array(4) { [0]=> string(99) "Computer-Vision-Nanodegree-master\project_1-facial_keypoint _detection\3. Facial Keypoint Detection" [1]=> string(24) " Complete Pipeline.ipynb" [2]=> string(7) " 786267" [3]=> string(21) " 2020-02-07 08:22:5 " } Computer-Vision-Nanodegree 联合开发网 - pudn.com
Computer-Vision-Nanodegree

所属分类:人工智能/神经网络/深度学习
开发工具:Jupyter Notebook
文件大小:5948KB
下载次数:0
上传日期:2022-12-07 23:54:08
上 传 者sh-1993
说明:  作为Facebook AI在第一阶段6000名“安全和私有AI”中选择的300名学者之一,我有一个...
(As one of the 300 scholars chosen among 6,000 from the first phase, "Secure and Private AI" by Facebook AI, I have earned a full scholarship to Udacity’s Computer Vision Nanodegree)

文件列表:
images (0, 2020-02-07)
images\caption_inference.jpg (34069, 2020-02-07)
images\facial_keypoint_inference.jpg (841398, 2020-02-07)
images\slam_result.jpg (130912, 2020-02-07)
project_1-facial_keypoint _detection (0, 2020-02-07)
project_1-facial_keypoint _detection\1. Load and Visualize Data.ipynb (670294, 2020-02-07)
project_1-facial_keypoint _detection\2. Define the Network Architecture.ipynb (803055, 2020-02-07)
project_1-facial_keypoint _detection\4. Fun with Keypoints.ipynb (111656, 2020-02-07)
project_1-facial_keypoint _detection\data_load.py (4826, 2020-02-07)
project_1-facial_keypoint _detection\detector_architectures (0, 2020-02-07)
project_1-facial_keypoint _detection\detector_architectures\haarcascade_eye.xml (341406, 2020-02-07)
project_1-facial_keypoint _detection\detector_architectures\haarcascade_frontalface_default.xml (930127, 2020-02-07)
project_1-facial_keypoint _detection\detector_architectures\haarcascade_mcs_nose.xml (1585209, 2020-02-07)
project_1-facial_keypoint _detection\detector_architectures\haarcascade_smile.xml (188650, 2020-02-07)
project_1-facial_keypoint _detection\images (0, 2020-02-07)
project_1-facial_keypoint _detection\images\facial_keypoint_inference.jpg (841398, 2020-02-07)
project_1-facial_keypoint _detection\images\key_pts_example.png (346539, 2020-02-07)
project_1-facial_keypoint _detection\models.py (3736, 2020-02-07)
project_1-facial_keypoint _detection\workspace_utils.py (1540, 2020-02-07)
project_2-automatic_image_captioning (0, 2020-02-07)
project_2-automatic_image_captioning\0_Dataset.ipynb (242643, 2020-02-07)
project_2-automatic_image_captioning\1_Preliminaries.ipynb (50847, 2020-02-07)
project_2-automatic_image_captioning\2_Training.ipynb (34561, 2020-02-07)
project_2-automatic_image_captioning\3_Inference.ipynb (1119833, 2020-02-07)
project_2-automatic_image_captioning\data_loader.py (7125, 2020-02-07)
project_2-automatic_image_captioning\images (0, 2020-02-07)
project_2-automatic_image_captioning\images\caption_inference.jpg (34069, 2020-02-07)
project_2-automatic_image_captioning\images\coco-examples.jpg (96787, 2020-02-07)
project_2-automatic_image_captioning\images\encoder-decoder.png (302509, 2020-02-07)
project_2-automatic_image_captioning\images\image-description.png (264207, 2020-02-07)
project_2-automatic_image_captioning\model.py (3952, 2020-02-07)
project_2-automatic_image_captioning\requirements.txt (3073, 2020-02-07)
project_2-automatic_image_captioning\training_log.txt (1033726, 2020-02-07)
project_2-automatic_image_captioning\vocab.pkl (242231, 2020-02-07)
project_2-automatic_image_captioning\vocabulary.py (3504, 2020-02-07)
... ...

# Computer Vision Nanodegree This repository contains the projects that I've developed during Udacity's [Computer Vision Nanodegree](https://www.udacity.com/course/computer-vision-nanodegree--nd891). ## Projects ### [Facial Keypoints Detection](https://github.com/HROlive/Computer-Vision-Nanodegree/tree/master/project_1-facial_keypoint%20_detection) Using image processing and deep learning techniques to create a facial keypoint detection system that takes in any image with faces, and predicts the location of 68 distinguishing keypoints on each face, such as the position of the eyes, nose, and mouth.

### [Automatic Image Captioning](https://github.com/HROlive/Computer-Vision-Nanodegree/tree/master/project_2-automatic_image_captioning) Designed and trained a CNN-RNN model that automatically generates image captions. The network is trained on the Microsoft Common Objects in COntext (MS COCO) dataset.

### [Landmark Detection & Robot Tracking (SLAM)](https://github.com/HROlive/Computer-Vision-Nanodegree/tree/master/project_3-SLAM_landmark_detection_%26_robot_tracking) Implementation of SLAM (Simultaneous Localization and Mapping) for a 2-dimensional world. Sensor and motion data gathered by a simulated robot is used to create a map of an environment. SLAM gives us a way to track the location of a robot in the world in real-time and identify the locations of landmarks such as buildings, trees, rocks, etc.


近期下载者

相关文件


收藏者