Use 3D ResNets to classify images (videos).

[Instructions]

1. 1_convert_avi_to_jpg.ipynb

Convert video (avi) to image (jpg).

2. 2_generate_annotation.ipynb

Generate annotated files of the image.

3. 3_train.ipynb

Setting parameters:

• root_path: the path of the training folder

• video_path: the file path of the training image

• annotation_path: the file path of the annotation

• result_path: the folder path of the result

After the setting is completed, it can be executed.

4. 4_inference_val.ipynb

Setting parameters:

• root_path: the path of the training folder

• video_path: the file path of the training image

• annotation_path: the file path of the annotation

• result_path: the folder path of the result

• resume_path: the path of the inference model

After the setting is completed, it can be executed.

After execution, you can see the results of 3D ResNets inference.

Jupyter-Image-Classification-3D-ResNets-inference.png

This SDK is built in AppForAI - AI Dev Tools.

Purchase license separately: USD 600, permanent authorization, single APP authorization, single machine authorization, one-year activation, one-year download, one-year update, one-year email technical support.