Open Allamrahul opened 1 year ago
I see that MAX_VOXELS is hard coded to 10000 in the export script exporter.py. But when I examine the pointpillar.yaml, I see this: MAX_NUMBER_OF_VOXELS: { 'train': 16000, 'test': 40000 } So, should'nt MAX_VOXELS in the export script be 40000?
I tried this out: when I gave 40000 for MAX_VOXELS and exported the onnx file, the multiple false positives I get in FP16 inference TFRT goes away. Can anyone confirm what I did makes sense?
Dataset: I am using a custom dataset with npy files and annotations. I just have a single class of objects to detect. I followed all steps required for custom dataset preparation and I am able to get great results during the evaluation phase using pytorch (90% mAP).
Post that, I am able to convert the model to onnx format and perform inference using TFRT. I am getting more or less same detections as what I got during the evaluation phase.
However, when I perform TFRT inference using FP16, I am getting too many false detections(200's) as shown below:
![image](https://user-images.githubusercontent.com/18104407/219123681-0f9ce632-27b1-4d94-9747-cefbb7667dcf.png)
I observed the same behavior on other examples as well. When I disable FP16, my detections using TFRT are approximately close to my evaluation numbers. But something about fp16 makes it go out of whack.
Please let me know if I am missing something here