Real-time Joint Semantic Reasoning for Autonomous Driving
关键参数与规格
关键参数与规格
参数
值
语言
Jupyter Notebook
类别
Model Development
子类别
Deep Learning Frameworks
关键词
Computer vision, Object detection
星标数
558
分叉数
71
贡献者
1
创建日期
2018-03-07
更新日期
2026-10-06
1 天星标数
0
7 天星标数
0
排名
17,065
上次排名
16,856
排名变化
-209
7 天星标排名
15,889
上次 7 天星标排名
15,894
7 天星标排名变化
5
总星标排名
17,787
上次总星标排名
17,753
总星标排名变化
-34
README 摘录
Detectorch - detectron for PyTorch (Disclaimer: this is work in progress and does not feature all the functionalities of detectron. ) This code allows to use some of the Detectron models for object detection from Facebook AI Research with PyTorch. It currently supports: Fast R-CNN Faster R-CNN Mask R-CNN It supports ResNet-50/101 models with or without FPN. The pre-trained models from caffe2 can be imported and used on PyTorch. Example Mask R-CNN with ResNet-101
and FPN. Evaluation Both bounding box evaluation and instance segmentation evaluation where tested, yielding the same results as in the Detectron caffe2 models. 6 | | 36224046 | | fast_rcnn_R-50-FPN_2x | 36. 8 | | 36225249 | | e2e_faster_rcnn_R-50-C4_2x | 36. 5 | | 35857281 | | e2e_faster_rcnn_R-50-FPN_2x | 37. 9 | | 35857389 | | e2e_mask_rcnn_R-50-C4_2x | 37. 8 | 35858828 | | e2e_mask_rcnn_R-50-FPN_2x| 38. 5 | 35859007 | | e2e_mask_rcnn_R-101-FPN
_2x | 40. 4 | 35861858 | Training Training code is experimental. Installation First, clone the repo with so that you also clone the Coco API. Other required packages torchvision ( ) opencv ( ) cython ( ) matplotlib ( ) scikit-image ( ) ninja ( ) *(required for Pytorch 0. 4 only)* Additionally, you need to build the Coco API and RoIAlign layer. Compiling the Coco API If you cloned this repo with you should have also cloned the cocoapi in . Compile this with: Compiling RoIAlign The RoIAlign layer was converted from the
caffe2 version. There are two different implementations for each PyTorch version: Pytorch 0. 4: RoIAlign using ATen library (lib/cppcuda). 1: RoIAlign using TH/THC and cffi (lib/cppcuda_cffi). Needs to be compiled with: Quick Start Check the demo notebook.
常见问题
记录了多少星标和分叉？
ignacio-rocco/detectorch 有 558 个星标和 71 个分叉。
仓库排名是多少？
ignacio-rocco/detectorch 排名第 17,065。
记录的语言和类别是什么？
ignacio-rocco/detectorch 有 558 个星标，语言为 Jupyter Notebook，类别为 Model Development。
(Disclaimer: this is work in progress and does not feature all the functionalities of detectron. Currently only inference and evaluation are supported -- no training)
(News: Now supporting FPN and ResNet-101!)
It supports ResNet-50/101 models with or without FPN. The pre-trained models from caffe2 can be imported and used on PyTorch.
Example Mask R-CNN with ResNet-101 and FPN.
Evaluation
Both bounding box evaluation and instance segmentation evaluation where tested, yielding the same results as in the Detectron caffe2 models. These results below have been computed using the PyTorch code:
