Issue with build_coordinates.py about ffn HOT 9 OPEN

I realized the home path doesn't work in this context, I have fixed it by changing:
--partition_volumes ~/third_party/neuroproof_examples/validation_sample/af.h5:af
to
--partition_volumes validation1:/home/user/third_party/neuroproof_examples/validation_sample/af.h5:af

from ffn.

I realized the home path doesn't work in this context, I have fixed it by changing:
--partition_volumes ~/third_party/neuroproof_examples/validation_sample/af.h5:af
to
--partition_volumes validation1:/home/user/third_party/neuroproof_examples/validation_sample/af.h5:af

Can you get the results in the paper?

from ffn.

I didn't reproduce the exact demo data in the paper because it's a different species than what I'm interested in but it performs great on my data.

from ffn.

I didn't reproduce the exact demo data in the paper because it's a different species than what I'm interested in but it performs great on my data.

Run_inference.py can get the result of each 2D segmentation ,but how to reconstruct the result of 3D segmentation?

from ffn.

I'm not sure what you're asking. FFN is a 3D solver, the output is 3D.

from ffn.

I'm not sure what you're asking. FFN is a 3D solver, the output is 3D.

Output shape is (250, 250, 250)，it shows that 250(numbers) x 2D segmentation(w:250,h:250).

from ffn.

I didn't reproduce the exact demo data in the paper because it's a different species than what I'm interested in but it performs great on my data.

HELLO，
There is no validation set in the code. How do you determine if your training results are great?

from ffn.

Hi @MatthewBM , @mk123qwe do you know how to run ffn on a dataset of about 5TB?

from ffn.

Hi @FrayaMiner,

Why don't you send me an email [email protected] with a little more detail about what you're trying to do.

from ffn.