Retrain SSD Object Detection Model with Pytorch on Colab PART - 1

Mode details
https://microcontrollerkits.blogspot....

Transfer Learning with Pytorch

Transfer learning is a technique for re-training a DNN model on a new dataset, which takes less time than training a network from scratch. With transfer learning, the weights of a pre-trained model are fine-tuned to classify a customized dataset. In these examples, we'll be using the ResNet-18 and SSD-Mobilenet networks, although you can experiment with other networks too.
PyTorch is the machine learning framework that we'll be using, and example datasets along with training scripts are provided to use below, in addition to a camera-based tool for collecting and labeling your own training datasets.

Re-training SSD-Mobilenet

Next, we'll train our own SSD-Mobilenet object detection model using PyTorch and the Open Images dataset. SSD-Mobilenet is a popular network architecture for realtime object detection on mobile and embedded devices that combines the SSD-300 Single-Shot MultiBox Detector with a Mobilenet backbone.

Dataset
The Open Images dataset contains over 600 object classes that you can pick and choose from. There is a script provided called open_images_downloader.py which will automatically download the desired object classes for you.
The classes that we'll be using are "Apple,Orange,Banana,Strawberry,Grape,Pear,Pineapple,Watermelon", for example for a fruit-picking robot - although you are welcome to substitute your own choices from the class list. The fruit classes have ~6500 images, which is a happy medium.

Dataset
*By default, the dataset will be downloaded to the data/*
6360 images. 8 classes

train images:  5145
train boxes:   23539

validation images:  285
validation boxes:   825

test images:  930
test boxes:   2824

Total available images: 6360
Total available boxes:  27188

สอบถาม :
อดุลย์ นันทะแก้ว 081-6452400
LINE : adunnan
FaceBook :   / adun.nantakaew  

Page :   / softpowergroup  
WebSite : https://softpower.tech

Youtube 1 :    / @androidcontrol  
Youtube 2 :   / @softpowergroupnetthailand  

Web Blog : http://raspberrypi4u.blogspot.com/
Web Blog : http://microcontrollerkits.blogspot.com/

WebSite : https://softpower.tech