Usually it is due to network. For example, the YOLO network downsamples the input by 32, so it is needed to make sure the width and height is a multiple of 32.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Optimal width and height of the images | 4 | 482 | December 5, 2021 | |
| Tiling and image size | 6 | 365 | September 19, 2023 | |
| TAO input image resizing | 9 | 1210 | April 18, 2022 | |
| Queries regarding Anchor shape and Resizing of image | 3 | 461 | December 21, 2021 | |
| Maximum input dimensions | 2 | 366 | July 18, 2023 | |
| Relationship between training dataset size and inference data size | 12 | 742 | February 22, 2022 | |
| TLT yolo_v4 image resizer during evaluation | 2 | 390 | October 12, 2021 | |
| Another clarification about the image size parameter | 5 | 639 | December 30, 2022 | |
| Questions regarding the preparation of images for training yolo_v4 model on TAO toolkit | 5 | 589 | January 17, 2024 | |
| Image size- DetectNet_v2 | 4 | 900 | January 21, 2023 |