Some Bugs on running the 3D Reconstruction from Single and Multi-view Images Project on the Colab page

I am trying to run the below GitHub project on this colab page:

Context-aware 3D Reconstruction from Single and Multi-view Images

But at the config.py file of it i have some bugs as you cans see below:

Use config:  {'CONST': {'BATCH_SIZE': 64,             'CROP_IMG_H': 128,             'CROP_IMG_W': 128,             'DEVICE': '0',             'IMG_H': 224,             'IMG_W': 224,             'N_VIEWS_RENDERING': 1,             'N_VOX': 32,             'RNG_SEED': 0,             'WEIGHTS': '/content/Pix2Vox/model.pth'},   'DATASET': {'MEAN': [0.5, 0.5, 0.5],               'STD': [0.5, 0.5, 0.5],               'TEST_DATASET': 'ShapeNet',               'TRAIN_DATASET': 'ShapeNet'},   'DATASETS': {'PASCAL3D': {'ANNOTATION_PATH': '/home/hzxie/Datasets/PASCAL3D/Annotations/%s_imagenet/%s.mat',                             'RENDERING_PATH': '/home/hzxie/Datasets/PASCAL3D/Images/%s_imagenet/%s.JPEG',                             'TAXONOMY_FILE_PATH': './datasets/Pascal3D.json',                             'VOXEL_PATH': '/home/hzxie/Datasets/PASCAL3D/CAD/%s/%02d.binvox'},                'PIX3D': {'ANNOTATION_PATH': '/home/hzxie/Datasets/Pix3D/pix3d.json',                          'RENDERING_PATH': '/home/hzxie/Datasets/Pix3D/img/%s/%s.%s',                          'TAXONOMY_FILE_PATH': './datasets/Pix3D.json',                          'VOXEL_PATH': '/home/hzxie/Datasets/Pix3D/model/%s/%s/%s.binvox'},                'SHAPENET': {'RENDERING_PATH': '/home/hzxie/Datasets/ShapeNet/ShapeNetRendering/%s/%s/rendering/%02d.png',                             'TAXONOMY_FILE_PATH': './datasets/ShapeNet.json',                             'VOXEL_PATH': '/home/hzxie/Datasets/ShapeNet/ShapeNetVox32/%s/%s/model.binvox'}},   'DIR': {'OUT_PATH': './output',           'RANDOM_BG_PATH': '/home/hzxie/Datasets/SUN2012/JPEGImages'},   'NETWORK': {'LEAKY_VALUE': 0.2,               'TCONV_USE_BIAS': False,               'USE_MERGER': True,               'USE_REFINER': True},   'TEST': {'RANDOM_BG_COLOR_RANGE': [[240, 240], [240, 240], [240, 240]],            'VOXEL_THRESH': [0.2, 0.3, 0.4, 0.5]},   'TRAIN': {'BETAS': [0.9, 0.999],             'BRIGHTNESS': 0.4,             'CONTRAST': 0.4,             'DECODER_LEARNING_RATE': 0.001,             'DECODER_LR_MILESTONES': [150],             'ENCODER_LEARNING_RATE': 0.001,             'ENCODER_LR_MILESTONES': [150],             'EPOCH_START_USE_MERGER': 0,             'EPOCH_START_USE_REFINER': 0,             'GAMMA': 0.5,             'MERGER_LEARNING_RATE': 0.0001,             'MERGER_LR_MILESTONES': [150],             'MOMENTUM': 0.9,             'NOISE_STD': 0.1,             'NUM_EPOCHES': 250,             'NUM_WORKER': 4,             'POLICY': 'adam',             'RANDOM_BG_COLOR_RANGE': [[225, 255], [225, 255], [225, 255]],             'REFINER_LEARNING_RATE': 0.001,             'REFINER_LR_MILESTONES': [150],             'RESUME_TRAIN': False,             'SATURATION': 0.4,             'SAVE_FREQ': 10,             'UPDATE_N_VIEWS_RENDERING': False}}  [FATAL] 2021-05-01 03:17:39.047988 Please specify the file path of checkpoint.  [INFO/MainProcess] process shutting down  

as it sad on its GitHub readme file about the datasets i guess i must to download some pretrained models, and give their folder location to config file.

So, Because The Config.py file contain model files and it takes time to find them, i prefer to ask about it and after that do it, the necessary model files on config.py file could be shown below:

'DATASETS': {'PASCAL3D': {'ANNOTATION_PATH': '/home/hzxie/Datasets/PASCAL3D/Annotations/%s_imagenet/%s.mat',                             'RENDERING_PATH': '/home/hzxie/Datasets/PASCAL3D/Images/%s_imagenet/%s.JPEG',                             'TAXONOMY_FILE_PATH': './datasets/Pascal3D.json',                             'VOXEL_PATH': '/home/hzxie/Datasets/PASCAL3D/CAD/%s/%02d.binvox'},                'PIX3D': {'ANNOTATION_PATH': '/home/hzxie/Datasets/Pix3D/pix3d.json',                          'RENDERING_PATH': '/home/hzxie/Datasets/Pix3D/img/%s/%s.%s',                          'TAXONOMY_FILE_PATH': './datasets/Pix3D.json',                          'VOXEL_PATH': '/home/hzxie/Datasets/Pix3D/model/%s/%s/%s.binvox'},                'SHAPENET': {'RENDERING_PATH': '/home/hzxie/Datasets/ShapeNet/ShapeNetRendering/%s/%s/rendering/%02d.png',                             'TAXONOMY_FILE_PATH': './datasets/ShapeNet.json',                             'VOXEL_PATH': '/home/hzxie/Datasets/ShapeNet/ShapeNetVox32/%s/%s/model.binvox'}}  

Update:

I asked it on the main github project asle :

Some Bugs on running the 3D Reconstruction from Single and Multi-view Images Project on the Colab page ( Config.py File Problem)

Thanks.

https://stackoverflow.com/questions/67342739/some-bugs-on-running-the-3d-reconstruction-from-single-and-multi-view-images-pro May 01, 2021 at 11:55AM