You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thanks for open-sourcing the code of your great work! Looks like there are some bugs when running the current tools/inference.py.
When using the configs/bdd100k/qdtrack-frcnn_r50_fpn_12e_bdd100k.py as config and qdtrack-frcnn_r50_fpn_12e_bdd100k-13328aed.pth as the checkpoint (from the google drive link provided in the README file), the model and loaded state dict do not match exactly. Looks like you updated the name of layers but didn't update the definition of the pre-trained model. Manually changing the layer names in the .pth file will work.
you can write a simple script to modify the keys of the state_dict and overwrite the .pth file. The only difference if you notice is the extra prefix 'detector'.
Hi,
Thanks for open-sourcing the code of your great work! Looks like there are some bugs when running the current
tools/inference.py
.When using the
configs/bdd100k/qdtrack-frcnn_r50_fpn_12e_bdd100k.py
as config andqdtrack-frcnn_r50_fpn_12e_bdd100k-13328aed.pth
as the checkpoint (from the google drive link provided in the README file), the model and loaded state dict do not match exactly. Looks like you updated the name of layers but didn't update the definition of the pre-trained model. Manually changing the layer names in the.pth
file will work.The text was updated successfully, but these errors were encountered: