You can check the log mentioned in Poor metric results after retraining maskrcnn using TLT notebook - #20 by Morganh. It was training against the COCO dataset with pretrained model.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Maskrcnn.ipynb - followed notebook and ended up with poor (almost untrained) network from instructions | 13 | 760 | October 12, 2021 | |
| Retraining Error after pruning the Mask RCNN model with TAO Toolkit | 5 | 509 | May 10, 2022 | |
| Mask rcnn poor results | 4 | 1037 | October 12, 2021 | |
| Basic questions about transfer learning with TAO Toolkit | 2 | 465 | January 12, 2023 | |
| Poor metric results after retraining maskrcnn using TLT notebook | 23 | 2412 | August 3, 2021 | |
| Save maskrcnn model in hdf5 format | 3 | 14 | August 16, 2024 | |
| Poor performance of MaskRCNN on images | 16 | 1331 | October 12, 2021 | |
| Training set accuracy is lower than validation set accuracy for classification task | 7 | 1571 | April 14, 2022 | |
| TAO Classification provides low precision with VehicleTypeNet pretrained model | 2 | 397 | October 13, 2022 | |
| Error while re-training with custom dataset using tlt file- FasterRCNN | 5 | 364 | June 26, 2023 |