mirror of
https://github.com/nerfstudio-project/nerfstudio.git
synced 2026-11-21 07:05:44 +08:00
Terrance/tensorf (#218)
* added tensorf, updated requirements for windows * cleaning up imports * tensorf changes * initial working version of tensorf * added callback for feature upsampling * modifying tests to match changes * reverting requirements changes * reverting unnecessary changes * reverting unnecessary changes * no more upsampling on step 0 * removed density field, fixed error msg * modified callbacks and upsampling, reinitializing optimzer in training loop * deleting tensorf_field file" * checkpointing progress on restructuring callbacks * updated callback logic for before and after train capabilities * fixing upsampling stepping * merging * adding tensorf to config, fixing some bugs with new callback * changed the way callbacks detected steps argument in callback func * fixing typing * adding pylint disable no self use to get_training_callbacks * fixing config * changing callback in vanilla nerf to allow for no density field * cleanup * removing config yaml Co-authored-by: Ethan Weber <eweb0124@gmail.com>
This commit is contained in:
1 parent
6ee6934581
commit
8670f19d2d
13 files changed
+394
-52
No files matched your search
@@ -29,11 +29,14 @@ from torch.cuda.amp.grad_scaler import GradScaler
|
||||
from torch.nn.parallel import DistributedDataParallel as DDP
|
||||
|
||||
from nerfactory.configs import base as cfg
|
||||
from nerfactory.dataloaders.structs import DatasetInputs
|
||||
from nerfactory.optimizers.optimizers import Optimizers, setup_optimizers
|
||||
from nerfactory.pipelines.base import Pipeline
|
||||
from nerfactory.utils import profiler, writer
|
||||
from nerfactory.utils.callbacks import Callback
|
||||
from nerfactory.utils.callbacks import (
|
||||
TrainingCallback,
|
||||
TrainingCallbackAttributes,
|
||||
TrainingCallbackLocation,
|
||||
)
|
||||
from nerfactory.utils.decorators import check_main_thread
|
||||
from nerfactory.utils.writer import EventName, TimeWriter
|
||||
from nerfactory.viewer.server import viewer_utils
|
||||
@@ -76,8 +79,6 @@ class Trainer:
|
||||
if self.device == "cpu":
|
||||
self.mixed_precision = False
|
||||
logging.warning("Mixed precision is disabled for CPU training.")
|
||||
# dataset variables
|
||||
self.dataset_inputs_train: DatasetInputs
|
||||
# model variables
|
||||
self.pipeline: Pipeline
|
||||
self.optimizers: Optimizers
|
||||
@@ -89,7 +90,7 @@ class Trainer:
|
||||
banner_messages = [f"Viewer at: {self.visualizer_state.viewer_url}"]
|
||||
self.grad_scaler = GradScaler(enabled=self.mixed_precision)
|
||||
# training callbacks
|
||||
self.callbacks: List[Callback]
|
||||
self.callbacks: List[TrainingCallback]
|
||||
# logging variables
|
||||
writer.setup_event_writers(
|
||||
config.logging, max_iter=config.trainer.max_num_iterations, banner_messages=banner_messages
|
||||
@@ -113,8 +114,9 @@ class Trainer:
|
||||
)
|
||||
dist.barrier(device_ids=[self.local_rank])
|
||||
|
||||
# TODO(ethan): do this for pipeline, not pipeline.model
|
||||
self.callbacks = self.pipeline.model.get_training_callbacks()
|
||||
self.callbacks = self.pipeline.get_training_callbacks(
|
||||
TrainingCallbackAttributes(optimizers=self.optimizers, grad_scaler=self.grad_scaler, pipeline=self.pipeline)
|
||||
)
|
||||
|
||||
def train(self) -> None:
|
||||
"""Train the model."""
|
||||
@@ -126,10 +128,17 @@ class Trainer:
|
||||
num_iterations = self.config.trainer.max_num_iterations
|
||||
for step in range(self.start_step, self.start_step + num_iterations):
|
||||
|
||||
# Note: if visualizer used, the rendering of the visualizer will be included in the iteration train time
|
||||
# if the visualizer used, the rendering of the visualizer will be included in the iteration train time
|
||||
with TimeWriter(writer, EventName.ITER_TRAIN_TIME, step=step) as t:
|
||||
|
||||
# training callbacks before the training iteration
|
||||
for callback in self.callbacks:
|
||||
callback.run_callback_at_location(
|
||||
step, location=TrainingCallbackLocation.BEFORE_TRAIN_ITERATION
|
||||
)
|
||||
|
||||
loss_metric_dict = self.train_iteration(step)
|
||||
with TimeWriter(writer, EventName.ITER_VIS_TIME, step=step) as t:
|
||||
with TimeWriter(writer, EventName.ITER_VIS_TIME, step=step) as _:
|
||||
self.visualizer_state.update_scene(step, self.pipeline.model)
|
||||
|
||||
train_num_rays_per_batch = self.config.pipeline.dataloader.train_num_rays_per_batch
|
||||
@@ -219,10 +228,7 @@ class Trainer:
|
||||
self.grad_scaler.scale(loss).backward() # type: ignore
|
||||
self.optimizers.optimizer_scaler_step_all(self.grad_scaler)
|
||||
self.grad_scaler.update()
|
||||
|
||||
self.optimizers.scheduler_step_all(step)
|
||||
for callback in self.callbacks:
|
||||
callback.after_step(step)
|
||||
|
||||
# Merging loss and metrics dict into a single output.
|
||||
loss_dict["loss"] = loss
|
||||
|
||||
Reference in new issue
Block a user