Hi everyone. Sharing my project entry for the NVIDIA Jetson AI Specialist Certification. The project is an Acute Lymphoblastic Leukemia classifier developed using Intel® oneAPI AI Analytics Toolkit and Intel® Optimization for Tensorflow* to accelerate the training process, and TFRT, ONNX &TensorRT for high performance inference on the NVIDIA® Jetson Nano™.
Acc 0.9158415794372559
Precision 0.9158415794372559
Recall 0.9158415794372559
Auc 0.984254002571106
True Positives: 160(39.603960396039604%)
False Positives: 10(2.4752475247524752%)
True Negatives: 210(51.98019801980198%)
False Negatives: 24(5.9405940594059405%)
Specificity: 0.9545454545454546
Misclassification: 34(8.415841584158416%)
In this project you will do the following.
- Train a custom CNN for Acute Lymphoblastic Leukemia on your development machine.
- Convert the Tensorflow SavedModel to TFRT format
- Convert the Tensorflow SavedModel to ONNX format
- Convert the Tensorflow ONNX model to TensorRT format
- Test the CNN on your development machine.
- Download or create a custom docker container for your NVIDIA Jetson Nano.
- Run the CNN on your NVIDIA Jetson Nano using Tensorflow.
- Run the CNN on your NVIDIA Jetson Nano using TFRT.
- Run the CNN on your NVIDIA Jetson Nano using TensorRT.
This is my first experience with developing a project for the Jetson Nano and I learnt a lot. I hope the project is useful.
Github: GitHub - AMLResearchProject/all-jetson-nano-classifier: An Acute Lymphoblastic Leukemia classifier developed for the NVIDIA Jetson Nano. Jetson AI Certification project by Adam Milton-Barker.
Docker Hub: Docker
Feedback welcome.