yolov--11--YOLO v3的原版训练记录、mAP、AP、recall、precision、time等评价指标计算
Yolov-1-TX2上用YOLOv3训练自己数据集的流程(VOC2007-TX2-GPU)
Yolov--2--一文全面了解深度学习性能优化加速引擎---TensorRT
Yolov--3--TensorRT中yolov3性能优化加速（基于caffe）
yolov-5-目标检测：YOLOv2算法原理详解
yolov--8--Tensorflow实现YOLO v3
yolov--9--YOLO v3的剪枝优化
yolov--10--目标检测模型的参数评估指标详解、概念解析
yolov--11--YOLO v3的原版训练记录、mAP、AP、recall、precision、time等评价指标计算
yolov--12--YOLOv3的原理深度剖析和关键点讲解
14、Detectron-e2e_mask_rcnn_R-101-FPN_2x_gn
训练：
CUDA_VISIBLE_DEVICES='8,9' python tools/train_net.py --cfg experiments/e2e_mask_rcnn_R-101-FPN_1x-train1999-2gpu.yaml OUTPUT_DIR e2e_mask_rcnn_R-101-FPN_1x-train1999-2gpu/ | tee visualization/e2e_mask_rcnn_R-101-FPN_1x-train1999-2gpu-start8-21-1620-833-500-1.log测试：
13、Detectron-e2e_mask_rcnn_R-50-FPN_2x_gn
训练：
测试：
12、Detectron-e2e_faster_rcnn_R-101-FPN_1x
训练：
CUDA_VISIBLE_DEVICES='6,7' python tools/train_net.py --cfg experiments/e2e_faster_rcnn_R-101-FPN_1x-train1999-2gpu.yaml OUTPUT_DIR e2e_faster_rcnn_R-101-FPN_1x-train1999-2gpu/ | tee visualization/e2e_faster_rcnn_R-101-FPN_1x-train1999-2gpu-start8-21-1520-833-500-1.log测试：
CUDA_VISIBLE_DEVICES=6 python tools/test_net.py --cfg experiments/e2e_faster_rcnn_R-101-FPN_1x-train1999-2gpu.yaml TEST.WEIGHTS e2e_faster_rcnn_R-101-FPN_1x-train1999-2gpu/train/voc_1999_train\:voc_1999_val/generalized_rcnn/model_final.pkl NUM_GPUS 1 | tee visualization/e2e_faster_rcnn_R-101-FPN_1x-train1999-2gpu-test_net-1.log
11、Detectron-e2e_faster_rcnn_R-50-FPN
训练：
CUDA_VISIBLE_DEVICES='6,7' python tools/train_net.py --cfg experiments/tutorial_2gpu_e2e_faster_rcnn_R-50-FPN-train1999.yaml OUTPUT_DIR tutorial_2gpu_e2e_faster_rcnn_R-50-FPN-train1999/ | tee visualization/tutorial_2gpu_e2e_faster_rcnn_R-50-FPN-train1999-start8-21-1355-2gpu-833-500-1.log测试：
10、tiny-v3-a-voc1999
https://blog.csdn.net/chengyq116/article/details/83213699
注意：测试计算map时区分val.txt与test.txt ，差别较大，在2-4%
训练：
./darknet detector train cfg/voc1999.data cfg/yolov3-tiny-voc1999.cfg yolov3-tiny.conv.22 -gpus 8,9 | tee visualization-tiny-v3-a-voc1999-2/tiny-v3-a-voc1999-bach64-16-2lei-train723-val181-itera8000-start2019-8-22-2050-1.log./darknet detector train cfg/voc1999.data cfg/yolov3-tiny-voc1999.cfg yolov3-tiny.conv.22 -gpus 6,7 | tee visualization-tiny-v3-a-voc1999-iter8000-mixup=1/tiny-v3-a-voc1999-bach64-16-2lei-train723-val181-itera8000-start2019-8-24-0110-mixup-1.log./darknet detector train cfg/voc1999.data cfg/yolov3-tiny-voc1999.cfg yolov3-tiny.conv.22 -gpus 6,7 | tee visualization-tiny-v3-a-voc1999-iter8000-angle=1/tiny-v3-a-voc1999-bach64-16-2lei-train723-val181-itera8000-start2019-8-24-0140-angle-1.log./darknet detector train cfg/voc1999.data cfg/yolov3-tiny-voc1999.cfg backup-tiny-v3-a-voc1999-iter8000--mixup-angle=1/yolov3-tiny-voc1999_last.weights -gpus 6,7 | tee visualization-tiny-v3-a-voc1999-iter12000--mixup-angle=1/tiny-v3-a-voc1999-bach64-16-2lei-train723-val181-itera12000-start2019-8-24-1810-angle-1.log./darknet detector train cfg/voc1999.data cfg/yolov3-tiny-voc1999-mixup-flip.cfg yolov3-tiny.conv.22 -gpus 8,9 | tee visualization-tiny-v3-a-voc1999-iter8000-mixup-flip-1/tiny-v3-a-voc1999-bach64-16-2lei-train723-val181-itera8000-mixup-flip-start2019-8-26-1530-1.log./darknet detector train cfg/voc1999.data cfg/yolov3-tiny-voc1999-mixup-flip.cfg backup-tiny-v3-a-voc1999-iter8000-mixup-flip-1/yolov3-tiny-voc1999-mixup-flip_last.weights -gpus 8,9 | tee visualization-tiny-v3-a-voc1999-iter8000-mixup-flip-1/tiny-v3-a-voc1999-bach64-16-2lei-train723-val181-itera8000-mixup-flip-start2019-8-26-1530-2.log./darknet detector train cfg/voc1999.data cfg/yolov3-tiny-voc1999-mixup-flip.cfg yolov3-tiny.conv.22 -dont_show -gpus 8,9 | tee visualization-tiny-v3-a-voc1999-iter10000-mixup-flip-1/tiny-v3-a-voc1999-bach64-4-2lei-train723-val181-itera10000-mixup-flip-start2019-8-27-1050-1.log./darknet detector train cfg/voc1999.data cfg/yolov3-tiny-voc1999-mixup-flip.cfg backup-tiny-v3-a-voc1999-iter10000-mixup-flip-1/yolov3-tiny-voc1999-mixup-flip_last.weights -dont_show -gpus 8,9 | tee visualization-tiny-v3-a-voc1999-iter10000-mixup-flip-1/tiny-v3-a-voc1999-bach64-4-2lei-train723-val181-itera10000-mixup-flip-start2019-8-27-1050-2.log
计算map：
./darknet detector map cfg/voc1999.data cfg/yolov3-tiny-voc1999.cfg backup-tiny-v3-a-voc1999/yolov3-tiny-voc1999_final.weights -points 11 | tee visualization-tiny-v3-a-voc1999/tiny-v3-voc1999-bach64-4-2lei-test181-prcurves-11points-finalweights.log./darknet detector map cfg/voc1999.data cfg/yolov3-tiny-voc1999.cfg backup-tiny-v3-a-voc1999/yolov3-tiny-voc1999_9000.weights -points 0 | tee visualization-tiny-v3-a-voc1999/tiny-v3-voc1999-bach64-4-2lei-test181-prcurves-0points-9000weights.log./darknet detector map cfg/voc1999.data cfg/yolov3-tiny-voc1999.cfg backup-tiny-v3-a-voc1999-iter8000-angle=1/yolov3-tiny-voc1999_final.weights -points 101 | tee visualization-tiny-v3-a-voc1999-iter8000-angle=1/tiny-v3-voc1999-bach64-16-2lei-test181-prcurves-101points-iter8000-angle-finalweights.log./darknet detector map cfg/voc1999.data cfg/yolov3-tiny-voc1999.cfg backup-tiny-v3-a-voc1999-iter12000--mixup-angle=1/yolov3-tiny-voc1999_final.weights -points 50 | tee visualization-tiny-v3-a-voc1999-iter12000--mixup-angle=1/tiny-v3-voc1999-bach64-16-2lei-test181-prcurves-50points-iter12000-mixup-angle-finalweights.log./darknet detector map cfg/voc1999.data cfg/yolov3-tiny-voc1999-mixup-flip.cfg backup-tiny-v3-a-voc1999-iter8000-mixup-flip-1/yolov3-tiny-voc1999-mixup-flip_final.weights -points 50 | tee visualization-tiny-v3-a-voc1999-iter8000-mixup-flip-1/tiny-v3-voc1999-bach64-16-2lei-test181-prcurves-50points-iter8000-mixup-flip-finalweights.log
测试单张：
./darknet detector test cfg/voc1999.data cfg/yolov3-tiny-voc1999.cfg backup-tiny-v3-a-voc1999-2/yolov3-tiny-voc1999_final.weights scripts/VOCdevkit/VOC1999/JPEGImages/000001.jpg | tee visualization-tiny-v3-test/test-181-tiny-v3-voc1999-bach64-16-2lei-iter8000-000001-jpg-1.log批量测试：
9、yolov3-a-voc1999
训练：
./darknet detector train cfg/voc1999.data cfg/yolov3-a-voc1999.cfg darknet53.conv.74 -gpus 6,7 | tee visualization-1999/v3-a-voc1999-bach64-16-2lei-train723-val181-itera-start2019-8-19-1050-1.log./darknet detector train cfg/voc1999.data cfg/yolov3-a-voc1999.cfg darknet53.conv.74 -gpus 6,7 | tee visualization-1999-2/v3-a-voc1999-bach64-16-2lei-train723-val181-itera8000-start2019-8-21-2250-1.log计算map：
./darknet detector map cfg/voc1999.data cfg/yolov3-a-voc1999.cfg backup-voc1999/yolov3-a-voc1999_final.weights -points 0 | tee visualization-1999/v3-a-voc1999-bach64-16-2lei-test181-prcurves-0points-finalweights.log./darknet detector map cfg/voc1999.data cfg/yolov3-a-voc1999.cfg backup-voc1999-2/yolov3-a-voc1999_final.weights -points 0 | tee visualization-1999-2-ite8000/v3-a-voc1999-bach64-16-2lei-test181-prcurves-0points-iter8000-finalweights.log测试：
./darknet detector test cfg/voc1999.data cfg/yolov3-a-voc1999.cfg backup-voc1999-2/yolov3-a-voc1999_final.weights scripts/VOCdevkit/VOC1999/JPEGImages/000001.jpg | tee visualization-1999-ite8000-test/test-181-v3-voc1999-bach64-16-2lei-iter8000-000001-jpg-1.log批量测试：
./darknet detector test cfg/voc1999.data cfg/yolov3-a-voc1999.cfg backup-voc1999-2/yolov3-a-voc1999_final.weights -dont_show -ext_output < scripts/1999_test.txt > results/1999-ite8000-test.txt | tee visualization-1999-ite8000-test/test-181-v3-voc1999-bach64-16-2lei-iter8000-jpg-1.log8、yolov3-network-slimming
1.对原始weights文件进行稀疏化训练
python sparsity_train-3.py -gpus 6,7 | tee visualization/sparsity-07-12trainval-yolov3-a-0.0001-resize416-batch128-32-2gpu-start2019-7-28-1450-1.log CUDA_VISIBLE_DEVICES='7' python sparsity_train-3.py | tee visualization/sparsity-07-12trainval-yolov3-a-0.0001-resize416-batch16-16-3cpu-start2019-7-28-1520-1.logCUDA_VISIBLE_DEVICES='7' python sparsity_train-3.py -sr --s 0.001 | tee visualization/sparsity-07trainval-yolov3-a-2-0.001-resize416-batch16-1-2cpu-start2019-8-3-1520-1.log2.剪枝
CUDA_VISIBLE_DEVICES=9 python new_prune-0.3.py --weights checkpoints-q-1/yolov3_sparsity_416_0.0001_final_1_182.weights --percent 0.5 | tee visualization/prune-0.5-07-12trainval-yolov3-a-resize416-batch16-1-2cpu-start2019-8-4-1500-1.log3.对剪枝后的weights进行微调
CUDA_VISIBLE_DEVICES='7' python sparsity_train-weitiao.py --cfg prune_yolov3-voc-sparsity-1.cfg --weights checkpoints-q-1/prune_yolov3_sparsity_416_0.0001_final_1_182.weights | tee visualization/weitiao-07-12trainval-yolov3-a-resize416-batch16-1-2cpu-start2019-8-4-1500-1.log4.微调后进行测试：
4.微调后进行测试：
7、facebookresearch/Detectron
https://github.com/facebookresearch/Detectron
https://caffe2.ai/docs/tutorials.html
source activate pytorch1.1-cuda9-py3.6 source activate pytorch1.1.0-py2.7_cuda9.0
https://github.com/facebookresearch/Detectron/blob/master/INSTALL.md
faster-rcnn-Detectron
- 开始训练
CUDA_VISIBLE_DEVICES='3,4' python tools/train_net.py --cfg experiment/2gpu_e2e_faster_rcnn_R-50-FPN-voc2007.yaml OUTPUT_DIR out-1 | tee visualization/2gpu_e2e_faster_rcnn_R-50-FPN-voc2007.log
CUDA_VISIBLE_DEVICES=2 python tools/train_net.py --cfg experiments/2gpu_e2e_faster_rcnn_R-50-FPN-voc2007.yaml OUTPUT_DIR out-faster-rcnn-1/train-2 | tee visualization/1gpu_e2e_faster_rcnn_R-50-FPN-voc2007-iter70000-start-7-20-2150.log
2019-7-25：
- voc2007+12trainval训练
CUDA_VISIBLE_DEVICES='2,3' python tools/train_net.py --cfg experiments/tutorial_2gpu_e2e_faster_rcnn_R-50-FPN-trainval07+12.yaml OUTPUT_DIR tutorial_2gpu_e2e_faster_rcnn_R-50-FPN/ | tee visualization/tutorial_2gpu_e2e_faster_rcnn_R-50-FPN-trainval07+12-ite60000-1.log
CUDA_VISIBLE_DEVICES='6,7,8' python tools/train_net.py --cfg experiments/e2e_faster_rcnn_R-101-FPN_1x-trainval07+12.yaml OUTPUT_DIR e2e_faster_rcnn_R-101-FPN_1x-trainval07+12/train-3/ | tee visualization/e2e_faster_rcnn_R-101-FPN_1x-trainval07+12-ite90000-start7-26-2040-1.log
CUDA_VISIBLE_DEVICES='6,7' python tools/train_net.py --cfg experiments/e2e_mask_rcnn_R-50-FPN_2x_gn-trainval07+12.yaml OUTPUT_DIR e2e_mask_rcnn_R-50-FPN_2x_gn-trainval07+12/ | tee visualization/e2e_mask_rcnn_R-50-FPN_2x_gn-trainval07+12-start7-27-1200-2gpu-1.logCUDA_VISIBLE_DEVICES='8,9' python tools/train_net.py --cfg experiments/e2e_faster_rcnn_R-101-FPN_1x-trainval07+12-2gpu.yaml OUTPUT_DIR e2e_faster_rcnn_R-101-FPN_1x-trainval07+12-2gpu/ | tee visualization/e2e_faster_rcnn_R-101-FPN_1x-trainval07+12-2gpu-start7-27-1215-1.log
CUDA_VISIBLE_DEVICES='6,7,8,9' python tools/train_net.py --cfg experiments/e2e_faster_rcnn_R-101-FPN_1x-trainval07+12-4gpu.yaml OUTPUT_DIR e2e_faster_rcnn_R-101-FPN_1x-trainval07+12-4gpu-iter20000/ | tee visualization/e2e_faster_rcnn_R-101-FPN_1x-trainval07+12-4gpu-start7-28-1100-iter20000-1.log
- 测试训练结果（几张图片）
CUDA_VISIBLE_DEVICES=4 python tools/infer_simple.py --cfg experiment/2gpu_e2e_faster_rcnn_R-50-FPN-voc2007.yaml --output-dir out-1/detectron-visualizations/ --image-ext jpg --wts out-1/train/voc_2007_train/generalized_rcnn/model_final.pkl demo | tee visualization/2gpu_e2e_faster_rcnn_R-50-FPN-voc2007-infer-simple.log
- 评估训练结果（生成mAP）
CUDA_VISIBLE_DEVICES=4 python tools/test_net.py --cfg experiments/2gpu_e2e_faster_rcnn_R-50-FPN-voc2007.yaml TEST.WEIGHTS out-faster-rcnn-1/train/voc_2007_train/generalized_rcnn/model_final.pkl NUM_GPUS 1 | tee visualization/2gpu_e2e_faster_rcnn_R-50-FPN-voc2007-test_net.log
- 可视化检测结果（测试多张图片）
CUDA_VISIBLE_DEVICES=4 python tools/visualize_results.py --dataset voc_2007_val --detections out-faster-rcnn-1/test/voc_2007_val/generalized_rcnn/detections.pkl --output-dir out-faster-rcnn-1/detectron-visualizations
问题：
FileNotFoundError: [Errno 2] No such file or directory: '/home/xxx/detectron/datasets/data/VOC2007/VOCdevkit2007/results/VOC2007/Main/comp4_80ce9d5d-3ac9-4469-8914-2b6eabc81797_det_val_aeroplane.txt'
新建results/VOC2007/Main文件夹即可
mask-rcnn-Detectron
训练：
CUDA_VISIBLE_DEVICES='2,3' python tools/train_net.py --cfg experiments/e2e_mask_rcnn_R-50-FPN_2x_gn.yaml OUTPUT_DIR out-e2e_mask_rcnn_R-50-FPN_2x_gn/ | tee visualization/e2e_mask_rcnn_R-50-FPN_2x_gn-voc2007-iter180000-start-7-21-1135.log
CUDA_VISIBLE_DEVICES='4,5' python tools/train_net.py --cfg experiments/e2e_mask_rcnn_R-101-FPN_1x.yaml OUTPUT_DIR out-e2e_mask_rcnn_R-101-FPN_1x/ | tee visualization/e2e_mask_rcnn_R-101-FPN_1x-voc2007-iter90000-start-7-21-1935.log
1、yolov3-a-Pytorch-voc2007
CUDA_VISIBLE_DEVICES=8 ./darknet detector train cfg/voc-y.data cfg/yolov3-voc-y.cfg darknet53.conv.74 -map原版训练：
CUDA_VISIBLE_DEVICES=3 ./darknet detector train cfg/voc-y.data cfg/yolov3-voc-y.cfg backup-y/yolov3-voc-y_2500.weights | tee visualization/train-yolov3-1.log
CUDA_VISIBLE_DEVICES=4 ./darknet detector train cfg/voc-y.data cfg/yolov3-voc-y.cfg | tee visualization/train-yolov3-1.log
CUDA_VISIBLE_DEVICES=4 ./darknet detector train cfg/voc-y.data cfg/yolov3-voc-y.cfg backup/yolov3-voc-y_last.weights 2>1 | tee visualization/darknet-y-batch64-16-voc07-train5011-iteration16767-02.logvoc2007+12trainval训练:
./darknet detector train cfg/voc-y.data cfg/yolov3-voc-y.cfg darknet53.conv.74 -gpus 4,5 | tee visualization/darknet-y-batch128-32-voc0712trainval-iteration-start7-24-1300-01.log./darknet detector train cfg/voc-y.data cfg/yolov3-voc-y.cfg backup/yolov3-voc-y_last.weights -gpus 4,5 | tee visualization/darknet-y-batch128-32-voc0712trainval-iteration-start7-24-1300-02.log
计算map：
./darknet detector map cfg/voc-y.data cfg/yolov3-voc-y.cfg backup/yolov3-voc-y_41000.weights | tee visualization/darknet-voc2007-bach64-16-20lei-iteration41000-prcurves-points-41000weights.logCUDA_VISIBLE_DEVICES='7' ./darknet detector map cfg/voc-y.data cfg/yolov3-voc-y.cfg backup/yolov3-voc-y_final.weights | tee visualization/darknet-a-y-batch128-32-voc0712trainval-iteration60200-test-1.log原版检测单张图片：
CUDA_VISIBLE_DEVICES=8 ./darknet detector test ./cfg/voc-y.data ./cfg/yolov3-voc-y.cfg ./yolov3.weights data/dog.jpg
2、yolov3-a-voc2001
训练：
CUDA_VISIBLE_DEVICES=4 ./darknet detector train cfg/voc2001.data cfg/yolov3-voc2001.cfg darknet53.conv.74 | tee visualization/darknet-voc2001-bach64-32-2lei-train5011-iteration.log计算map：
./darknet detector map cfg/voc2001.data cfg/yolov3-voc2001.cfg backup/yolov3-voc2001_5000.weights | tee visualization/darknet-voc2001-bach64-32-2lei-trainval904-iteration-5000weights.log./darknet detector map cfg/voc2001.data cfg/yolov3-voc2001.cfg backup/yolov3-voc2001_4000.weights | tee visualization/darknet-voc2001-bach64-32-2lei-trainval904-iteration5000-4000weights.log./darknet detector map cfg/voc2001.data cfg/yolov3-voc2001.cfg backup/yolov3-voc2001_3000.weights | tee visualization/darknet-voc2001-bach64-32-2lei-trainval904-iteration5000-3000weights.log./darknet detector map cfg/voc2001.data cfg/yolov3-voc2001.cfg backup/yolov3-voc2001_5000.weights -points 11 | tee visualization/darknet-voc2001-bach64-32-2lei-trainval904-iteration-prcurves-11points-5000weights.log
检测单张图片：
./darknet detector test cfg/voc2001.data cfg/yolov3-voc2001.cfg backup/yolov3-voc2001_last.weights data/000001.jpg | tee visualization/darknet-voc2001-bach64-32-2lei-trainval904-iteration5000-000001-jpg.log
3、yolov2-a-voc2001
训练：
CUDA_VISIBLE_DEVICES=5 ./darknet detector train cfg/voc2001.data cfg/yolov2-voc2001.cfg darknet19_448.conv.23 | tee visualization/darknet-v2-voc2001-batch64-16-trainval904-iteration-start6-30-22:58-01.log
计算map：
./darknet detector map cfg/voc2001.data cfg/yolov2-voc2001.cfg backup/yolov2-voc2001_4000.weights | tee visualization/darknet-v2-voc2001-bach64-32-2lei-trainval904-iteration5000-4000weights.log./darknet detector map cfg/voc2001.data cfg/yolov2-voc2001.cfg backup/yolov2-voc2001_final.weights | tee visualization/darknet-v2-voc2001-bach64-32-2lei-trainval904-iteration5000-finalweights.log
检测单张图片：
./darknet detector test cfg/voc2001.data cfg/yolov2-voc2001.cfg backup/yolov2-voc2001_last.weights data/000002.jpg | tee visualization/darknet-voc2001-bach64-32-2lei-trainval904-iteration5000-000002-jpg.log
4、SSD.Pytorch
CUDA_VISIBLE_DEVICES=8 python train.py | tee visualization/train-ssd300-voc07-batch32-classes21-iter-04.log
5、yolov3原版剪枝
稀疏化：
CUDA_VISIBLE_DEVICES=9 python sparsity_train-3.py | tee visualization/sparsity-train-yolov3-voc07trainval--02.log剪枝：
CUDA_VISIBLE_DEVICES=9 python new_prune-0.3.py --weights checkpoints-3/yolov3_sparsity_416_0.0001_final_1_410.weights
5、Faster-RCNN
- voc2007
训练：
CUDA_VISIBLE_DEVICES=4 python trainval_net.py --bs 10 --cuda --checkepoch 13 --checkpoint 1001 --use_tfb | tee visualization/faster-rcnn-voc07-trainval-iteration-01.log测试：
CUDA_VISIBLE_DEVICES=4 python test_net.py --checkepoch 20 --checkpoint 1001 --cuda | tee visualization/faster-rcnn-voc07-trainval-checkepoch-20-checkpoint-1001-01.log2、自己数据集
训练：
python setup.py build developCUDA_VISIBLE_DEVICES=4 python trainval_net.py --bs 5 --cuda --use_tfb | tee visualization/faster-rcnn-voc2001-trainval-bs5-iteration-01.log
测试：
CUDA_VISIBLE_DEVICES=4 python test_net.py --checkepoch 20 --checkpoint 179 --cuda | tee visualization/faster-rcnn-voc2001-test275-checkepoch-20-checkpoint-179-01.log
6、CornerNet-Lite
1、Getting Started
anaconda创建pytorch1.1虚拟环境：
source activate pytorch退出pytorch1.1虚拟环境：
conda deactivate
conda create --name cornerNet_Lite-y --file conda_packagelist.txt --channel pytorchhttps://conda.anaconda.org/pytorch/linux-64/pytorch-1.0.0-py3.7_cuda10.0.130_cudnn7.4.1_1.tar.bz2
原文：https://blog.csdn.net/u014236392/article/details/81127537