小编dee*_*net的帖子

我想同时在我自己的数据集上训练/评估ssd_mobile_v1_coco Object Detection API.

但是,当我只是尝试这样做时,我面临的GPU内存几乎已满,因此评估脚本无法启动.以下是我用于训练和评估的命令:
在一个终端窗格中调用训练脚本,如下所示:

python3 train.py \
        --logtostderr \
        --train_dir=training_ssd_mobile_caltech \
        --pipeline_config_path=ssd_mobilenet_v1_coco_2017_11_17/ssd_mobilenet_v1_focal_loss_coco.config

运行正常,培训工作......然后我尝试在第二个终端窗格中运行评估脚本:

 python3 eval.py \
        --logtostderr \
        --checkpoint_dir=training_ssd_mobile_caltech \
        --eval_dir=eval_caltech \
        --pipeline_config_path=ssd_mobilenet_v1_coco_2017_11_17/ssd_mobilenet_v1_focal_loss_coco.config 

它失败并出现以下错误:

python3 eval.py \
        --logtostderr \
        --checkpoint_dir=training_ssd_mobile_caltech \
        --eval_dir=eval_caltech \
       --pipeline_config_path=ssd_mobilenet_v1_coco_2017_11_17/ssd_mobilenet_v1_focal_loss_coco.config 
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional conv before box predictor: 0
INFO:tensorflow:depth of additional …