-
Notifications
You must be signed in to change notification settings - Fork 44
Cannot find the 'metadata.csv' #24
Comments
You need to generate it first by running neptune run --config configs/neptune.yaml main.py prepare_metadata remember to specify the paths in the Thanks for spotting this. The Readme.md was missing this part of the instruction. |
How to generate metadata.csv using python only? when I am running below command: I am getting error:
|
@saurabh502 |
@jakubczakon |
Hi - could you clarify where the metadata.csv file should be? I eventually got the prepare_metadata step running in the cloud, which has put the metadata.csv file into SAL-10\output\metadata.csv I then changed the neptune.yaml file back to "metadata_filepath: /input/metadata.csv" as per the instructions and ran the line to train the network, but this comes up with an error: "You cannot use input that is not in Neptune storage." Does the command line to train the network need to include "SAL-10" somewhere? Plus the metadata.csv file is sitting in the output directory of SAL-10 - does it need to move to an input directory? Thanks |
Hi @LisburnLad There was a typo-like mistake in the command. It should indeed, contain the reference to SAL-10 neptune send
--worker m-p100 \
--environment pytorch-0.3.1-gpu-py3 \
--config configs/neptune.yaml \
--input /SAL-10/output/metadata.csv \
main.py train --pipeline_name unet Should work in your case. |
* Hypercolumn (#16) * fixed lovash loss, added helpers for loss weighing (#14) * updated results exploration, added unet with hypercolumn * updated with lighter hypercolumn setup * Model average (#17) * added prediction average notebook * added simple average notebook * added replication pad instead of zero pad (#18) * changed to heng-like arch, added channel and spatial squeeze and excite, extended hypercolumn (#19) * Update unet_models.py typo in resnet unet fixed * added resnet 18 an50 pretrained options, unified hyper and vanilla in one class (#20) * Update models.py Changed old class import and namings * Loss design (#21) * local * initial * formated results * added focal, added border weighing, added size weighing added focus, added loss desing notebook * fixed wrong focal definition, updated loss api * exp with dropped borders * set best params, not using weighing for now * Dev depth experiments (#23) * add depth layer in input * reduce lr on plateau scheduler * depth channels transformer * fix reduce lr * bugfix * change default config * added adaptive threshold in callbacks (#24) * added adaptive threshold in callbacks * fix * added initial lr selector (#25) * Initial lb selector (#26) * added initial lr selector * small refactor * Auxiliary data small masks (#27) * exping * auxiliary data for border masks generated
After run the code, I'm sorry to find 'metadata.csv' does not exist. And I could not find it in the homepage of TGS. I was wondering how to solve this problem.
The text was updated successfully, but these errors were encountered: