This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| mAP training several classes = 0.0 and so low with data custom using detectnet_v2 (resnet_18)) | 33 | 491 | February 1, 2024 | |
| TLT-Train DetectNetv2 ResNet18 always give mAP 0% at target class | 11 | 489 | October 26, 2022 | |
| Reduced Accuracy when importing SSD model from TLT into DeepStream | 4 | 539 | October 12, 2021 | |
| mAP=0 error | 7 | 1372 | October 12, 2021 | |
| SSD loss possible int overflow on one computer, but not the other | 14 | 653 | October 12, 2021 | |
| Getting 0 mAP for detectnet_v2 model over 150 epochs | 14 | 59 | January 11, 2025 | |
| TLT trained model accuracy worse after deployment | 11 | 834 | October 12, 2021 | |
| Unable to retrain pre-trained SSD Mobilenet v1 | 4 | 429 | October 12, 2021 | |
| Performance difference between various tlt models while deploying on deepstream. | 8 | 752 | October 12, 2021 | |
| FasterRCNN evaluation when validation set contains just one class and the model was trained with 80 classes | 11 | 516 | December 4, 2021 |