upload code

9-前沿应用/9.08-3D目标检测2/READMEpointpillars.md → 9-前沿应用/9.08-3D目标检测2/READMEiassd.md

-代码及数据下载：
-代码及数据下载：
-通过网盘分享的文件：OpenPCDet-master.zip
-链接: https://pan.baidu.com/s/10-SrX6_Hj8qDoYy5Qvv5LA 提取码: eg64 
---来自百度网盘超级会员v2的分享
+
 
 ## 环境配置
-conda create -n OpenPCDet python==3.8
-conda activate OpenPCDet
+conda create -n iassd python==3.8
+conda activate iassd
 pip install torch==1.10.0+cu111 torchvision==0.11.0+cu111 torchaudio==0.10.0 -f https://download.pytorch.org/whl/torch_stable.html
 pip install -r requirements.txt
-pip install kornia==0.6.8
 pip install numpy==1.23.4
 pip install numba==0.56.4
-pip install av2==0.2.0
 pip install spconv-cu111
-pip install open3d==0.10.0（要检查这个是否安上了）
 编译：python setup.py develop
 
 
@@ -33,7 +26,6 @@ python -m pcdet.datasets.kitti.kitti_dataset create_kitti_infos tools/cfgs/datas
 
 ## 模型训练与测试
 cd tools
-训练：python train.py --cfg_file cfgs/kitti_models/pointpillar.yaml
-log文件保存在：/OpenPCDet-master/output/kitti_models/pointpillar/default/train_20250209-230544.log
-测试：python test.py --cfg_file cfgs/kitti_models/pointpillar.yaml --batch_size 1 --ckpt ../output/kitti_models/pointpillar/default/ckpt/checkpoint_epoch_80.pth --save_to_file
-可视化：CUDA_VISIBLE_DEVICES=1 python demo.py --cfg_file cfgs/kitti_models/pointpillar.yaml --ckpt ../output/kitti_models/pointpillar/default/ckpt/checkpoint_epoch_80.pth --data_path ../data/kitti/testing/velodyne/000000.bin
\ No newline at end of file
+训练：python train.py --cfg_file ./cfgs/kitti_models/IA-SSD.yaml --batch_size 2
+测试：python test.py --cfg_file ./cfgs/kitti_models/IA-SSD.yaml --batch_size 1 --ckpt ../output/kitti_models/IA-SSD/default/ckpt/checkpoint_epoch_80.pth --set MODEL.POST_PROCESSING.RECALL_MODE 'speed'
+#测试时速度优先
\ No newline at end of file