by FriedaSmith - 8
- 5
Training loss is unstable
#125 opened by Kizna1ver - 0
- 1
How to convert class id to class name
#129 opened by huijiang2486 - 0
Pooling strategy
#130 opened by mactavish91 - 1
how to get the hidden features by api code?
#126 opened by hardlipay - 0
Ripple-like Artifacts on Mask Surfaces with EVA Model
#128 opened by asdlkjw - 2
Cannot find Evaluation Metrics on LVIS
#123 opened by FrancoisPorcher - 3
- 0
Augmentation on EVA02
#106 opened by xiaoxin83121 - 0
About post normalization
#124 opened by HJYao00 - 0
Issue with Detectron2 and CUDA
#121 opened by FrancoisPorcher - 1
- 0
- 1
the .sh script of Evaluate the fine-tuned EVA (336px, patch_size=14) on ImageNet-1K val with a single node (click to expand) can not execute.
#118 opened by peter-ni-noob - 2
- 0
EVA-01 and EVA-02
#116 opened by Egorundel - 0
- 0
deepspeed can not work
#114 opened by shuowoshishui - 0
- 0
Deep speed not supported in Windows.
#112 opened by JeavanCode - 2
- 0
- 1
Where is Shinji
#110 opened by power0341 - 0
Performance of LVIS det & ins seg
#108 opened by yhcao6 - 0
How to use EVA-01/02 to extract region features?
#105 opened by PolarisHsu - 0
What are the differences between your paper and dBot(Exploring target representations for masked autoencoders)
#104 opened by gengenkai - 0
- 5
- 1
- 0
Pre-training time of EVA02
#100 opened by memoiry - 0
Student outperforms teacher, but student is fine-tuned with a larger resolution, is that fair?
#99 opened by tommiekerssies - 0
- 0
add negative samples when training
#98 opened by Jubbuuliiing