Hardware requirements for Deepcell for training model on full HeLa_S3.npz dataset

[manugarciaquismondo]

Greetings,

I have deployed the Deepcell notebook example Interior-Edge Segmentation 2D Fully Convolutional.ipynb on Google Colab. When I try to load the dataset HeLa_S3.npz from Deepcell's AWS example bucket, the computing environment runs out of memory and crashes. Can you please advise on the recommended hardware requirements on which Deepcell has been proven to work for this notebook, so that I can set up a computing environment that meets these requirements and run Deepcell?

Thank you very much,

@manugarciaquismondo and @cornhundred

[willgraf]

We ran these notebooks on our own NVIDIA DGX station, on one GPU with 16GB of memory.

The HeLaS3 dataset is almost 6 GB. If you are unable to load the data into memory, we also have hosted the following 2 datasets which are both under 2GB:

3T3_NIH.npz

HEK293.npz

---

These are the smallest datasets we have hosted currently.

[manugarciaquismondo]

Greetings,

I have downsampled the HeLa dataset to 1500 images and now it works fine on my notebook on Google Colab. I will close the issue now.

Thank you very much,