search

BramSW / iccv_2019_few_shot_3d_wallace

11 stars 3 forks source link

Required packages #2

Open hamaadtahir opened 4 years ago

hamaadtahir commented 4 years ago

Required packages and their versions are missing from readme

BramSW commented 4 years ago

Please try the new requirements.txt and let me know how it does

hamaadtahir commented 4 years ago

Thankyou once again for your help. Now another issue that popped up is missing file "mode_to_cat_to_model_ids.pickle". It is referred in the line 228 of "highres_sampler.py"

BramSW commented 4 years ago

Added needed pickle files to pickle_files/ and changed paths. Thanks for bringing these to my attention.

hamaadtahir commented 4 years ago

Thankyou, how many epochs did you train it for?

BramSW commented 4 years ago

I believe that the default settings should be sufficient, if that doesn't quite reach reported performance try upping the # of epochs by a factor of 2-3

hamaadtahir commented 4 years ago

by default it is infinity

BramSW commented 4 years ago

https://github.com/BramSW/iccv_2019_few_shot_3d_wallace/blob/master/train_iterative_RGB_refiner.py#L39

This was updated in yesterday's reorg. Make sure you have the latest version pulled

hamaadtahir commented 4 years ago

Thanks, now just a final thing, how do I test a novel category image using a prior once a model has been trained, and where does it save the trained model.

BramSW commented 4 years ago

It saves to the path provided in --save-path (e.g. --save-path my_refiner.h5)

To test the model with a new image/prior simply load the model and feed in the images/voxel priors as in https://github.com/BramSW/iccv_2019_few_shot_3d_wallace/blob/master/train_iterative_RGB_refiner.py#L191

hamaadtahir commented 4 years ago

I am sorry i didnt follow your response regarding the loading of model using the same script that was earlier used for training. Could you give a hint for what argument switches to use for testing using new image/prior when running the same script file

hamaadtahir commented 4 years ago

And does this "--num-refine-iters" switch refers to the iterative training

ChenHsing commented 3 years ago

what does --num-refine-iters means and what number should I set to this value

BramSW commented 3 years ago

Hi, the --num-refine-iters refers to how many iterations to run during training/inference. As noted in the paper, we found just 1 iteration to suffice for most performance purposes, but the higher-iteration refiners do exhibit interesting performance as noted in our figures. Hope that helps!