search

CosmiQ / solaris

CosmiQ Works Geospatial Machine Learning Analysis Toolkit
https://solaris.readthedocs.io
Apache License 2.0
413 stars 112 forks source link

[BUG]: (num_samples should be a positive integer value, but got num_samples=0) from Colab #396

Open Servando1990 opened 4 years ago

Servando1990 commented 4 years ago

Summary of the bug

Getting a Pytorch error num_samples should be a positive integer value but got num_samples=0. when using INRIA dataset to reproduce Fine-tuning notebook from the tutorial Solaris_FOSS4G_2019

Checking Pytorch forums and issues this is due to a wrong path to training data
https://github.com/thstkdgus35/EDSR-PyTorch/issues/185

PATH to training csv: training_data_csv: '/content/drive/My Drive/solaris/solaris_tutorials/Solaris_FOSS4G_2019/data/workshop_configs/inria_train.csv'

Screenshots

Training CSV structure

image

Environment information

Shikib commented 4 years ago

In my case, I solved this issue (albeit in a different setting) by setting the block_size to 512. If the block_size is unspecified, it seems that the tokenizer's maximum size is used and since sometimes that can be really large -- the result is an empty dataset.

Servando1990 commented 4 years ago

Hi @Shikib !

Do you mean block_size within the yml file?

Can't find this argument in the yml skeleton image