Downloads · 30 days
0
GeorgePearse/visdet-weights
visdet-weights is a object detection model from GeorgePearse. Use it when you need objects located in an image. The card lists the license as apache-2.0.
This repository contains pretrained weights for VisDet, a streamlined object detection and instance segmentation library.
Downloads · 30 days
0
Access
Public
Updated Dec 25, 2025
Repo size
20.8 GB
Likes
1
Public
Click a slice to open those files.
.pth20.8 GB · 100%
From the Hugging Face model README
This repository contains pretrained weights for VisDet, a streamlined object detection and instance segmentation library.
The weights are organized by source:
openmmlab/: Backbone weights from OpenMMLab's model zoommcls/: Classification backbone weights from MMClassificationfrom visdet.apis import init_detector
# Use HuggingFace-hosted weights
model = init_detector(
config="configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.py",
checkpoint="hf://GeorgePearse/visdet-weights/openmmlab/resnet50_msra-5891d200.pth"
)
Or in config files:
model = dict(
backbone=dict(
init_cfg=dict(
type="Pretrained",
checkpoint="hf://GeorgePearse/visdet-weights/openmmlab/resnet50_msra-5891d200.pth"
)
)
)
These weights are provided under the Apache 2.0 license, consistent with their original sources.