See Poor metric results after retraining maskrcnn using TLT notebook - #17 by Morganh , it needs longer training. Refer to the spec and the log I shared in that forum topic.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Models Pretrained on MS COCO | 6 | 1436 | August 17, 2021 | |
| Poor metric results after retraining maskrcnn using TLT notebook | 23 | 2490 | August 3, 2021 | |
| Poor performance of MaskRCNN on images | 16 | 1371 | October 12, 2021 | |
| Mask rcnn poor results | 4 | 1049 | October 12, 2021 | |
| Low accuracy for MS COCO dataset in tao maskrcnn model training | 10 | 79 | September 17, 2024 | |
| Training Instance Segmentation Models Using Mask R-CNN on the NVIDIA Transfer Learning Toolkit | 3 | 1039 | August 18, 2021 | |
| Mask_rcnn shows training logs loss 0.00000 fast_rcnn class loss: 0.00000 fast_rcnn box loss: 0.00000 | 22 | 824 | August 16, 2022 | |
| Pre processing for MaskRCNN | 4 | 846 | December 6, 2021 | |
| Training problems with the TAO toolkit using Mask R-CNN | 7 | 878 | November 22, 2022 | |
| Unable to visualize the mask in MaskRcnn using Nvidia tao toolkit | 4 | 324 | August 22, 2023 |