initial commit

.gitignore

+.idea
+data
+logs
+**/__pycache__
+*.log

Makefile

+
+help:  ## Show help
+	@grep -E '^[.a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}'
+
+clean: ## Clean autogenerated files
+	rm -rf dist
+	find . -type f -name "*.DS_Store" -ls -delete
+	find . | grep -E "(__pycache__|\.pyc|\.pyo)" | xargs rm -rf
+	find . | grep -E ".pytest_cache" | xargs rm -rf
+	find . | grep -E ".ipynb_checkpoints" | xargs rm -rf
+	rm -f .coverage
+
+clean-logs: ## Clean logs
+	rm -r logs/**
+
+style: ## Run pre-commit hooks
+	pre-commit run -a
+
+sync: ## Merge changes from main branch to your current branch
+	git fetch --all
+	git merge main
+
+test: ## Run not slow tests
+	pytest -k "not slow"
+
+test-full: ## Run all tests
+	pytest
+
+train: ## Train the model
+	python src/train.py
+
+debug: ## Enter debugging mode with pdb
+	#
+	# tips:
+	# - use "import pdb; pdb.set_trace()" to set breakpoint
+	# - use "h" to print all commands
+	# - use "n" to execute the next line
+	# - use "c" to run until the breakpoint is hit
+	# - use "l" to print src code around current line, "ll" for full function code
+	# - docs: https://docs.python.org/3/library/pdb.html
+	#
+	python -m pdb src/train.py debug=default

configs/callbacks/default.yaml

+defaults:
+  - model_checkpoint.yaml
+  - early_stopping.yaml
+  - model_summary.yaml
+  - rich_progress_bar.yaml
+  - _self_
+
+model_checkpoint:
+  dirpath: ${paths.output_dir}/checkpoints
+  filename: "epoch_{epoch:03d}"
+  monitor: "val/acc"
+  mode: "max"
+  save_last: True
+  auto_insert_metric_name: False
+
+early_stopping:
+  monitor: "val/acc"
+  patience: 100
+  mode: "max"
+
+model_summary:
+  max_depth: -1

configs/callbacks/early_stopping.yaml

+# https://pytorch-lightning.readthedocs.io/en/latest/api/pytorch_lightning.callbacks.EarlyStopping.html
+
+# Monitor a metric and stop training when it stops improving.
+# Look at the above link for more detailed information.
+early_stopping:
+  _target_: pytorch_lightning.callbacks.EarlyStopping
+  monitor: ??? # quantity to be monitored, must be specified !!!
+  min_delta: 0. # minimum change in the monitored quantity to qualify as an improvement
+  patience: 3 # number of checks with no improvement after which training will be stopped
+  verbose: False # verbosity mode
+  mode: "min" # "max" means higher metric value is better, can be also "min"
+  strict: True # whether to crash the training if monitor is not found in the validation metrics
+  check_finite: True # when set True, stops training when the monitor becomes NaN or infinite
+  stopping_threshold: null # stop training immediately once the monitored quantity reaches this threshold
+  divergence_threshold: null # stop training as soon as the monitored quantity becomes worse than this threshold
+  check_on_train_epoch_end: null # whether to run early stopping at the end of the training epoch
+  # log_rank_zero_only: False  # this keyword argument isn't available in stable version

configs/callbacks/model_checkpoint.yaml

+# https://pytorch-lightning.readthedocs.io/en/latest/api/pytorch_lightning.callbacks.ModelCheckpoint.html
+
+# Save the model periodically by monitoring a quantity.
+# Look at the above link for more detailed information.
+model_checkpoint:
+  _target_: pytorch_lightning.callbacks.ModelCheckpoint
+  dirpath: null # directory to save the model file
+  filename: null # checkpoint filename
+  monitor: null # name of the logged metric which determines when model is improving
+  verbose: False # verbosity mode
+  save_last: null # additionally always save an exact copy of the last checkpoint to a file last.ckpt
+  save_top_k: 1 # save k best models (determined by above metric)
+  mode: "min" # "max" means higher metric value is better, can be also "min"
+  auto_insert_metric_name: True # when True, the checkpoints filenames will contain the metric name
+  save_weights_only: False # if True, then only the model’s weights will be saved
+  every_n_train_steps: null # number of training steps between checkpoints
+  train_time_interval: null # checkpoints are monitored at the specified time interval
+  every_n_epochs: null # number of epochs between checkpoints
+  save_on_train_epoch_end: null # whether to run checkpointing at the end of the training epoch or the end of validation

configs/callbacks/model_summary.yaml

+# https://pytorch-lightning.readthedocs.io/en/latest/api/pytorch_lightning.callbacks.RichModelSummary.html
+
+# Generates a summary of all layers in a LightningModule with rich text formatting.
+# Look at the above link for more detailed information.
+model_summary:
+  _target_: pytorch_lightning.callbacks.RichModelSummary
+  max_depth: 1 # the maximum depth of layer nesting that the summary will include

configs/callbacks/rich_progress_bar.yaml

+# https://pytorch-lightning.readthedocs.io/en/latest/api/pytorch_lightning.callbacks.RichProgressBar.html
+
+# Create a progress bar with rich text formatting.
+# Look at the above link for more detailed information.
+rich_progress_bar:
+  _target_: pytorch_lightning.callbacks.RichProgressBar

configs/datamodule/mimic_cxr.yaml

+_target_: src.datamodules.mimic_datamodule.MimicDataModule
+data_dir: "${paths.data_dir}/mimic_cxr"
+
+num_workers: 12
+batch_size: 16
+
+max_seq_length: 100
+
+tokenizer:
+    _target_: src.models.components.r2gen.r2gen_tokenizers.Tokenizer
+    ann_path: '${paths.data_dir}/mimic_cxr/annotation.json'
+    dataset_name: 'mimic_cxr'

configs/datamodule/mnist.yaml

+_target_: src.datamodules.mnist_datamodule.MNISTDataModule
+data_dir: ${paths.data_dir}
+batch_size: 128
+train_val_test_split: [55_000, 5_000, 10_000]
+num_workers: 0
+pin_memory: False

configs/debug/default.yaml

+# @package _global_
+
+# default debugging setup, runs 1 full epoch
+# other debugging configs can inherit from this one
+
+# overwrite task name so debugging logs are stored in separate folder
+task_name: "debug"
+
+# disable callbacks and loggers during debugging
+callbacks: null
+logger: null
+
+extras:
+  ignore_warnings: False
+  enforce_tags: False
+
+# sets level of all command line loggers to 'DEBUG'
+# https://hydra.cc/docs/tutorials/basic/running_your_app/logging/
+hydra:
+  job_logging:
+    root:
+      level: DEBUG
+
+  # use this to also set hydra loggers to 'DEBUG'
+  # verbose: True
+
+trainer:
+  max_epochs: 1
+  accelerator: cpu # debuggers don't like gpus
+  devices: 1 # debuggers don't like multiprocessing
+  detect_anomaly: true # raise exception if NaN or +/-inf is detected in any tensor
+
+datamodule:
+  num_workers: 0 # debuggers don't like multiprocessing
+  pin_memory: False # disable gpu memory pin

configs/debug/fdr.yaml

+# @package _global_
+
+# runs 1 train, 1 validation and 1 test step
+
+defaults:
+  - default.yaml
+
+trainer:
+  fast_dev_run: true

configs/debug/limit.yaml

+# @package _global_
+
+# uses only 1% of the training data and 5% of validation/test data
+
+defaults:
+  - default.yaml
+
+trainer:
+  max_epochs: 3
+  limit_train_batches: 0.01
+  limit_val_batches: 0.05
+  limit_test_batches: 0.05

configs/debug/overfit.yaml

+# @package _global_
+
+# overfits to 3 batches
+
+defaults:
+  - default.yaml
+
+trainer:
+  max_epochs: 20
+  overfit_batches: 3
+
+# model ckpt and early stopping need to be disabled during overfitting
+callbacks: null

configs/debug/profiler.yaml

+# @package _global_
+
+# runs with execution time profiling
+
+defaults:
+  - default.yaml
+
+trainer:
+  max_epochs: 1
+  profiler: "simple"
+  # profiler: "advanced"
+  # profiler: "pytorch"

configs/eval.yaml

+# @package _global_
+
+defaults:
+  - _self_
+  - datamodule: mnist.yaml # choose datamodule with `test_dataloader()` for evaluation
+  - model: mnist.yaml
+  - logger: null
+  - trainer: default.yaml
+  - paths: default.yaml
+  - extras: default.yaml
+  - hydra: default.yaml
+
+task_name: "eval"
+
+tags: ["dev"]
+
+# passing checkpoint path is necessary for evaluation
+ckpt_path: ???

configs/experiment/r2gen.mimic.train.yaml

+# @package _global_
+
+defaults:
+  - override /datamodule: mimic_cxr.yaml
+  - override /model: r2gen.mimic.yaml
+  - override /trainer: gpu.yaml
+  - override /logger: tensorboard.yaml
+
+
+task_name: "r2gen.mimic.multiview.train"
+tags: ["r2gen", "mimic", "train"]
+
+seed: 456789
+
+
+trainer:
+  min_epochs: 30
+  max_epochs: 30

configs/extras/default.yaml

+# disable python warnings if they annoy you
+ignore_warnings: False
+
+# ask user for tags if none are provided in the config
+enforce_tags: True
+
+# pretty print config tree at the start of the run using Rich library
+print_config: True