如何增加ssd_mobilenet_v1 tensorflow中的num_classes



我正在使用ssd_mobilenet_v1_coco.config和

我在计划训练后添加了13个东西,将num_classes的值改为20

python model_main.py --alsologtostderr --model_dir=training/ --pipeline_config_path=training/ssd_mobilenet_v1_coco.config

我一直试着用命令学习,但我犯了一个错误。增加num_classes我该怎么办?我应该从头开始获取num_classes=100吗?我需要帮助。

model {
ssd {
num_classes: 20
box_coder {
faster_rcnn_box_coder {
y_scale: 10.0
x_scale: 10.0
height_scale: 5.0
width_scale: 5.0
}

File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/training/saver.py", line 1326, in restore
err, "a mismatch between the current graph and the graph")
tensorflow.python.framework.errors_impl.InvalidArgumentError: Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
Assign requires shapes of both tensors to match. lhs shape= [126] rhs shape= [84]
[[node save/Assign_56 (defined at /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/framework/ops.py:1748) ]]

我最近遇到了类似的问题。为了解决我的问题,我不得不做以下事情:

  • 在pipeline.config的train_config部分中,使fine_tune_checkpoint指向上一个模型检查点。例如:`fine_tune_checkpoint:"model/model.ckpt">
  • model_main.py命令调用中,使model_dir引用与上一个检查点不同的文件夹:
python research/object_detection/model_main.py 
--model_dir=./model/finetune0 
--pipeline_config_path=./model/pipeline.config 
--alsologtostderr

我的文件结构:

+ models
-+ model
--+ checkpoint
--+ model.ckpt.index
--+ model.ckpt.meta
--+ model.ckpt.data-00000-of-00001
--+ pipeline.config
--- finetune0 (will be autogenerated)
-- data (tfrecord dataset)
-- annotations (labels)
...

上下文

看起来,当您在model_dir上已经有了一个检查点时,脚本将尝试恢复对所提供模型的训练,但pipeline.config上的新配置与当前模型不匹配(num_class不同(。

如果您在fine_tune_checkpoint中提供此检查点,并将model_dir指向一个新文件夹,它将从检查点变量构建模型,对其进行调整以匹配新配置,然后开始训练。

相关内容

  • 没有找到相关文章

最新更新