结果放在./YOLOX_output/yolo_x_ablation/track_results datasets /MOT17 -default -parameters - with -reid -benchmark "MOT17" - eval "val" -fp16 -fuse datasets /MOT17 -default -parameters -benchmark "MOT17" - eval "val" -fp16 -fuse py -default -parameters -benchmark "MOT17" - eval "val" -fp16 -fuse =./YOLOX_output/yolo_x_mix_det/track_results YOLOX_output /yolo_x_mix_det /track_results datasets /MOT17 -default -parameters - with -reid -benchmark "MOT17" - eval "test" -fp16 -fuse -fast -reid -config = r"logs/MOT17/sbs_S50/config.yaml" -fast -reid -weights = r"logs/MOT17/sbs_S50/model_final.pth" py -default -parameters - with -reid -benchmark "MOT17" - eval "test" -fp16 -fuse 在tools/track.py文件修改–fast-reid-weights=r"logs/MOT17/sbs_S50/model_final.pth"和–fast-reid-config=r"logs/MOT17/sbs_S50/config.yaml" add_argument ( "-resume" ,default = True ,Īction = "store_true", help = "whether to attempt to resume from the checkpoint directory", )ĥ.'DefaultTrainer has no attribute ‘self.epoch’ 利用’fast_reid/fastreid/engine/defaults.py’的resume_or_load(resume=args.resume)，令args.resume=True，接下来的训练能接着上一次的checkpoints继续训练。 parser. cache /torch /hub /checkpoints /resnest50 - 528c19ca. Please ''put data folders such as "bounding_box_train" under '' "MOT17-ReID"
DEVICE "cuda:0"ġ.训练时出现错误： TypeError : register_buffer ( )takes 3 positional arguments but 4 were given. Python3 fast_reid /datasets /generate_mot_patches. Latter case the central directory and zipfile comment will be found onĢ.处理数据集，处理完的数据集放在BOT-SORT/fast-reid/datasets/MOT17_reid cd space /BOT -SORT Either this file is notĪ zipfile, or it constitutes one disk of a multi -part archive. zipĮnd -of -central -directory signature not found.
#Chitchat tracking install
则直接用conda安装lap库： conda install -c conda -forge lap Hint : See above for output from the failure. Note : This is an issue with the package mentioned above, not pip. × Encountered error while trying to install package. Pip3 install cython pip3 install 'git +https : ///cocodataset/cocoapi.git#subdirectory=PythonAPI' # cuda = 10.1 库要求pytorch > 1.6Ĭonda install pytorch = 1.7. Git clone https : ///NirAharon/BoT-SORT.git Pytorch在 pytorch/previous-versions中下载。 conda create -n botsort_env python = 3.7
0 kommentar(er)
