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
Hello, I'm very interested in your work about FPN,but When I try to debug code,I using the image_demo script in the demo directory as well as using faster_rcnn_r50_opa_fpn_112_sml1_coco for config. However, it's report a error :
"FasterRCNN: 'OPA_FPN is not in the models registry'"
I have no idea,Hope you can give me a solution
The text was updated successfully, but these errors were encountered:
Thanks,I've solved this problem。
Now I want to ask, how to use the script in the code to debug. Because the image_demo script given in the source code, there are only have model initialization, image prediction and drawing prediction results.
I didn't find the implementation of preprocessing the input of a batch images, then model propagate and calculating loss.
In addition, README only gives the method of using .sh method to train as well as predict, and does not find how to call a script to debug the model. e.g. using one script of the source code to debug how does a batch image preprocess, propagate and compute loss?
Hello, I'm very interested in your work about FPN,but When I try to debug code,I using the image_demo script in the demo directory as well as using faster_rcnn_r50_opa_fpn_112_sml1_coco for config. However, it's report a error :
"FasterRCNN: 'OPA_FPN is not in the models registry'"
I have no idea,Hope you can give me a solution
The text was updated successfully, but these errors were encountered: