core/options.py

# SPDX-FileCopyrightText: Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

import tyro
from dataclasses import dataclass
from typing import Tuple, Literal, Dict, Optional


@dataclass
class Options:
    ### model
    # Unet image input size
    input_size: int = 256
    # Unet definition
    down_channels: Tuple[int, ...] = (64, 128, 256, 512, 1024, 1024)
    down_attention: Tuple[bool, ...] = (False, False, False, True, True, True)
    mid_attention: bool = True
    up_channels: Tuple[int, ...] = (1024, 1024, 512, 256)
    up_attention: Tuple[bool, ...] = (True, True, True, False)
    # Unet output size, dependent on the input_size and U-Net structure!
    splat_size: int = 64
    # gaussian render size
    output_size: int = 256

    ### dataset
    # data mode (only support s3 now)
    data_mode: str = '4d'
    # fovy of the dataset
    fovy: float = 49.1
    # camera near plane
    znear: float = 0.5
    # camera far plane
    zfar: float = 2.5
    # number of all views (input + output)
    num_views: int = 12
    # number of views
    num_input_views: int = 4
    # camera radius
    cam_radius: float = 1.5 # to better use [-1, 1]^3 space
    # num workers
    num_workers: int = 16
    datalist: str=''

    ### training
    # workspace
    workspace: str = './workspace'
    # resume
    resume: Optional[str] = None
    # batch size (per-GPU)
    batch_size: int = 8
    # gradient accumulation
    gradient_accumulation_steps: int = 1
    # training epochs
    num_epochs: int = 30
    # lpips loss weight
    lambda_lpips: float = 1.0
    # gradient clip
    gradient_clip: float = 1.0
    # mixed precision
    mixed_precision: str = 'bf16'
    # learning rate
    lr: float = 4e-4
    # augmentation prob for grid distortion
    prob_grid_distortion: float = 0.5
    # augmentation prob for camera jitter
    prob_cam_jitter: float = 0.5
    # number of gaussians per pixel
    gaussian_perpixel: int = 1

    ### testing
    # test image path
    test_path: Optional[str] = None

    ### misc
    # nvdiffrast backend setting
    force_cuda_rast: bool = False
    # render fancy video with gaussian scaling effect
    fancy_video: bool = False

    # 4D
    num_frames: int = 8
    use_temp_attn: bool = True
    shuffle_input: bool = True
    
    # s3
    sample_by_anim: bool = True

    # interp
    interpresume: Optional[str] = None
    interpolate_rate: int = 3
    

# all the default settings
config_defaults: Dict[str, Options] = {}
config_doc: Dict[str, str] = {}

config_doc['lrm'] = 'the default settings for LGM'
config_defaults['lrm'] = Options()


config_doc['big'] = 'big model with higher resolution Gaussians'
config_defaults['big'] = Options(
    input_size=256,
    up_channels=(1024, 1024, 512, 256, 128), # one more decoder
    up_attention=(True, True, True, False, False),
    splat_size=128,
    output_size=512, # render & supervise Gaussians at a higher resolution.
    batch_size=1,
    num_views=8,
    gradient_accumulation_steps=1,
    mixed_precision='bf16',
    resume='pretrained/model_fp16_fixrot.safetensors',
)


AllConfigs = tyro.extras.subcommand_type_from_defaults(config_defaults, config_doc)