facebookresearch / ov-seg

This is the official PyTorch implementation of the paper Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP.

facebookresearch/ov-seg Issues

Per-pixel feature extraction
Updated 2 months ago
About train on other datasets
Closed 6 months ago2
During the fine-tuning of CLIP, is the mask used generated by the previous segmentation model (with the original CLIP)?
Closed 5 months ago3
Customer dataset error: ValueError: not enough values to unpack (expected 3, got 2)
Updated 4 months ago
Can you provide the code of incorperating OVSeg CLIP w/ Segment_Anything?
Updated 5 months ago
How can we access the pre-trained models？
Updated 6 months ago
The issue with the dataset during the training process.
Updated 6 months ago1
Details about using SAM
Closed 6 months ago2
demo.py
Closed 8 months ago1
SAM+Mask_adapted CLIP
Closed 8 months ago1
Why can't support 'CLIP_ENSEMBLE_WEIGHT > 0' using 'R101c + CLIP-ViT-B/16' in demo.py
Closed 8 months ago3
Loss plots
Closed a year ago2
Reproducing the results of baseline w/ original CLIP
Closed 8 months ago1
Finetuning CLIP
Closed 8 months ago1
Release under a license for commercial use?
Closed 9 months ago2
PATH_TO_MASKADAPTED_CLIP
Closed 9 months ago3
swin_base_patch4_window12_384_22k.pkl
Closed 9 months ago3
The CLIP ViT-B/16 model
Closed a year ago5
Download data error!
Closed 10 months ago1
d2.engine.defaults]: No evaluator found. Use `DefaultTrainer.test(evaluators=)`, or implement its `build_evaluator` method.
Closed a year ago2
Use which feature to classify for demo.
Closed a year ago1
create ONNX for anylabeling
Closed a year ago1
Where is visual prompt implemented
Closed a year ago2
Code for generating training data from COCO Captions
Closed a year ago1
CLIP weights?
Closed a year ago1
FREEZE_AT parameter in config
Closed a year ago1
The training process of ovseg
Closed a year ago5
model problem
Closed a year ago1
Segmentation Problem
Closed a year ago