Commits on Apr 10, 2021

1. Tensorboard model visualization bug fix …

   This fix should allow for visualizing YOLOv5 model graphs correctly in Tensorboard by uncommenting line 335 in train.py:
   ```python
                       if tb_writer:
                           tb_writer.add_graph(torch.jit.trace(model, imgs, strict=False), [])  # add model graph
   ```
   
   The problem was that the detect() layer checks the input size to adapt the grid if required, and tracing does not seem to like this shape check (even if the shape is fine and no grid recomputation is required). The following will warn:
   https://github.com/ultralytics/yolov5/blob/0cae7576a9241110157cd154fc2237e703c2719e/train.py#L335
   
   Solution is below. This is a YOLOv5s model displayed in TensorBoard. You can see the Detect() layer merging the 3 layers into a single output for example, and everything appears to work and visualize correctly.
   ```python
   tb_writer.add_graph(torch.jit.trace(model, imgs, strict=False), [])
   ```
   <img width="893" alt="Screenshot 2021-04-11 at 01 10 09" src="https://user-images.githubusercontent.com/26833433/114286928-349bd600-9a63-11eb-941f-7139ee6cd602.png">

   

   glenn-jocher committed Apr 10, 2021
   Configuration menu

   • View commit details
   • Copy full SHA for b1509fa
   • Browse repository at this point

   Copy the full SHA

   b1509fa View commit details

   Browse the repository at this point in the history