SSD训练自己的数据集经历的心酸_ssd数据集 python-优快云博客

本文链接：https://blog.youkuaiyun.com/qq_35291087/article/details/115278147

在Linux环境下执行shtrain.sh时遇到问题，原因是sh脚本内的python3train_ssd_network.py命令后存在空格，这导致了执行错误。修复此问题的关键是移除该命令后的空格，确保正确调用Python训练脚本。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

在这里插入图片描述
这里是运行sh train.sh时出现的错误，找原因找了好久我发现是sh脚本里面

python3 train_ssd_network.py \（这里出现了空格！！！！）
    --train_dir=/home/hj/SSD-Tensorflow-master/train_model \
    --dataset_dir=/home/hj/SSD-Tensorflow-master/train-tfrecords \
    --dataset_name=pascalvoc\
    --dataset_split_name=train \
    --model_name=ssd_300_vgg \
    --checkpoint_path=/home/hj/SSD-Tensorflow-master/checkpoints/vgg_16.ckpt \
    --checkpoint_model_scope=vgg_16 \
    --checkpoint_exclude_scopes=ssd_300_vgg/conv6,ssd_300_vgg/conv7,ssd_300_vgg/block8,ssd_300_vgg/block9,ssd_300_vgg/block10,ssd_300_vgg/block11,ssd_300_vgg/block4_box,ssd_300_vgg/block7_box,ssd_300_vgg/block8_box,ssd_300_vgg/block9_box,ssd_300_vgg/block10_box,ssd_300_vgg/block11_box \
    --trainable_scopes=ssd_300_vgg/conv6,ssd_300_vgg/conv7,ssd_300_vgg/block8,ssd_300_vgg/block9,ssd_300_vgg/block10,ssd_300_vgg/block11,ssd_300_vgg/block4_box,ssd_300_vgg/block7_box,ssd_300_vgg/block8_box,ssd_300_vgg/block9_box,ssd_300_vgg/block10_box,ssd_300_vgg/block11_box \
    --save_summaries_secs=60 \
    --save_interval_secs=600 \
    --weight_decay=0.0005 \
    --optimizer=adam \
    --learning_rate=0.001 \
    --learning_rate_decay_factor=0.94 \
    --batch_size=24 \
    --gpu_memory_fraction=0.9