Closed Brainkite closed 2 years ago
That is very strange indeed. Can you provide a colab notebook training on a simple dataset (maybe fridge?) that reproduces the issue?
That is very strange indeed. Can you provide a colab notebook training on a simple dataset (maybe fridge?) that reproduces the issue?
Okay, finally took the time to reproduce it in one of your Colab Nbs: https://colab.research.google.com/drive/1MkvqCjobGyateYeOXsEZsc_xg5CyANrH?usp=sharing
The issue can be witnessed here: https://colab.research.google.com/drive/1MkvqCjobGyateYeOXsEZsc_xg5CyANrH?authuser=1#scrollTo=s8hnDq1WKgx0&line=1&uniqifier=1
@lgvaz Any update on this?
@Brainkite does this issue persist even using icevision from master?
Closing due to lack of activity.
I've managed to train an mmdet Retinanet RN50 to a specific task with decent performances. But when I load the weights on a fresh model and a fresh kernel to perform just predictions, predictions are very poor compared to the trained and saved model, almost non of them is above det threshold. But for some reason, doing 1 epoch of training with the model and then loading the desired weights, resolves the issue and the model performs as expected.
This performs poor:
This performs properly:
Icevision 0.8.1 pytorch 1.8.0 torchvision 0.9.0 fastai 2.3.1 python 3.8.10 Ubuntu 18.04.5