several computer vision projects in learning to create deep learning models, especially in the field of computer vision, starting from classification, object detection and others
These are some mini projects I created using Pytorch for computer vision tasks
in this repo I will create a mini project with various tasks in computer vision such as image classification, object detection, object segmentation, GAN and many more
add a star to get updates from this repo
Model Name | Model URL |
---|---|
Cat and Dogs | click here to download |
Plant Species | click here to download |
Manga Text | click here to download |
Facemask Detection | click here to download |
in this project, I focused on fine-tune the resnet-50 model then exported it to onnx format.
which initially resnet-50 outputs approximately 1000 classes into just 2 classes according to the dataset that has been downloaded, namely cats and dogs
in this project, I focused on fine-tune the google/vit-base-patch16-224 model then exported it to onnx format.
which initially google/vit-base-patch16-224 outputs approximately 1000 classes into just 47 classes according to the dataset that has been downloaded, namely house-plant-species
in this project, I focused on fine-tune the faster-RCNN model then exported it to onnx format.
create object detection on text in manga pages with the manga-text-detection dataset
in this project, I focused on fine-tune the YOLOv10 model then exported it to onnx format.
create object detection on facemask-dataset