HydraConfig support (#1022)

* 1. tests/_tests_cv_classification_hydra: 'catalyst-dl run --hydra' MNIST classification test pipeline was added
2. catalyst/experiments/hydra_config.py: HydraConfigExperiment was added
3. catalyst/runners/hydra_supervised.py: HydraSupervisedExperiment was added
4. catalyst/dl/script/hydra_run.py: @hydra.main() was added as entry point for hydra configuration experiment
5. catalyst/dl/script/run.py: optional argument '--hydra' was added to change entrypoint to hydra config experiment one
6. catalyst/settings.py: optional 'hydra' package import was added
7. catalyst/utils/hydra_config.py: hydra config utils was added
8. catalyst/utils/hydra_scripts.py: hydra scripts utils was added
9. catalyst/utils/hydra_sys.py: hydra sys utils was added
10. requirements/requirements-hydra.txt: optional 'hydra-core' package was added

* Update hydra_supervised.py, __init__.py, and transforms.py

* Update hydra_run.py, run.py, and 3 more files...

* Update check_dl_cv.sh
Hydra cv classification test was fixed

* Update config.py, functional.py, and hydra_config.py
All dublicated code was replaced to catalyst/experiments/functional.py

* Update hydra_supervised.py
Hydra cv classification test was fixed

* Removed catalyst/utils/hydra_scripts.py, catalyst/utils/hydra_sys.py and changed catalyst/utils/sys.py:
Functions 'catalyst/utils/scripts.py:distributed_cmd_run()' and 'catalyst/utils/sys.py:dump_environment()' are used for both HydraConfigExperiment and ConfigExperiment

* Renamed catalyst/runners/hydra_supervised.py to catalyst/runners/multi_supervised.py
MultiSupervisedRunner was added for multiple model support

* Update config_infer.yaml and config_train.yaml due to MultiSupervisedRunner

* Updated Dockerfile-dev and Dockerfile-dev-fp16 with installing requirements/requirements-hydra.txt

* Update check_dl_cv.sh and run.py for hydra-tests fix

* Update config.py and hydra_config.py

* catalyst/utils/hydra_config.py: prepare_config() -> prepare_hydra_config()

Co-authored-by: Sergey Kolesnikov <[email protected]>

bin/tests/check_dl_cv.sh

@@ -603,5 +603,65 @@ fi
 rm -rf ./tests/logs/_tests_cv_segmentation
 
 
+################################  pipeline 23  ################################
+echo 'pipeline 23'
+python3 -m pip install hydra-core
+
+EXPDIR=./tests/_tests_cv_classification_hydra
+LOGDIR=./tests/logs/_tests_cv_classification_hydra
+LOGFILE=${LOGDIR}/checkpoints/_metrics.json
+
+PYTHONPATH=./examples:.:${PYTHONPATH} \
+  python catalyst/dl/scripts/run.py \
+  --hydra \
+  --config-dir ${EXPDIR} \
+  --config-name conf/config_train.yaml \
+  args.expdir=${EXPDIR} \
+  args.logdir=${LOGDIR} \
+  args.check=1
+
+if [[ ! (-f "$LOGFILE" && -r "$LOGFILE") ]]; then
+    echo "File $LOGFILE does not exist"
+    exit 1
+fi
+
+cat $LOGFILE
+echo 'pipeline 23'
+python -c """
+from catalyst import utils
+metrics = utils.load_config('$LOGFILE')
+# assert metrics['train.2']['loss'] < metrics['train.1']['loss']
+assert metrics['train.1']['loss'] < 2.0
+assert metrics['train.2']['loss'] < 3.3
+"""
+
+if [[ "$USE_DDP" != "1" ]]; then
+    PYTHONPATH=./examples:.:${PYTHONPATH} \
+      python catalyst/dl/scripts/run.py \
+      --hydra \
+      --config-dir ${EXPDIR} \
+      --config-name conf/config_infer.yaml \
+      args.expdir=${EXPDIR} \
+      args.logdir=${LOGDIR} \
+      args.resume=${LOGDIR}/checkpoints/best.pth \
+      vals.out_dir="." \
+      vals.out_prefix="predictions/"
+
+    cat $LOGFILE
+    echo 'pipeline 23 - infer'
+    python -c """
+import numpy as np
+data = np.load('${LOGDIR}/predictions/infer.logits.npy')
+print(data.shape)
+assert data.shape == (10000, 10)
+"""
+
+fi
+
+rm -rf ${LOGDIR}
+
+python3 -m pip uninstall -y hydra-core
+
+
 ################################  pipeline 99  ################################
 rm -rf ./tests/logs

catalyst/dl/scripts/hydra_run.py

@@ -0,0 +1,51 @@
+import logging
+
+import hydra
+from omegaconf import DictConfig
+
+from catalyst.utils.distributed import get_rank
+from catalyst.utils.hydra_config import prepare_hydra_config
+from catalyst.utils.misc import set_global_seed
+from catalyst.utils.scripts import (
+    distributed_cmd_run,
+    dump_code,
+    import_module,
+)
+from catalyst.utils.sys import dump_environment
+from catalyst.utils.torch import prepare_cudnn
+
+logger = logging.getLogger(__name__)
+
+
+def main_worker(cfg: DictConfig):
+    set_global_seed(cfg.args.seed)
+    prepare_cudnn(cfg.args.deterministic, cfg.args.benchmark)
+
+    import_module(hydra.utils.to_absolute_path(cfg.args.expdir))
+
+    experiment = hydra.utils.instantiate(cfg.experiment, cfg=cfg)
+    runner = hydra.utils.instantiate(cfg.runner)
+
+    if experiment.logdir is not None and get_rank() <= 0:
+        dump_environment(cfg, experiment.logdir)
+        dump_code(
+            hydra.utils.to_absolute_path(cfg.args.expdir), experiment.logdir
+        )
+
+    runner.run_experiment(experiment)
+
+
+@hydra.main()
+def main(cfg: DictConfig):
+    """
+    Hydra config catalyst-dl run entry point
+
+    Args:
+        cfg: (DictConfig) configuration
+
+    """
+    cfg = prepare_hydra_config(cfg)
+    distributed_cmd_run(main_worker, cfg.args.distributed, cfg)
+
+
+__all__ = ["main"]

catalyst/dl/scripts/run.py

@@ -4,7 +4,9 @@
 from argparse import ArgumentParser
 import os
 from pathlib import Path
+import sys
 
+from catalyst.settings import IS_HYDRA_AVAILABLE
 from catalyst.utils.distributed import get_rank
 from catalyst.utils.misc import boolean_flag, set_global_seed
 from catalyst.utils.parser import parse_args_uargs
@@ -16,6 +18,9 @@
 from catalyst.utils.sys import dump_environment
 from catalyst.utils.torch import prepare_cudnn
 
+if IS_HYDRA_AVAILABLE:
+    from catalyst.dl.scripts.hydra_run import main as hydra_main
+
 
 def build_args(parser: ArgumentParser):
     """Constructs the command-line arguments for ``catalyst-dl run``."""
@@ -27,7 +32,7 @@ def build_args(parser: ArgumentParser):
         help="path to config/configs",
         metavar="CONFIG_PATH",
         dest="configs",
-        required=True,
+        required=False,
     )
     parser.add_argument("--expdir", type=str, default=None)
     parser.add_argument("--logdir", type=str, default=None)
@@ -94,6 +99,8 @@ def build_args(parser: ArgumentParser):
         help="Deterministic mode if running in CuDNN backend",
     )
     boolean_flag(parser, "benchmark", default=None, help="Use CuDNN benchmark")
+    if IS_HYDRA_AVAILABLE:
+        boolean_flag(parser, "hydra", default=None, help="Use Hydra")
 
     return parser
 
@@ -133,4 +140,8 @@ def main(args, unknown_args):
 
 if __name__ == "__main__":
     args, unknown_args = parse_args()
-    main(args, unknown_args)
+    if IS_HYDRA_AVAILABLE and args.hydra:
+        sys.argv.remove("--hydra")
+        hydra_main()
+    else:
+        main(args, unknown_args)

catalyst/experiments/__init__.py

@@ -4,5 +4,16 @@
 from catalyst.experiments.auto import AutoCallbackExperiment
 from catalyst.experiments.config import ConfigExperiment
 
+from catalyst.settings import IS_HYDRA_AVAILABLE
 
-__all__ = ["ConfigExperiment", "Experiment", "AutoCallbackExperiment"]
+if IS_HYDRA_AVAILABLE:
+    from catalyst.experiments.hydra_config import HydraConfigExperiment
+
+    __all__ = [
+        "ConfigExperiment",
+        "Experiment",
+        "AutoCallbackExperiment",
+        "HydraConfigExperiment",
+    ]
+else:
+    __all__ = ["ConfigExperiment", "Experiment", "AutoCallbackExperiment"]