Refer to “freeze_blocks” in MaskRCNN - NVIDIA Docs
What do you mean viewing the json file?
Below is an example. When train on COCO dataset, the spec is inside this topic.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| MaskRCNN Input to reshape is a tensor with 3135248 values, but the requested shape has 2691200 | 38 | 1120 | May 9, 2023 | |
| Mask_rcnn shows training logs loss 0.00000 fast_rcnn class loss: 0.00000 fast_rcnn box loss: 0.00000 | 22 | 798 | August 16, 2022 | |
| Requested more than 0 entries, but params is empty. Params shape: [0,1920,1080] | 23 | 1831 | March 1, 2022 | |
| Poor metric results after retraining maskrcnn using TLT notebook | 23 | 2396 | August 3, 2021 | |
| Training Custom FasterRCNN resnet50 Object detection issue | 9 | 1108 | October 12, 2021 | |
| Training multi-class UNet does not converge | 31 | 2918 | October 12, 2021 | |
| BodyPoseNet trained with custom dataset not detecting | 21 | 825 | June 6, 2022 | |
| Permission denied: 'mrcnn_log.json' while converting data into tfrecords | 9 | 893 | August 16, 2022 | |
| Multi GPU's and invalid loss | 18 | 1165 | July 19, 2022 | |
| Train with my own tlt model | 14 | 704 | December 13, 2021 |