faster-rcnn-pytorch-V1.0资源-CSDN文库

共148个文件

py：20个

sample：11个

md：5个

object

detection

目标检测

需积分: 50 133 浏览量 2020-07-19 14:53:47 上传评论收藏 11.21MB ZIP 举报

资源推荐

资源详情

资源评论

收起资源包目录

faster-rcnn-pytorch-V1.0 （148个子文件）

00c7b94b8ae92dd54207cc9081c07c17e1fa48 2KB

00f81235f062d3cd860265996b11984bc85b27 212B

0588407fe0b7adf18fbcdcac519825da2f8590 577B

07a49f90c7bfdb4d80143779fef2e872706763 576B

0d08e0c16ec30d2b129e2bcef769805a8e5b78 54B

0e39108475fc3ae62a16914e2abc3575aba6e6 212B

17c8573a2eb4ca0ca286610aa80847a5aa670b 2KB

17e3e14fb1e07c7bc3d0266bb00b37b21a1cad 2KB

1811e962ce874008d2ae34aed9b6683bae6afa 560B

1a189d1fca535cf43be71214f358db1d43e7a2 2KB

1b033f6d2bb10ad2e311a9ba3ad5090bfbcceb 118B

1b802a8fa950dbee71927c9727b3bacab5bcaf 577B

1fb915c677f2a9a0c67e4393ad33bf5d646b6f 577B

224a465fe3446e6723ac2c9bc196f9924d04db 2KB

2434d9655e452ee8fa7f1fbd0477c158a1d288 2KB

243e317285bd1cec8fdd4eb62678e4160ca024 576B

2443df526e5a2d4a7daa4d003070421196099c 1KB

2654370d8104cfb12db57467ded7ef567500ec 94B

2760baa9c1aec2ed81a970edb12d7dad2e7905 2KB

2847d46805e503099458e8153dfdab55e2c622 2KB

2eadab5e79c8fc51dfc67dd470cbc7938017a4 2KB

3074c69b350548efb1e77a57e43331410c9ba2 562B

311dabeaa9f3af7251d8f7a7458a0b7867db9d 158B

33dac53c15504ff119ceeda1b4f6d3944caa06 559B

36e42e9568101bddb9cffd05118c5e41cc9d94 1KB

39dabed13e4df7399f6810070671d5de60328d 575B

3a1916c99aecd41ce3fbebad1da573bc3c5845 37B

3aec41d84955951c9493f3e3af5f5b9618923e 558B

3c9bbb97bf0e0ed2a0c14524a34e8605454acb 272B

3ddf1a8a108c7ab55f464dcb9f69f1404ca5a9 1KB

43058997cef4a411b7be90d50db4d6f10f7ab9 671B

482eebd825a40e2c31b9abf3dbf4e67acb06ef 2KB

4a54416c9c36bddf035e5f6b40b59e4b5ca2c6 562B

4b0f6c6f9383a0a5740c87843b0905109de96f 576B

50d3724956500e32d5bc4a918a57db7df30100 435KB

527b71a2c1a990f905dd689136fcdd2ddc7567 3KB

52e3e2199a5476a4baf4cc958535557d8b615b 1KB

533c3b5633d72eb22c05d750041d2ca5850b2f 2KB

55028afba9d96738efbe2e57fab7fe7413ad41 561B

5732d11df498f382f7d3ad193d9fb0dec90757 2KB

5b08b33ce6b3f7c028cb198725f8f56ae373be 556B

5fbbd68c0a336772b096df055eb1fa8c6543ec 54B

625515a9076d03a7486c1c0818d4248f7bf8a2 1KB

631e5abc543a2ceba8273b8254ee87ea956049 568B

64689eec9dea443787852d99ba30dc97f42731 49B

64921067993322973aba9260091c48c26aa43f 43B

6ba25dd513c9c38887464595a64235ae4950a9 559B

700dbe93764f9b5c36f29c285a154cb52374cb 2KB

71799322878c4d4fa44c27f2bac94f8a84068e 46B

754b650cd8b8b22e0a8b1fda78f400bf41cd3b 577B

7a078ead0fea4f459a7215aa85ed34760e2ab6 1KB

7aa3a57e1893ef3e76d5fee4dd2c8bec6e090a 2KB

890a7e8651a49cd55e4ab77c667a88c4002c32 576B

8a903adde267d3f3d4a40ca43462a05df232fe 558B

8f45d243f4732221e93d99f296752c11655b51 524B

90dfc0be5a61de4850315c8969c898a7780145 574B

90ffb3c58ef169e56ac28bfe9a4aab52ae1f40 574B

95f6fd971fe18a536dcb4ae0c94a81a8e419bf 2KB

96033f1cabb980f4089c69281f42b41ca0905c 561B

99492c473487cca590fb983eed9488b79c004a 565B

9a44291475b6c04dcb39de675fba7050d33f74 562B

9a62234a761855effdc0ecbd49825ca705b8d3 53B

9e8e27590bee7e394ab8b38f110d2059d17360 560B

a4e83a14c24077990821e5faba651ad09db243 577B

aaced23be88d4f11bce5384b8465f26a6abced 575B

abcc061d98bfa4546bcfab3217a201a72841dd 54B

adcdc13bd181589e66e7cf14f41b43cc1a7162 85B

afd18ae44eca049561be1fa15119f689431778 654B

b4b9c1710cc43e4b2d64e31544cdbe584b3416 567B

b4ffdeee9afdbd6271c2a45c710ac722280ca0 575B

ba9bbfb67420c27bdb1b5e7e8f98302eb9ae3e 576B

bc5d728d5df3b0cdab51e23620ffbd66b97fe0 576B

bcfe29067c72c1f402ced74698ba9767fe80ba 574B

bf658244538fa51a16233dcafe67912ad7863f 2KB

c1b622c19478d847285c7fcde40bdbc6355b90 122B

c3d279338b8f53f4f9a64d73478b5a81f0fe06 3KB

c45218a57aed66c0530b1ab3018887a32af91b 583B

c72d92155a0624344457f0ded2209bd64b3016 2KB

cad1f197718ace67c00404bb5a508d75de7029 2KB

cfa2844b17899ada6716ce0403c97b76c3b664 621B

config 324B

d06592385d41da2ea6db30c1c74e8b9db7fdbe 57B

d15928e8de6f6b142643a1950a67dfaaa20d28 566B

d4687e7212775e23bea569f08fdd1cd7395dc3 5.34MB

d56a880ec27c4fe910db4f56714727496ff49f 710B

d70c81d7a5ffc8f15f91785b1f986e0483bdb0 11KB

d8a8f7f3a1cb804d446e8eeeafc4d4cf5ad9bb 850B

description 73B

dfeaf219f1d3387fefcec42e56eea9f4132a3e 577B

e377adb4116ed0ca85abfe5b7461c58b8d0bc0 556B

e40c7140bb4eccaf43b12137392d66693b6661 479B

e5c241f49ab1444e99ec5691b48a92aa77600b 1KB

e8282bbbb85397873faa642162ec136fce6095 566B

ead34f26ab1324d02c374db4d38a5be80c6dea 119B

eb1bb3164dbe745c157930a5eafa752a7b007c 568B

eba56d77f4c1b335f52bcd0208d62a1d9052c9 54B

ed724974c33be7e83a12d2cf7c5081b3acb591 888B

exclude 240B

f32ea1aa6b31fcbbeba5b862e31bfff5ae527c 37B

f9e3e00a4040c47844b7d4f9a49b9fff3f367d 128B

共 148 条

评论收藏

内容反馈

FightingCV

粉丝: 136
资源: 1

faster-rcnn-pytorch-V1.0

faster-rcnn.pytorch-pytorch-1.0.zip

pytorch-faster-rcnn：pytorch1.0已更新。 支持CPU测试和演示。 （使用detectron2，这是一个杰作）

Faster RCNN pytroch代码

Python-用PyTorch实现FasterRCNN

fast-rcnn.pytorch：更快的r-cnn的更快的pytorch实现

voc-weights-resnet.pth

使用faster-rcnn-tf 对voc2007数据集进行40000次迭代获得模型

se_resnet50-ce0d4300.pth

voc_weights_resnet.zip

faster-rcnn-pytorch-master[附带预训练权重可迁移学习].zip

faster_rcnn_pytorch

PyTorch-Faster-RCNN:基于pytorch的faster rcnn实现

pytorch-faster-rcnn:基于pytorch的实现更快的rcnn

faster-rcnn-pytorch:python pytorch faster-rcnn 目标检测 简单 零基础

simple-faster-rcnn-pytorch:更快的R-CNN

Win10 faster-rcnn pytorch1.0入坑记录及数据集准备

Python-用PyTorch10实现FasterRCNN和MaskRCNN比Detectron快2倍

Faster-RCNN pytorch1.0，vgg16-caffe.pth和resnet101-caffe.pth

PyTorch 1.0新特性摘要

yolact权重下载yolact_plus_base_54_800000.pth

faster-rcnn在CUDA8.0环境下编译caffe

VOC和COCO的训练权重

voc_weights_resnet.pth

resnet101_faster_rcnn_final.zip

深度学习领域faster-rcnn算法在小麦头目标检测（带数据集）-7、pytorch-starter-fasterrcnn

simple-faster-rcnn-pytorch：Faster R-CNN的简化实现，可从原始纸中复制性能

classification-faster-rcnn-pytorch.rar

目标检测算法-faster-rcnn-pytorch-master.zip

simple-faster-rcnn-pytorch-master.rar

simple-faster-rcnn-pytorch-master_pytorch_simplefasterRCNN_simpl

最新资源

pytorch-faster-rcnn：pytorch1.0已更新。支持CPU测试和演示。（使用detectron2，这是一个杰作）

faster-rcnn-pytorch:python pytorch faster-rcnn 目标检测简单零基础