Issues
- 8
- 2
loading radio_v2.5-h from huggingface
#95 opened by gaowei724 - 4
AM-RADIO 2.5 ViT-H ?
#78 opened by javiabellan - 0
Thank you for your excellent work! Excuse me, how can the radio_v2.5-l model achieve the running speed of the e-radio_v2.1 model?
#93 opened by tianyi-1349 - 3
- 5
quick question about resolution
#89 opened by CoinCheung - 6
Fine-tuning on downstream tasks directly
#84 opened by githubiubiu - 0
Worth updating default norm arg of intermediate layer features to be consistent with DINOv2?
#87 opened by Nik-V9 - 8
- 4
RADIO with lora
#83 opened by aries-young - 16
Use RADIOV2 as VLM's vision encoder.
#60 opened by echo840 - 2
SAM COCO decoder
#82 opened by kav-hareichert - 3
- 3
Training / Tuning the model
#79 opened by paul-mdt - 3
Making sense of feature dimensions
#80 opened by OasisArtisan - 16
Reproducing mmseg/ade20k results
#73 opened by collinmccarthy - 5
Replace the clip with radio
#68 opened by StuHude - 2
How is `max_resolution` used?
#74 opened by collinmccarthy - 6
Will the training code get released?
#10 opened by hanjianhua44 - 1
LLaVA questions
#69 opened by DiWHNJ - 4
Interpretation of Feature Layers
#67 opened by mfischer-ucl - 2
is there an adaptor for SAM?
#65 opened by haoxiangzhaotju - 3
ModuleNotFoundError: No module named 'transformers_modules.RADIO.enable_cpe_support'
#66 opened by TuuSiwei - 4
Other pre-trained E-RADIO variants?
#62 opened by collinmccarthy - 3
Problems of using RADIO in LLAVA setting.
#15 opened by weiwei0224 - 4
onnx export
#59 opened by GallonDeng - 1
Include Stable Diffusion into AM-RADIO ?
#61 opened by javiabellan - 3
- 1
Inference code?
#57 opened by echo840 - 2
Feature map visualization
#58 opened by icekang - 3
Per-pixel features
#55 opened by SimonGeb - 3
- 3
What is the rtx-translate adaptor?
#40 opened by javiabellan - 3
larger-scale radio models
#44 opened by yeezhu - 3
radio-v2 update
#30 opened by PinxueGuo - 4
Problem with zero-shot image classification
#16 opened by happychow001 - 2