RSERSTM

Hello, When we say `training.pretrained_weights : imagenet`, it relates to the weigths of the `backbone`. This `backbone`, is trained for classification tasks by Google on a big dataset called `imagenet`....

`If I had multiple classes in my dataset, I would not be able to use the ssd_mobilenet_v2_fpnlite_035_416.h5` -> yes exactly that is correct. `But if I'm only providing training.pretrained_weights: imagenet...

Hello ChloeCarbonniere, What do you mean by ` transforme-based models` ? Transformer-based models ? Attention layers ? Encoder-only computer vision models ? Generative models ? Thank you,

Ok I understand. For info STM32N6-DK has `128MB of Flash` to store weights and RAM (`internal 4.2MB + external 32MB`) to store activations(the data) https://www.st.com/en/evaluation-tools/stm32n6570-dk.html. In other words regarding these...

> [@RSERSTM](https://github.com/RSERSTM) What do we need in order to run a transformer-based model? Don't we need to implement a "transformer runner" first? Well, what do you mean by `transformer-based models`...

> > > [@RSERSTM](https://github.com/RSERSTM) What do we need in order to run a transformer-based model? Don't we need to implement a "transformer runner" first? > > > > > >...

Hello Cypamigon, After some investigations with the provided yaml file we couldn't replicate the issue regarding `best_weights.h5` not being present in `/experiments_outputs/"%Y_%m_%d_%H_%M_%S"/saved_models/` . Because you are on Windows maybe you...

Ok, another explanation could be that the `ssd_mobilenet_v2_fpnlite_035_416.h5` model we provide, trained on `person detection` kept the information about its previous training especially `the best val_loss`. And when you try...