问题描述
我正在研究使用 tensorflow 训练一个对象检测网络，我查看了 TF2 模型动物园.我注意到那里的模型明显少于目录/models/research/models/中的模型，包括为 jetson xavier 开发的带有 ssdlite 的 mobiledet.
I'm looking into training an object detection network using tensorflow, and i had a look at the TF2 model zoo. I noticed there are noticeably less models there than in the directory /models/research/models/, including the mobiledet with ssdlite developed for the jetson xavier.
澄清一下，自述文件说有一个带有 ssdlite 的 mobildet gpu，并且提供了在 COCO 上训练的模型和检查点，但我在 repo 的任何地方都找不到它们
to clarify, the readme says that there is a mobildet gpu with ssdlite, and that model and checkpoints trained on COCO are provided, yet i couldn't find them anywhere in the repo
应该如何使用这些模型?
How is one supposed to use those models?
我已经有一个经过自定义训练的用于图像分类的 mobilenetv3，我希望看到一种方法，可以根据 mobilenetv3 论文将网络变成对象检测网络.如果这不简单，从头开始训练一个网络也可以，我只需要知道从哪里开始
I already have a custom-trained mobilenetv3 for image classification, and i was hoping to see a way to turn the network into an object detection network, in accordance to the mobilenetv3 paper. If this is not straightforward, training one network from scratch could be ok too, i just need to know where to even start from
推荐答案
如果您计划使用对象检测 API，则不能使用现有模型.您必须从模型列表中选择此处 v2 和 此处 v1
If you plan to use the object detection API, you can't use your existing model. You have to choose from a list of models here for v2 and here for v1
文档维护得很好，并且很好地解释了对自定义数据进行训练或验证或运行推理(测试)的步骤 此处 由 TensorFlow 团队提供.该链接适用于 TensorFlow 版本 v2.但是，如果您希望使用 v1，该过程非常相似，并且有许多博客/视频解释了如何操作
The documentation is very well maintained and the steps to train or validate or run inference (test) on custom data is very well explained here by the TensorFlow team. The link is meant for TensorFlow version v2. However, if you wish to use v1, the process is fairly similar and there are numerous blogs/videos explaining how to go about it
这篇关于如何使用tensorflow/models/research/object_detection/models下的模型的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！