diff --git a/pysegcnn/main/config.py b/pysegcnn/main/config.py
index 707129a0d57ec5e933ff83c9422ef7a5168644f9..583bc7d734095d8ee15f393a2f112a6e0fc061d3 100644
--- a/pysegcnn/main/config.py
+++ b/pysegcnn/main/config.py
@@ -28,7 +28,7 @@ HERE = pathlib.Path(__file__).resolve().parent
# path to the datasets on the current machine
DRIVE_PATH = pathlib.Path('C:/Eurac/Projects/CCISNOW/_Datasets/')
-# DRIVE_PATH = pathlib.Path('/mnt/CEPH_PROJECTS/cci_snow/dfrisinghelli/_Datasets/')
+# DRIVE_PATH = pathlib.Path('/mnt/CEPH_PROJECTS/cci_snow/dfrisinghelli/_Datasets/') # nopep8
# name and paths to the datasets
DATASETS = {'Sparcs': DRIVE_PATH.joinpath('Sparcs'),
@@ -47,6 +47,9 @@ BANDS = ['red', 'green', 'blue', 'nir', 'swir1', 'swir2']
# tile size of a single sample
TILE_SIZE = 128
+# number of folds for cross validation
+K_FOLDS = 2
+
# the source dataset configuration dictionary
src_ds_config = {
@@ -81,11 +84,6 @@ src_ds_config = {
# 'pad': False,
'pad': True,
- # the random seed for the numpy random number generator
- # ensures reproducibility of the training, validation and test data split
- # used if split_mode='random' and split_mode='scene'
- 'seed': 0,
-
# whether to sort the dataset in chronological order, useful for time
# series data
# 'sort': True,
@@ -156,11 +154,11 @@ trg_ds_config = {
'bands': BANDS,
'tile_size': TILE_SIZE,
'pad': True,
- 'seed': 0,
'sort': True,
'transforms': [],
'merge_labels': {'Cirrus': 'Cloud',
'Not_used': 'No_data'}
+
}
# the source dataset split configuration dictionary
@@ -172,64 +170,58 @@ src_split_config = {
# the mode to split the dataset:
#
- # - 'random': randomly split the scenes
- # for each scene, the tiles can be distributed among the
+ # - 'tile': for each scene, the tiles can be distributed among the
# training, validation and test set
#
- # - 'scene': randomly split the scenes
- # for each scene, all the tiles of the scene are included in
+ # - 'scene': for each scene, all the tiles of the scene are included in
# either the training set, the validation set or the test
# set, respectively
- #
- # - 'date': split the scenes of a dataset based on a date, useful for
- # time series data
- # scenes before date build the training set, scenes after
- # the date build the validation set, the test set is empty
- # 'split_mode': 'date',
- # 'split_mode': 'random',
+ # 'split_mode': 'tile',
'split_mode': 'scene',
+ # the number of folds for cross validation
+ #
+ # k_folds = 1 : The model is trained with a single dataset split based on
+ # 'tvratio' and 'ttratio'
+ # k_folds > 1 : The model is trained via cross validation on k_folds splits
+ # of the dataset
+ 'k_folds': K_FOLDS,
+
+ # the random seed for the random number generator
+ # ensures reproducibility of the training, validation and test data split
+ 'seed': 0,
+
+ # whether to shuffle the data before splitting
+ 'shuffle': True,
+
+ # -------------------------------------------------------------------------
+ # IMPORTANT: these setting only apply if 'kfolds=1'
+ # -------------------------------------------------------------------------
+
# (ttratio * 100) % of the dataset will be used for training and
# validation
- # used if split_mode='random' and split_mode='scene'
+ # used if 'kfolds=1'
'ttratio': 1,
# (ttratio * tvratio) * 100 % will be used for training
# (1 - ttratio * tvratio) * 100 % will be used for validation
- # used if split_mode='random' and split_mode='scene'
+ # used if 'kfolds=1'
'tvratio': 0.8,
- # the date to split the scenes
- # format: 'yyyymmdd'
- # scenes before date build the training set, scenes after the date build
- # the validation set, the test set is empty
- # used if split_mode='date'
- 'date': '',
- 'dateformat': '%Y%m%d',
-
- # whether to drop samples (during training only) with a fraction of
- # pixels equal to the constant padding value cval >= drop
- # drop=1 means, do not use a sample if all pixels = cval
- # drop=0.8 means, do not use a sample if 80% or more of the pixels are
- # equal to cval
- # drop=0.2 means, ...
- # drop=0 means, do not drop any samples
- 'drop': 0,
-
- }
+}
# the target dataset split configuration dictionary
trg_split_config = {
- # 'split_mode': 'date',
- # 'split_mode': 'random',
+ # 'split_mode': 'tile',
'split_mode': 'scene',
+ 'k_folds': K_FOLDS,
+ 'seed': 0,
+ 'shuffle': True,
'ttratio': 1,
'tvratio': 0.8,
- 'date': '',
- 'dateformat': '%Y%m%d',
- 'drop': 0,
- }
+
+}
# the model configuration dictionary
model_config = {
@@ -302,8 +294,8 @@ tlda_config = {
# whether to apply any sort of transfer learning
# if transfer=False, the model is only trained on the source dataset
- 'transfer': True,
- # 'transfer': False,
+ # 'transfer': True,
+ 'transfer': False,
# Supervised vs. Unsupervised ---------------------------------------------
# -------------------------------------------------------------------------
diff --git a/pysegcnn/main/train.py b/pysegcnn/main/train.py
deleted file mode 100644
index fc0e91db95184dfcc48ee5f541852eba4a6f8cfd..0000000000000000000000000000000000000000
--- a/pysegcnn/main/train.py
+++ /dev/null
@@ -1,126 +0,0 @@
-"""Main script to train a model.
-
-Steps to launch a model run:
-
- 1. Configure the model run in :py:mod:`pysegcnn.main.config.py`
- - configure the dataset(s): ``src_ds_config`` and ``trg_ds_config``
- - configure the split(s) : ``src_ds_config`` and ``trg_ds_config``
- - configure the model : ``model_config``
- 2. Save :py:mod:`pysegcnn.main.config.py`
- 3. In a terminal, navigate to the repository's root directory
- 4. Run
-
- .. code-block:: bash
-
- python pysegcnn/main/train.py
-
-
-License
--------
-
- Copyright (c) 2020 Daniel Frisinghelli
-
- This source code is licensed under the GNU General Public License v3.
-
- See the LICENSE file in the repository's root directory.
-
-"""
-
-# !/usr/bin/env python
-# -*- coding: utf-8 -*-
-
-# builtins
-from logging.config import dictConfig
-
-# locals
-from pysegcnn.core.trainer import (DatasetConfig, SplitConfig, ModelConfig,
- TransferLearningConfig, StateConfig,
- LogConfig, DomainAdaptationTrainer)
-from pysegcnn.main.config import (src_ds_config, src_split_config,
- trg_ds_config, trg_split_config,
- model_config, tlda_config)
-from pysegcnn.core.logging import log_conf
-
-
-if __name__ == '__main__':
-
- # (i) instanciate the source domain configurations
- src_dc = DatasetConfig(**src_ds_config) # source domain dataset
- src_sc = SplitConfig(**src_split_config) # source domain dataset split
-
- # (ii) instanciate the target domain configuration
- trg_dc = DatasetConfig(**trg_ds_config) # target domain dataset
- trg_sc = SplitConfig(**trg_split_config) # target domain dataset split
-
- # (iii) instanciate the model configuration
- net_mc = ModelConfig(**model_config)
-
- # (iv) instanciate the transfer learning configuration
- trn_sf = TransferLearningConfig(**tlda_config)
-
- # (v) instanciate the model state file
- net_sc = StateConfig(src_dc, src_sc, trg_dc, trg_sc, net_mc, trn_sf)
- state_file = net_sc.init_state()
-
- # (vi) instanciate logging configuration
- net_lc = LogConfig(state_file)
- dictConfig(log_conf(net_lc.log_file))
-
- # (vii) instanciate the datasets to train the model on
- src_ds = src_dc.init_dataset()
- trg_ds = trg_dc.init_dataset()
-
- # (viii) instanciate the training, validation and test datasets and
- # dataloaders for the source domain
- src_tra_ds, src_val_ds, src_tes_ds = src_sc.train_val_test_split(src_ds)
- src_tra_dl, src_val_dl, src_tes_dl = src_sc.dataloaders(
- src_tra_ds, src_val_ds, src_tes_ds, batch_size=net_mc.batch_size,
- shuffle=True, drop_last=False)
-
- # (ix) instanciate the training, validation and test datasets and
- # dataloaders dor the target domain
- trg_tra_ds, trg_val_ds, trg_tes_ds = trg_sc.train_val_test_split(trg_ds)
- trg_tra_dl, trg_val_dl, trg_tes_dl = trg_sc.dataloaders(
- trg_tra_ds, trg_val_ds, trg_tes_ds, batch_size=net_mc.batch_size,
- shuffle=True, drop_last=False)
-
- # (x) instanciate the model
- if trn_sf.transfer and (trn_sf.supervised or trn_sf.uda_from_pretrained):
- # check whether to load a pretrained model for (un)supervised transfer
- # learning
- net, optimizer, checkpoint = trn_sf.transfer_model(
- trn_sf.pretrained_path,
- nclasses=len(src_ds).labels,
- optim_kwargs=net_mc.optim_kwargs,
- freeze=trn_sf.freeze)
- else:
- # initialize model from scratch or from an existing model checkpoint
- net, optimizer, checkpoint = net_mc.init_model(
- len(src_ds.use_bands), len(src_ds.labels), state_file)
-
- # (xi) instanciate the network trainer class
- trainer = DomainAdaptationTrainer(
- model=net,
- optimizer=optimizer,
- state_file=net.state_file,
- src_train_dl=src_tra_dl,
- src_valid_dl=src_val_dl,
- src_test_dl=src_tes_dl,
- epochs=net_mc.epochs,
- nthreads=net_mc.nthreads,
- early_stop=net_mc.early_stop,
- mode=net_mc.mode,
- delta=net_mc.delta,
- patience=net_mc.patience,
- checkpoint_state=checkpoint,
- save=net_mc.save,
- supervised=trn_sf.supervised,
- trg_train_dl=trg_tra_dl,
- trg_valid_dl=trg_val_dl,
- trg_test_dl=trg_tes_dl,
- uda_loss_function=trn_sf.uda_loss_function,
- uda_lambda=trn_sf.uda_lambda,
- uda_pos=trn_sf.uda_pos)
-
- # (xi) train the model
- # training_state = trainer.train()