Amir Hassanzadeh
Amir Hassanzadeh
it seems like it is not stalling it is extremely slow for some reason. I put a `print(i)`, where `i` is the validation data loader counter at the end of...
I figured this out, it seems like the voxelization exists for train_loader when fetching the data, but not for val_laoder, I am setting voxel_max = 10k so the data chunks...
still have the same problem even with smaller chunks. for 24 files of training it takes seconds, but for 24 files of validation it takes 25 minutes.
Thank you very much for this!
Unfortunately, I am still seeing the same behavior with python 3.11. I am able to run it with 500 iterations and sampling 1000 from my dataset, but anything above that...
I am using PySR 1.4. below is my code: ``` df = pd.read_csv("data.csv") x = np.vstack([df["w"].to_numpy(), df["T1"].to_numpy() - df["T2"].to_numpy(), (df["e1"].to_numpy() + df["e2"].to_numpy())/2, df["e1"].to_numpy() - df["e2"].to_numpy()] ).T.astype(np.float32) y = df['error'].to_numpy() from...
had the same problem, I had nan in my colors in the dataset.