Pramay

> Training images are upscaled here: > > https://github.com/Wovchena/text-detection-fots.pytorch/blob/04b969c87491630dce38cdb48932aa33115798c6/datasets.py#L32 > > I think the model doesn't work for size of 384 because it was trained for a larger scale. You...

```python export_model.py -c configs/det/det_r50_vd_east.yml``` I was able to resolve the shape error. But am getting this error now ``` E0407 23:29:26.869138 13973 helper.h:84] Assertion failed: cublasStatus == CUBLAS_STATUS_SUCCESS ../rtSafe/cublas/cublasLtWrapper.cpp:279 Aborting......

@maclandrol yes I was able to train the model and perform inferencing.

@maclandrol you can check my repo [here](https://github.com/QuickLearner171998/Retrosynthesis-Reaction-Pathway). Performance was pretty good for my use case at least.