add hyperparameter search for convolutional model

configs/hparams_search/focusConvMSE_150_hyperparameter_search.yaml

@@ -0,0 +1,76 @@
+# @package _global_
+
+# example hyperparameter optimization of some experiment with Optuna:
+# python train.py -m hparams_search=mnist_optuna experiment=example
+
+defaults:
+ - override /datamodule: focus150.yaml
+ - override /model: focusConv_150.yaml
+ - override /hydra/sweeper: optuna
+
+# choose metric which will be optimized by Optuna
+# make sure this is the correct name of some metric logged in lightning module!
+optimized_metric: "val/mae_best"
+
+name: "focusConvMSE_150_hyperparameter_search"
+
+# here we define Optuna hyperparameter search
+# it optimizes for value returned from function with @hydra.main decorator
+# docs: https://hydra.cc/docs/next/plugins/optuna_sweeper
+hydra:
+ sweeper:
+ _target_: hydra_plugins.hydra_optuna_sweeper.optuna_sweeper.OptunaSweeper
+
+ # storage URL to persist optimization results
+ # for example, you can use SQLite if you set 'sqlite:///example.db'
+ storage: null
+
+ # name of the study to persist optimization results
+ study_name: focusConvMSE_150_hyperparameter_search
+
+ # number of parallel workers
+ n_jobs: 1
+
+ # 'minimize' or 'maximize' the objective
+ direction: minimize
+
+ # total number of runs that will be executed
+ n_trials: 20
+
+ # choose Optuna hyperparameter sampler
+ # docs: https://optuna.readthedocs.io/en/stable/reference/samplers.html
+ sampler:
+ _target_: optuna.samplers.TPESampler
+ seed: 12345
+ n_startup_trials: 10 # number of random sampling runs before optimization starts
+
+ # define range of hyperparameters
+ search_space:
+ datamodule.batch_size:
+ type: categorical
+ choices: [64, 128]
+ model.lr:
+ type: float
+ low: 0.0001
+ high: 0.2
+ model.pool_size:
+ type: categorical
+ choices: [1, 2, 3]
+ model.conv1_size:
+ type: categorical
+ choices: [3, 5, 7, 9]
+ model.conv1_channels:
+ type: categorical
+ choices: [1, 3, 6, 9]
+ model.conv2_size:
+ type: categorical
+ choices: [3, 5, 7, 9]
+ model.conv2_channels:
+ type: categorical
+ choices: [1, 3, 6, 9]
+ model.lin1_size:
+ type: categorical
+ choices: [16, 32, 64, 96, 128]
+ model.lin2_size:
+ type: categorical
+ choices: [16, 32, 64, 96, 128]