如何微调tensorflow对象检测api模型？
[英]how to fine tune the tensorflow object detection api model?
问题描述
I have used 300 images, in that used 80%-20% as a train and test data respectively, as per eval.py, I am getting 13 mAP%.
我使用了 300 张图像，其中分别使用了 80%-20% 作为训练和测试数据，根据 eval.py，我得到了 13 mAP%。 in config batch size is 1, the number of steps is 200k, input image size is 512x512.在配置中批量大小为 1，步数为 200k，输入图像大小为 512x512。
so what is the solution?那么解决方案是什么？ to fine-tune only?仅微调？
1 个解决方案
解决方案1
0 2019-12-13 06:50:26
请参考这个SO 问题它解释了如何微调对象检测 API 模型。
声明:本站的技术帖子网页，遵循CC BY-SA 4.0协议，如果您需要转载，请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.
相关问题
TensorFlow 对象检测 API 微调检查点 - TensorFlow object detection API fine tune checkpoint
如何使用TensorFlow中的fine_tune_checkpoint Object检测API - How to use the fine_tune_checkpoint in TensorFlow Object Detection API
使用Tensorflow对象检测API来微调mask_rcnn_inception_resnet_v2_atrous_coco模型时断言失败错误 - assertion failed error when using tensorflow object detection API to fine tune the mask_rcnn_inception_resnet_v2_atrous_coco model
Tensorflow Object 检测 API - “fine_tune”与“检测”与“分类” - Tensorflow Object Detection API - "fine_tune" vs "detection" vs "classification"
Tensorflow object_detection 保存和加载微调的正确方式 model - Tensorflow object_detection correct way to save and load fine tune model
TensorFlow 对象检测 API：使用“fine_tune_checkpoint”进行训练 - 解冻较早的层？ - TensorFlow Object Detection API: training with `fine_tune_checkpoint` - unfreeze the earlier layers?
如何使用 Tensorflow 2 对象检测 API 恢复微调模型进行测试？ - How to restore a fine-tuned model with Tensorflow 2 Object Detection API for testing?
如何使用 Detectron2 为自定义数据和类微调 object 检测 model？ - How to fine tune an object detection model for custom data and classes using Detectron2?
Tensorflow：微调 Inception 模型 - Tensorflow: Fine tune Inception model
tensorflow对象检测中checkpoint_dir和fine_tune_checkpoint有什么区别？ - What is the difference between checkpoint_dir and fine_tune_checkpoint in tensorflow object detection?
相关标签