lightly-train 0.2.2__tar.gz → 0.2.4__tar.gz

lightly_train-0.2.4/.github/pull_request_template.md

@@ -0,0 +1,7 @@
+## What has changed and why?
+
+(Delete this: Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change.)
+
+## How has it been tested?
+
+(Delete this: Please describe the tests that you ran to verify your changes. Provide instructions so we can reproduce. Please also list any relevant details for your test configuration.)

{lightly_train-0.2.2 → lightly_train-0.2.4}/.github/workflows/build_docker_image.yml

@@ -52,7 +52,7 @@ jobs:
         if: ${{ needs.build-docker-image.result == 'success' }}
         uses: rtCamp/action-slack-notify@v2
         env:
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK_RELEASES }}
+          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK_RELEASES_DEV }}
           SLACK_ICON_EMOJI: ":train:"
           SLACK_USERNAME: "Build of LightlyTrain Docker Image"
           SLACK_COLOR: "good"
@@ -71,7 +71,7 @@ jobs:
         if: ${{ needs.build-docker-image.result != 'success' }}
         uses: rtCamp/action-slack-notify@v2
         env:
-          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK_RELEASES }}
+          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK_RELEASES_DEV }}
           SLACK_ICON_EMOJI: ":x:"
           SLACK_USERNAME: "Build of LightlyTrain Docker Image"
           SLACK_COLOR: "danger"

{lightly_train-0.2.2 → lightly_train-0.2.4}/.gitignore

@@ -1,5 +1,6 @@
 *.code-workspace
 lightly_train_docker_test_data
+out
 
 # Created by https://www.toptal.com/developers/gitignore/api/macos,windows,linux,python
 # Edit at https://www.toptal.com/developers/gitignore?templates=macos,windows,linux,python

{lightly_train-0.2.2 → lightly_train-0.2.4}/DOCS.md

@@ -27,12 +27,20 @@ lightly_train.train(
 
 In most cases you only have to specify `out`, `data`, and `model`. The rest is optional.
 
-The training process can be monitored with TensorBoard (requires 
-`pip install lightly-train[tensorboard]`):
+You can monitor your training process with the help of `tensorboard` and `wandb` loggers:
 ```
-tensorboard --logdir my_output_dir
+pip install "lightly-train[tensorboard, wandb]"
 ```
 
+Configure the loggers from Python:
+* `loggers={"tensorboard": True}`: Enable `tensorboard` logger with default arguments.
+* `loggers={"wandb": True}`: Enable `wandb` logger with default arguments.
+* `loggers={"wandb": {"project": "my-project"}}`: Configure `wandb` logger with custom arguments.
+
+LightlyTrain uses the PyTorchLightning loggers under the hood. Learn more about their configuration:
+* https://lightning.ai/docs/pytorch/stable/api/lightning.pytorch.loggers.wandb.html
+* https://lightning.ai/docs/pytorch/stable/api/lightning.pytorch.loggers.tensorboard.html
+
 #### Exporting
 ```python
 import lightly_train
@@ -94,8 +102,21 @@ lightly-train train \
 
 In most cases you only have to specify `out`, `data`, and `model`. The rest is optional.
 
-The training process can be monitored with TensorBoard (requires 
-`pip install lightly-train[tensorboard]`):
+You can monitor your training process with the help of `tensorboard` and `wandb` loggers:
+```
+pip install "lightly-train[tensorboard, wandb]"
+```
+
+Configure the loggers from the command-line:
+* `loggers.tensorboard=True`: Enable `tensorboard` logger with default arguments.
+* `loggers.wandb=True`: Enable `wandb` logger with default arguments.
+* `loggers.wandb.project="my-project"`: Configure `wandb` logger with custom arguments.
+
+LightlyTrain uses the PyTorchLightning loggers under the hood. Learn more about their configuration:
+* https://lightning.ai/docs/pytorch/stable/api/lightning.pytorch.loggers.wandb.html
+* https://lightning.ai/docs/pytorch/stable/api/lightning.pytorch.loggers.tensorboard.html
+
+
 ```
 tensorboard --logdir my_output_dir
 ```

{lightly_train-0.2.2 → lightly_train-0.2.4}/Makefile

@@ -72,7 +72,7 @@ test:
 
 .PHONY: test-ci
 test-ci:
-	pytest tests --capture=no -v
+	pytest tests -v
 
 
 ### Virtual Environment
@@ -105,8 +105,8 @@ endif
 
 # SuperGradients is not compatible with Python>=3.10. It is also not easy to install
 # on MacOS. Therefore we exclude it from the default extras.
-EXTRAS = [dev,tensorboard,timm]
-DOCKER_EXTRAS = --extra tensorboard --extra timm 
+EXTRAS = [dev,tensorboard,timm,wandb]
+DOCKER_EXTRAS = --extra tensorboard --extra timm --extra wandb
 
 # Date until which dependencies installed with --exclude-newer must have been released.
 # Dependencies released after this date are ignored.

{lightly_train-0.2.2 → lightly_train-0.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: lightly_train
-Version: 0.2.2
+Version: 0.2.4
 Summary: Train models with self-supervised learning in a single command
 Author: Lightly Team
 License: AGPL-3.0
@@ -28,6 +28,8 @@ Provides-Extra: tensorboard
 Requires-Dist: tensorboard>=2.10.0; extra == "tensorboard"
 Provides-Extra: timm
 Requires-Dist: timm>=1.0.3; extra == "timm"
+Provides-Extra: wandb
+Requires-Dist: wandb>=0.12.10; extra == "wandb"
 
 # LightlyTrain
 

{lightly_train-0.2.2 → lightly_train-0.2.4}/docker/Dockerfile-amd64-cuda

@@ -4,10 +4,8 @@
 # Start FROM PyTorch image https://hub.docker.com/r/pytorch/pytorch
 FROM pytorch/pytorch:2.3.0-cuda11.8-cudnn8-runtime AS runtime
 
-# Set the environment variable for the volume mounting
-ENV LIGHTLY_TRAIN_IS_DOCKER="True" \
-    # Install packages into the system Python and skip creating a virtual environment.
-    UV_SYSTEM_PYTHON="true" \
+# Install packages into the system Python and skip creating a virtual environment.
+ENV UV_SYSTEM_PYTHON="true" \
     # Do not cache dependencies as they would also be saved in the docker image.
     UV_NO_CACHE="true"
 
@@ -19,8 +17,8 @@ WORKDIR /home/lightly_train
 
 # Install uv
 COPY Makefile /home/lightly_train
-
 RUN make install-uv
+
 # Add uv to PATH
 ENV PATH="/root/.cargo/bin:$PATH"
 
@@ -31,8 +29,9 @@ RUN make install-docker-dependencies
 # Copy the package itself
 COPY src /home/lightly_train/src
 
+# Set and create the directory to save pretrained torch models into
+ENV TORCH_HOME="/home/lightly_train/.cache/torch"
+RUN mkdir -p ${TORCH_HOME} && chmod -R a+w $TORCH_HOME
+
 # Install the package.
 RUN make install-docker
-
-# Default command that runs when the container starts.
-ENTRYPOINT ["lightly-train"]

{lightly_train-0.2.2 → lightly_train-0.2.4}/docker/Makefile

@@ -62,15 +62,28 @@ test:
 	@echo "Generate images"
 	mkdir -p $(LIGHTLY_TRAIN_DATA)
 	python -c 'from PIL import Image; [Image.new("RGB", (250, 300)).save(f"$(LIGHTLY_TRAIN_DATA)/{i}.png") for i in range(5)]'
+	@echo "Create output directory"
+	mkdir -p $(LIGHTLY_TRAIN_OUT)
+	chmod -R +rw $(LIGHTLY_TRAIN_OUT)
+	docker run --rm --shm-size=1g --user $(shell id -u):$(shell id -g) \
+		-v $(LIGHTLY_TRAIN_OUT):/out \
+		-v $(LIGHTLY_TRAIN_DATA):/data \
+		-v ./Makefile:/home/lightly_train/docker/Makefile \
+		--gpus all \
+		lightly/$(IMAGE):$(TAG) make test-cli-from-within-docker -C docker
+
+# This target is run from within the docker container
+test-cli-from-within-docker:
 	@echo "Test train"
-	docker run --rm --shm-size=1g --user $(id -u):$(id -g) -v $(LIGHTLY_TRAIN_OUT):/out -v $(LIGHTLY_TRAIN_DATA):/data lightly/$(IMAGE):$(TAG) train model="torchvision/convnext_small" epochs=2 batch_size=2
-	test -f $(LIGHTLY_TRAIN_OUT)/checkpoints/last.ckpt
+	lightly-train train data=/data out=/out model="torchvision/convnext_small" epochs=2 batch_size=2 model_args.weights="IMAGENET1K_V1" devices=2
+	test -f /out/checkpoints/last.ckpt
+	test `grep -c "GPU available: True (cuda), used: True" /out/train.log` -gt 0
 	@echo "Test embed"
-	docker run --rm --shm-size=1g --user $(id -u):$(id -g) -v $(LIGHTLY_TRAIN_OUT):/out -v $(LIGHTLY_TRAIN_DATA):/data lightly/train:$(TAG) embed out="/out/embeddings.csv" checkpoint="/out/checkpoints/last.ckpt" batch_size=2 format="csv"
-	test `wc -l < $(LIGHTLY_TRAIN_OUT)/embeddings.csv` -eq 6
+	lightly-train embed data=/data out="/out/embeddings.csv" checkpoint="/out/checkpoints/last.ckpt" batch_size=2 format="csv"
+	test `wc -l < /out/embeddings.csv` -eq 6
 	@echo "Test export"
-	docker run --rm --shm-size=1g --user $(id -u):$(id -g) -v $(LIGHTLY_TRAIN_OUT):/out -v $(LIGHTLY_TRAIN_DATA):/data lightly/train:$(TAG) export out="/out/model.pth" checkpoint="/out/checkpoints/last.ckpt" part="model" format="torch_state_dict"
-	test -f $(LIGHTLY_TRAIN_OUT)/model.pth
+	lightly-train export out="/out/model.pth" checkpoint="/out/checkpoints/last.ckpt" part="model" format="torch_state_dict"
+	test -f /out/model.pth
 
 
 

{lightly_train-0.2.2 → lightly_train-0.2.4}/docker/README.md

@@ -21,7 +21,20 @@ TODO
 
 ## Usage
 
-TODO
+First, start the docker container in interactive mode by using the -it flag. Furthermore,
+you must mount the directories you want to use.
+
+```
+docker run -it --gpus=all --user $(id -u):$(id -g) -v /my_data_dir:/data -v /my_output_dir:/out lightly/train:latest
+```
+
+Then all the usual CLI commands are fully available. E.g. run 
+
+```
+lightly-train train data="/data" out="/out" model="torchvision/convnext_small" method=dino
+```
+
+
 
 
 ## Development

{lightly_train-0.2.2 → lightly_train-0.2.4}/pyproject.toml

@@ -52,6 +52,9 @@ tensorboard = [
 timm = [
     "timm>=1.0.3",
 ]
+wandb = [
+    "wandb>=0.12.10", # required by pytorch-lightning
+]
 
 [project.scripts]
 lightly-train = "lightly_train._cli:_cli_entrypoint"
@@ -89,3 +92,7 @@ known-first-party = ["lightly_train"]
 [tool.ruff.lint.pydocstyle]
 # Use Google-style docstrings.
 convention = "google"
+
+[tool.ruff.lint.per-file-ignores]
+# Ignore `E402` (import violations) in root `__init__.py`.
+"src/lightly_train/__init__.py" = ["E402"]

{lightly_train-0.2.2 → lightly_train-0.2.4}/src/lightly_train/__init__.py

@@ -5,6 +5,14 @@
 # This source code is licensed under the license found in the
 # LICENSE file in the root directory of this source tree.
 #
+
+# Disable beta transforms warning by torchvision.
+# See https://stackoverflow.com/questions/77279407
+# TODO(Philipp, 09/24): Remove this once the warning is removed.
+import torchvision
+
+torchvision.disable_beta_transforms_warning()
+
 from lightly_train._commands.embed import embed
 from lightly_train._commands.export import ModelFormat, ModelPart, export
 from lightly_train._commands.train import train
@@ -23,4 +31,4 @@ __all__ = [
     "train",
 ]
 
-__version__ = "0.2.2"
+__version__ = "0.2.4"

lightly_train-0.2.4/src/lightly_train/_callbacks/callback_args.py

@@ -0,0 +1,45 @@
+#
+# Copyright (c) Lightly AG and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+#
+from dataclasses import dataclass, field
+from typing import Optional
+
+from lightly_train._callbacks.checkpoint import ModelCheckpointArgs
+from lightly_train._configs.config import Config
+
+
+@dataclass
+class LearningRateMonitorArgs(Config):
+    pass
+
+
+@dataclass
+class DeviceStatsMonitorArgs(Config):
+    pass
+
+
+@dataclass
+class EarlyStoppingArgs(Config):
+    monitor: str = "train_loss"
+    patience: int = int(1e12)
+    check_finite: bool = True
+
+
+@dataclass
+class CallbackArgs(Config):
+    learning_rate_monitor: Optional[LearningRateMonitorArgs] = field(
+        default_factory=LearningRateMonitorArgs
+    )
+    device_stats_monitor: Optional[DeviceStatsMonitorArgs] = field(
+        default_factory=DeviceStatsMonitorArgs
+    )
+    early_stopping: Optional[EarlyStoppingArgs] = field(
+        default_factory=EarlyStoppingArgs
+    )
+    model_checkpoint: Optional[ModelCheckpointArgs] = field(
+        default_factory=ModelCheckpointArgs
+    )

lightly_train-0.2.4/src/lightly_train/_callbacks/callback_helpers.py

@@ -0,0 +1,75 @@
+#
+# Copyright (c) Lightly AG and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the license found in the
+# LICENSE file in the root directory of this source tree.
+#
+from __future__ import annotations
+
+import dataclasses
+from pathlib import Path
+from typing import Any
+
+from omegaconf import OmegaConf
+from pytorch_lightning import Callback
+from pytorch_lightning.callbacks import (
+    DeviceStatsMonitor,
+    EarlyStopping,
+    LearningRateMonitor,
+)
+from torch.nn import Module
+
+from lightly_train._callbacks.callback_args import (
+    CallbackArgs,
+)
+from lightly_train._callbacks.checkpoint import ModelCheckpoint
+from lightly_train._checkpoint import CheckpointLightlyTrainModels
+from lightly_train._configs import validate
+from lightly_train._models.embedding_model import EmbeddingModel
+
+
+def validate_callback_args(callback_dict: dict[str, Any] | None) -> CallbackArgs:
+    callback_dictconfig = OmegaConf.create(
+        {} if callback_dict is None else callback_dict
+    )
+    callback_dictconfig = validate.validate_dictconfig(
+        callback_dictconfig, CallbackArgs
+    )
+    callback_args = OmegaConf.to_object(callback_dictconfig)
+    assert isinstance(callback_args, CallbackArgs)  # make mypy happy
+    return callback_args
+
+
+def get_callbacks(
+    callback_args: CallbackArgs,
+    out: Path,
+    model: Module,
+    embedding_model: EmbeddingModel,
+):
+    callbacks: list[Callback] = []
+    if callback_args.learning_rate_monitor is not None:
+        callbacks.append(
+            LearningRateMonitor(
+                **dataclasses.asdict(callback_args.learning_rate_monitor)
+            )
+        )
+    if callback_args.device_stats_monitor is not None:
+        callbacks.append(
+            DeviceStatsMonitor(**dataclasses.asdict(callback_args.device_stats_monitor))
+        )
+    if callback_args.early_stopping is not None:
+        callbacks.append(
+            EarlyStopping(**dataclasses.asdict(callback_args.early_stopping))
+        )
+    if callback_args.model_checkpoint is not None:
+        callbacks.append(
+            ModelCheckpoint(
+                models=CheckpointLightlyTrainModels(
+                    model=model, embedding_model=embedding_model
+                ),
+                dirpath=out / "checkpoints",
+                **dataclasses.asdict(callback_args.model_checkpoint),
+            )
+        )
+    return callbacks

{lightly_train-0.2.2 → lightly_train-0.2.4}/src/lightly_train/_callbacks/checkpoint.py

@@ -7,9 +7,10 @@
 #
 from __future__ import annotations
 
-import warnings
+import logging
+from dataclasses import dataclass
 from datetime import timedelta
-from typing import Any
+from typing import Any, Optional
 
 from pytorch_lightning import LightningModule, Trainer
 from pytorch_lightning.callbacks import ModelCheckpoint as _ModelCheckpoint
@@ -19,8 +20,19 @@ from lightly_train._checkpoint import (
     CheckpointLightlyTrain,
     CheckpointLightlyTrainModels,
 )
+from lightly_train._configs.config import Config
 from lightly_train.types import PathLike
 
+logger = logging.getLogger(__name__)
+
+
+@dataclass
+class ModelCheckpointArgs(Config):
+    save_last: bool = True
+    enable_version_counter: bool = False
+    save_top_k: int = 1
+    every_n_epochs: Optional[int] = None
+
 
 class ModelCheckpoint(_ModelCheckpoint):
     def __init__(
@@ -78,7 +90,6 @@ class ModelCheckpoint(_ModelCheckpoint):
                 checkpoint
             ).models
         except KeyError as ex:
-            warnings.warn(
+            logger.warning(
                 f"Could not restore lightly_train models from checkpoint: {ex}"
             )
-            pass

{lightly_train-0.2.2 → lightly_train-0.2.4}/src/lightly_train/_checkpoint.py

@@ -8,6 +8,7 @@
 from __future__ import annotations
 
 import dataclasses
+import logging
 from dataclasses import dataclass
 from datetime import datetime, timezone
 from pathlib import Path
@@ -21,6 +22,8 @@ from torch.serialization import MAP_LOCATION
 import lightly_train
 from lightly_train._models.embedding_model import EmbeddingModel
 
+logger = logging.getLogger(__name__)
+
 CHECKPOINT_LIGHTLY_TRAIN_KEY = "lightly_train"
 
 
@@ -104,11 +107,34 @@ class Checkpoint:
 
     @staticmethod
     def from_path(
-        checkpoint: Path, map_location: MAP_LOCATION | None = "cpu"
+        checkpoint: Path,
+        map_location: MAP_LOCATION | None = "cpu",
+        weights_only: bool = False,
     ) -> Checkpoint:
-        checkpoint_dict = torch.load(checkpoint, map_location=map_location)
+        """Load a checkpoint from a file path.
+
+        Args:
+            checkpoint:
+                Path to the checkpoint file.
+            map_location:
+                If map_location is a string, it must be a key in torch.device, such as
+                'cpu' or 'cuda:0'. If map_location is a torch.device, it will be used to
+                determine where the checkpoint should be loaded to. Default: 'cpu'.
+            weights_only:
+                If False (default), the whole checkpoint is loaded. If True, only the weights
+                of the model are loaded. This requires the user to add safe globals with:
+                https://pytorch.org/docs/stable/notes/serialization.html#torch.serialization.add_safe_globals
+                TODO(Philipp, 09/24): Expose weights_only argument to the user.
+        """
+        logger.debug(
+            f"Loading checkpoint from '{checkpoint}' with map_location '{map_location}' and weights_only {weights_only}"
+        )
+        checkpoint_dict = torch.load(
+            checkpoint, map_location=map_location, weights_only=weights_only
+        )
         return Checkpoint.from_dict(checkpoint=checkpoint_dict)
 
     def save(self, path: Path) -> None:
+        logger.debug(f"Saving checkpoint to '{path}'")
         path.parent.mkdir(parents=True, exist_ok=True)
         torch.save(self.to_dict(), path)

{lightly_train-0.2.2 → lightly_train-0.2.4}/src/lightly_train/_cli.py

@@ -6,17 +6,23 @@
 # LICENSE file in the root directory of this source tree.
 #
 import inspect
+import logging
+import os
 import sys
 from typing import Callable
 
 from omegaconf import DictConfig, OmegaConf
 
 import lightly_train
+from lightly_train import _logging
 from lightly_train._commands import embed, export, extract_video_frames, train
 from lightly_train._commands.train import TrainConfig
+from lightly_train._logging import LIGHTLY_TRAIN_LOG_LEVEL_ENV_VAR
 from lightly_train._models import package_helpers
 from lightly_train.errors import ConfigError
 
+logger = logging.getLogger(__name__)
+
 _HELP_COMMANDS = {"help", "--help", "-h"}
 _HELP_MSG = """
     Commands:
@@ -28,7 +34,10 @@ _HELP_MSG = """
         lightly-train extract_video_frames  Extract frames from videos using ffmpeg.
         lightly-train help                  Show help message.
 
-    Run `lightly_train <command> help` for more information on a specific command.
+    Run `lightly-train <command> help` for more information on a specific command.
+
+    Optional arguments:
+        -v, --verbose  Run the command in verbose mode for detailed output.
     """
 
 _train_cfg = TrainConfig()
@@ -96,6 +105,20 @@ _TRAIN_HELP_MSG = f"""
             For details, see: https://lightning.ai/docs/pytorch/stable/common/trainer.html#precision
         seed (int):
             Random seed for reproducibility. Default: {_train_cfg.seed}
+        loggers (dict):
+            Loggers for training. Either null or a dictionary of logger names to either
+            null or a dictionary of logger arguments. Null uses the default loggers.
+            To disable a logger, set it to null: `loggers.tensorboard=null`.
+            To configure a logger, pass the respective arguments:
+            `loggers.wandb.project="my_project"`.
+            Default: null
+        callbacks (dict):
+            Callbacks fo training. Either null or a dictionary of callback names to
+            either null or a dictionary of callback arguments. Null uses the default
+            callbacks. To disable a callback, set it to null:
+            `callbacks.model_checkpoint=null`. To configure a callback, pass the
+            respective arguments: `callbacks.model_checkpoint.every_n_epochs=5`.
+            Default: null
         optim_args (dict):
             Arguments for AdamW optimizer. Available arguments are:
             - lr (float)
@@ -115,6 +138,9 @@ _TRAIN_HELP_MSG = f"""
             Additional arguments for the model. The available arguments depend on the
             the `model` parameter.
 
+    Optional arguments:
+        -v, --verbose  Run the command in verbose mode for detailed output.
+
     Examples:
     # Train a ResNet-18 model with SimCLR on ImageNet
     lightly-train train out=out data=imagenet/train model=torchvision/resnet18 method=simclr
@@ -147,12 +173,15 @@ _EXPORT_HELP_MSG = """
             Format to save the model in. Valid options are 'torch_model' and
             'torch_state_dict'. 'torch_model' saves the model as a torch module which
             can be loaded with `model = torch.load(out)`. This requires that the same
-            lightly_train version is installed when the model is exported and when it is
+            LightlyTrain version is installed when the model is exported and when it is
             loaded again. 'torch_state_dict' saves the model's state dict which can be
             loaded with `model.load_state_dict(torch.load(out))`. This is more flexible
-            and can be used to load the model with different lightly_train versions but
+            and can be used to load the model with different LightlyTrain versions but
             requires the model to already be instantiated.
 
+    Optional arguments:
+        -v, --verbose  Run the command in verbose mode for detailed output.
+
     Examples:
     # Export the state dict of the model
     lightly-train export checkpoint=out/checkpoints/last.ckpt out=out/model.pth \\
@@ -201,6 +230,9 @@ _EMBED_HELP_MSG = """
         overwrite (bool):
             Overwrite the output file if it already exists.
 
+    Optional arguments:
+        -v, --verbose  Run the command in verbose mode for detailed output.
+
     Examples:
     # Embed images from a model checkpoint
     lightly-train embed out=embeddings.csv data=images checkpoint=out/checkpoints/last.ckpt \\
@@ -245,6 +277,9 @@ _EXTRACT_VIDEO_FRAMES_HELP_MSG = f"""
             Number of parallel calls to ffmpeg when processing multiple videos.
             If None, the number of workers is set to the number of available CPU cores.
 
+    Optional arguments:
+        -v, --verbose  Run the command in verbose mode for detailed output.
+
     Examples:
     # Extract frames from videos
     lightly-train extract_video_frames data=videos out=frames
@@ -257,12 +292,25 @@ _EXTRACT_VIDEO_FRAMES_HELP_MSG = f"""
 """
 
 
+_VERBOSE_FLAGS = ["-v", "--verbose"]
+
+
 def cli(config: DictConfig) -> None:
+    keys = list(config.keys())
+
+    # Check if the user wants to run the command in verbose mode.
+    # Any of the following will enable verbose mode: -v, --verbose
+    if any(flag in keys for flag in _VERBOSE_FLAGS):
+        os.environ[LIGHTLY_TRAIN_LOG_LEVEL_ENV_VAR] = str(logging.DEBUG)
+        config = OmegaConf.create(
+            {k: v for k, v in config.items() if k not in _VERBOSE_FLAGS}
+        )
+    _logging.set_up_console_logging()
+
     if config.is_empty():
         _show_help()
         return
 
-    keys = list(config.keys())
     # First argument after lightly_train is the command. For example `lightly-train train ...`
     command = str(keys[0]).lower()
     help_if_config_empty = True
@@ -336,17 +384,21 @@ def _run_command_fn(
     try:
         command_fn(config)
     except ConfigError as ex:
+        logger.error(ex)
+        raise ex from None  # Shorten stacktrace
+    except Exception as ex:
+        logger.error(ex)
         raise ex from None  # Shorten stacktrace
 
 
 def _list_models(config: DictConfig) -> None:
     lines = [f"    {model}" for model in package_helpers.list_model_names()]
-    print("\n".join(lines))
+    logger.info("\n".join(lines))
 
 
 def _list_methods(config: DictConfig) -> None:
     lines = [f"    {method}" for method in lightly_train.list_methods()]
-    print("\n".join(lines))
+    logger.info("\n".join(lines))
 
 
 def _is_help_command_in_config(config: DictConfig) -> bool:
@@ -361,7 +413,7 @@ def _show_invalid_command_help(command: str) -> None:
     msg = _format_msg(
         f"""
         Unknown command '{command}':
-            lightly_train {command}
+            lightly-train {command}
         """
     )
     msg += "\n"
@@ -370,7 +422,7 @@ def _show_invalid_command_help(command: str) -> None:
 
 
 def _show_msg(msg: str) -> None:
-    print(_format_msg(msg))
+    logger.info(_format_msg(msg))
 
 
 def _format_msg(msg: str) -> str:

{lightly_train-0.2.2 → lightly_train-0.2.4}/src/lightly_train/_commands/_warnings.py

@@ -37,6 +37,29 @@ def filter_train_warnings() -> None:
             "in this directory can be modified when the new ones are saved!"
         ),
     )
+    # Ignore mixed precision CUDA warnings as the information that CUDA is not available
+    # can be found elsewhere. The same warnings don't pop up for full precision training.
+    warnings.filterwarnings(
+        "ignore",
+        message="User provided device_type of 'cuda', but CUDA is not available.",
+        module="torch.amp",
+        category=UserWarning,
+    )
+    warnings.filterwarnings(
+        "ignore",
+        message="torch.cuda.amp.GradScaler is enabled, but CUDA is not available.",
+        module="torch.amp",
+        category=UserWarning,
+    )
+    # Ignore `lr_scheduler.step()` before `optimizer.step()` warning as it's a PyTorch Lightning issue.
+    # See https://github.com/Lightning-AI/pytorch-lightning/issues/5558
+    # TODO(Philipp, 09/24): Remove this once the issue is resolved.
+    warnings.filterwarnings(
+        "ignore",
+        message="Detected call of \`lr_scheduler.step\(\)\` before \`optimizer.step\(\)\`",
+        category=UserWarning,
+        module="torch.optim.lr_scheduler",
+    )
 
 
 def filter_embed_warnings() -> None: