文末有福利!
前言
無論是做計算機視覺還是做自然語言處理,無論是做傳統的機器學習還是做深度學習,都會免不了和機器學習庫打交道,其中就有numpy、tensorflow、scipy、keras、matplotlib等,如果我們想使用一項功能,卻不知道里面有沒有該怎麼辦?去官方文檔查詢速度會很慢,而且有很多多餘的語言描述,效率必然很低,如果有一個速查表就會極大的提高效率。
此外,這幾年人工智能如雨後春筍一樣,出現了很多優秀的卷積神經網絡模型,我們該怎麼學習?該從哪裡獲取源碼和資源?這也是困擾很多人的問題,今天我們就一個一個來說一下。
資源
- cheatsheets-ai
- deep_learning_object_detection
cheatsheets-ai
- cheatsheets-ai
Github地址:https://github.com/kailashahirwar/cheatsheets-ai
- deep_learning_object_detection
Github地址:https://github.com/hoya012/deep_learning_object_detection
圖中標紅的是作者認為必讀的文章,涉及R-CNN、OverFeat、SSD、YOLO等計算機視覺領域優秀的網絡模型。
整理了從2014年到2019年之間的所有計算機視覺領域優秀的文章。
2014 年
R-CNN
Rich feature hierarchies for accurate object detection and semantic segmentation | Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik | [CVPR’ 14]
https://arxiv.org/pdf/1311.2524.pdf
代碼 Caffe:
https://github.com/rbgirshick/rcnn
OverFeat
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks | Pierre Sermanet, et al. | [ICLR’ 14]
https://arxiv.org/pdf/1312.6229.pdf
代碼 Torch:
https://github.com/sermanet/OverFeat
2015 年
Fast R-CNN
Fast R-CNN | Ross Girshick | [ICCV’ 15]
https://arxiv.org/pdf/1504.08083.pdf
代碼 caffe:
https://github.com/rbgirshick/fast-rcnn
Faster R-CNN
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks | Shaoqing Ren, et al. | [NIPS’ 15]
https://papers.nips.cc/paper/5638-faster-r-cnn-towards-real-time-object-detection-with-region-proposal-networks.pdf
代碼 caffe:
https://github.com/rbgirshick/py-faster-rcnn
代碼 tensorflow:
https://github.com/endernewton/tf-faster-rcnn
代碼 pytorch:
https://github.com/jwyang/faster-rcnn.pytorch
2016 年
OHEM
Training Region-based Object Detectors with Online Hard Example Mining | Abhinav Shrivastava, et al. | [CVPR’ 16]
https://arxiv.org/pdf/1604.03540.pdf
代碼 caffe:
https://github.com/abhi2610/ohem
YOLO v1
You Only Look Once: Unified, Real-Time Object Detection | Joseph Redmon, et al. | [CVPR’ 16]
https://arxiv.org/pdf/1506.02640.pdf
代碼 c:
https://pjreddie.com/darknet/yolo/
SSD
Single Shot MultiBox Detector | Wei Liu, et al. | [ECCV’ 16]
https://arxiv.org/pdf/1512.02325.pdf
代碼 caffe:
https://github.com/weiliu89/caffe/tree/ssd
代碼 tensorflow:
https://github.com/balancap/SSD-Tensorflow
代碼 pytorch:
https://github.com/amdegroot/ssd.pytorch
R-FCN
Object Detection via Region-based Fully Convolutional Networks | Jifeng Dai, et al. | [NIPS’ 16]
https://arxiv.org/pdf/1605.06409.pdf
代碼 caffe:
https://github.com/daijifeng001/R-FCN
代碼 caffe:
https://github.com/YuwenXiong/py-R-FCN
2017 年
YOLO v2
Better, Faster, Stronger | Joseph Redmon, Ali Farhadi | [CVPR’ 17]
https://arxiv.org/pdf/1612.08242.pdf
代碼 c:
https://pjreddie.com/darknet/yolo/
代碼 caffe:
https://github.com/quhezheng/caffe_yolo_v2
代碼 tensorflow:
https://github.com/nilboy/tensorflow-yolo
代碼 tensorflow:
https://github.com/sualab/object-detection-yolov2
代碼 pytorch:
https://github.com/longcw/yolo2-pytorch
FPN
Feature Pyramid Networks for Object Detection | Tsung-Yi Lin, et al. | [CVPR’ 17]
http://openaccess.thecvf.com/content_cvpr_2017/papers/Lin_Feature_Pyramid_Networks_CVPR_2017_paper.pdf
代碼 caffe:
https://github.com/unsky/FPN
RetinaNet
Focal Loss for Dense Object Detection | Tsung-Yi Lin, et al. | [ICCV’ 17]
https://arxiv.org/pdf/1708.02002.pdf
代碼 keras:
https://github.com/fizyr/keras-retinanet
代碼 pytorch:
https://github.com/kuangliu/pytorch-retinanet
代碼 mxnet:
https://github.com/unsky/RetinaNet
代碼 tensorflow:
https://github.com/tensorflow/tpu/tree/master/models/official/retinanet
Mask R-CNN
Kaiming He, et al. | [ICCV’ 17]
http://openaccess.thecvf.com/content_ICCV_2017/papers/He_Mask_R-CNN_ICCV_2017_paper.pdf
代碼 caffe2:
https://github.com/facebookresearch/Detectron
代碼 tensorflow:
https://github.com/matterport/Mask_RCNN
代碼 tensorflow:
https://github.com/CharlesShang/FastMaskRCNN
代碼 pytorch:
https://github.com/multimodallearning/pytorch-mask-rcnn
2018 年
YOLO v3
An Incremental Improvement | Joseph Redmon, Ali Farhadi | [arXiv’ 18]
https://pjreddie.com/media/files/papers/YOLOv3.pdf
代碼 c:
https://pjreddie.com/darknet/yolo/
代碼 pytorch:
https://github.com/ayooshkathuria/pytorch-yolo-v3
代碼 pytorch:
https://github.com/eriklindernoren/PyTorch-YOLOv3
代碼 keras:
https://github.com/qqwweee/keras-yolo3
代碼 tensorflow:
https://github.com/mystic123/tensorflow-yolo-v3
RefineDet
Single-Shot Refinement Neural Network for Object Detection | Shifeng Zhang, et al. | [CVPR’ 18]
http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Single-Shot_Refinement_Neural_CVPR_2018_paper.pdf
代碼 caffe:
https://github.com/sfzhang15/RefineDet
代碼 chainer:
https://github.com/fukatani/RefineDet_chainer
代碼 pytorch:
https://github.com/lzx1413/PytorchSSD
2019 年
M2Det
A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network | Qijie Zhao, et al. | [AAAI’ 19]
https://arxiv.org/pdf/1811.04533.pdf
我整理了計算機視覺、強化學習相關的優秀文章,優秀書籍中英文電子版、源碼等,如果需要可以關注微信公眾號"平凡而詩意",回覆相應關鍵字獲取。
閱讀更多 Lee先森的技術站 的文章