Turgut

I get the following with ```to_fp16```: ``` Error in py_call_impl(callable, dots$args, dots$keywords) : AssertionError: Mixed-precision training requires a GPU, remove the call `to_fp16` Detailed traceback: File "/home/turgut/.local/share/r-miniconda/envs/r-reticulate/lib/python3.6/site-packages/fastcore/logargs.py", line 56, in...

I probably installed the cpu version. Regarding your question I advise to run similar code from python side and see if it works. Btw, did it work without fp16? On...

I reintalled fastai and now it works fine with batch size == 10. This is the result for 1 epoch: ``` epoch train_loss valid_loss accuracy time ------ ----------- ----------- ---------...

This is my full code: ``` library(fastai) library(magrittr) df = data.table::fread("~/Downloads/plant/train.csv") df[['label']] = as.character(df[['label']]) smp = data.table::fread("~/Downloads/plant/sample_submission.csv") df = dplyr::sample_n(df,250) batch_tfms = list(RandomResizedCrop(256), #DeterministicDihedral(), #Warp(), Hue(), Saturation(), Hue(0.2, 0.5), aug_transforms(size...

I think it is a CUDA error. So, it is not related to the wrapper, IMO. Kaggle output also tells that: ``` Error in py_call_impl(callable, dots$args, dots$keywords): RuntimeError: CUDA out...

Hi. Did you manage to solve this issue?

Were you able to train the model with TPUs on Colab?

Thanks, I am using the following package ```grid``` and it has an issue with rmarkdown. This is why you cannot see them (graphs/plots) while executing a cell ``` library(tiff) img

Could you do the same but with python and see that works as you intended? However, here is the path argument, could specify ur path here, as well? https://github.com/henry090/fastai/blob/a37c463c7ab9494729089924ac0f933439730651/R/image_loaders.R#L368-L373

Yes, I got it. I am not sure why. Could you run this code from the python side? If it works fine (same folder), then I can take a look