小编use*_*338的帖子

我可以获得该项目，但它没有检索该Social Preview项目的：

我正在使用的链接是这个： https://api.github.com/repos/AngelRibeiro10/BCMIC-PHD

返回以下内容：

{
  "id": 215636067,
  "node_id": "MDEwOlJlcG9zaXRvcnkyMTU2MzYwNjc=",
  "name": "BCMIC-PHD",
  "full_name": "AngelRibeiro10/BCMIC-PHD",
  "private": false,
  "owner": {
    "login": "AngelRibeiro10",
    "id": 13433634,
    "node_id": "MDQ6VXNlcjEzNDMzNjM0",
    "avatar_url": "https://avatars2.githubusercontent.com/u/13433634?v=4",
    "gravatar_id": "",
    "url": "https://api.github.com/users/AngelRibeiro10",
    "html_url": "https://github.com/AngelRibeiro10",
    "followers_url": "https://api.github.com/users/AngelRibeiro10/followers",
    "following_url": "https://api.github.com/users/AngelRibeiro10/following{/other_user}",
    "gists_url": "https://api.github.com/users/AngelRibeiro10/gists{/gist_id}",
    "starred_url": "https://api.github.com/users/AngelRibeiro10/starred{/owner}{/repo}",
    "subscriptions_url": "https://api.github.com/users/AngelRibeiro10/subscriptions",
    "organizations_url": "https://api.github.com/users/AngelRibeiro10/orgs",
    "repos_url": "https://api.github.com/users/AngelRibeiro10/repos",
    "events_url": "https://api.github.com/users/AngelRibeiro10/events{/privacy}",
    "received_events_url": "https://api.github.com/users/AngelRibeiro10/received_events",
    "type": "User",
    "site_admin": false
  },
  "html_url": "https://github.com/AngelRibeiro10/BCMIC-PHD",
  "description": "This is a Brain-Computer Music Interfacing Project",
  "fork": false,
  "url": "https://api.github.com/repos/AngelRibeiro10/BCMIC-PHD",
  "forks_url": "https://api.github.com/repos/AngelRibeiro10/BCMIC-PHD/forks",
  "keys_url": "https://api.github.com/repos/AngelRibeiro10/BCMIC-PHD/keys{/key_id}",
  "collaborators_url": "https://api.github.com/repos/AngelRibeiro10/BCMIC-PHD/collaborators{/collaborator}",
  "teams_url": "https://api.github.com/repos/AngelRibeiro10/BCMIC-PHD/teams",
  "hooks_url": …

我正在使用谷歌的 tensorflow 和 colab notbook 加载神经网络。我想移除输出层的全连接层并添加另一个只有一个神经元的全连接层，我想冻结其他层并只训练这个添加的输出层。我正在使用tf.keras.application.MobileNetV2并且正在使用 mledu- datasets/cats_and_dogs。

我在 tensorflow API 中搜索并测试了要添加的方法，但没有成功。我的代码如下

Original file is located at
    https://colab.research.google.com/drive/16VdqQFBfY_jp5-5kRQvWQ0Y0ytN9W1kN

https://colab.research.google.com/github/tensorflow/docs/blob/master/site/en/tutorials/images/classification.ipynb#scrollTo=3f0Z7NZgVrWQ

This tutorial follows a basic machine learning workflow:

1.   Examine and understand data
2.   Build an input pipeline
3.   Build the model
4.   Train the model
5.   Test the model
6.   Improve the model and repeat the process

## Import packages

Let's start by importing the required packages. The `os` package is used to read files and directory …