ubunutu下anaconda3下object detection

下载model——更名为model_8.1:

    sudo apt install git

    使用码云复制github项目,然后从码云下载

    git clone http...

按照官方指导步骤

    install点击打开链接

    config点击打开链接

        配置文件从samples中复制faster_rcnn_resnet101_voc07.config

    prepare点击打开链接

    running点击打开链接:

        新建的modles下面的modle文件命名为faster_rcnn_resnet101

上述步骤中:

    配置文件faster_rcnn_resnet101_voc07.config和运行代码中的路径为:

modle zoo:

/home/zhanghao/models_8.1/research/faster_rcnn_resnet101_coco_2018_01_28

record文件:

/home/zhanghao/models_8.1/research/data

运行代码:

python3 object_detection/train.py \

    --logtostderr \

    --pipeline_config_path=/home/zhanghao/models_8.1/research/models/faster_rcnn_resnet101/faster_rcnn_resnet101_voc07.config \

    --train_dir=/home/zhanghao/models_8.1/research/models/faster_rcnn_resnet101/train/


程序中需要把learning_shedules.py文件的 第167-169行由

rate_index = tf.reduce_max(tf.where(tf.greater_equal(global_step, boundaries),
range(num_boundaries),
[0] * num_boundaries))

改为

rate_index = tf.reduce_max(tf.where(tf.greater_equal(global_step, boundaries),
list(range(num_boundaries)),
[0] * num_boundaries))



猜你喜欢

转载自blog.csdn.net/f2h3k999/article/details/79770422