From baae368376ab022d1614ad2db83de70c09fac880 Mon Sep 17 00:00:00 2001 From: Mikko Kotila Date: Mon, 22 Apr 2024 12:50:38 +0300 Subject: [PATCH 1/4] few small changes to README.md --- README.md | 18 ++---------------- 1 file changed, 2 insertions(+), 16 deletions(-) diff --git a/README.md b/README.md index 9fa5627..30f7207 100755 --- a/README.md +++ b/README.md @@ -4,19 +4,7 @@
-

Hyperparameter Optimization for TensorFlow and Keras

- -

- - - Talos Travis - - - - Talos Coveralls - - -

+

Bullet-Proof Hyperparameter Experiments for TensorFlow and Keras

Talos • @@ -51,13 +39,11 @@ TL;DR Thousands of researchers have found Talos to importantly improve ordinary Talos is made for researchers, data scientists, and data engineers that want to remain in **complete control of their TensorFlow (tf.keras) and Keras models**, but are tired of mindless parameter hopping and confusing optimization solutions that add complexity instead of reducing it. -**Within minutes, without learning any new syntax,** Talos allows you to configure, perform, and evaluate hyperparameter experiments that yield state-of-the-art results across a wide range of prediction tasks. Talos provides the **simplest and yet most powerful** available method for hyperparameter optimization with TensorFlow (tf.keras) and Keras. -


### :wrench: Key Features -Based on what no doubt constitutes a "biased" review (being our own) of more than ~30 hyperparameter tuning and optimization solutions, Talos comes on top in terms of intuitive, easy-to-learn, highly permissive access to critical hyperparameter experimentation capabilities. Key features include: +**Within minutes, without learning any new syntax,** Talos allows you to configure, perform, and evaluate hyperparameter experiments that yield state-of-the-art results across a wide range of prediction tasks. Talos provides the **simplest and yet most powerful** available method for hyperparameter optimization with TensorFlow (tf.keras) and Keras. Key features include: - Single-line optimize-to-predict pipeline `talos.Scan(x, y, model, params).predict(x_test, y_test)` - Automated hyperparameter optimization From d346852325dc1ff027e5e2ac5cfd4294dd1d27ca Mon Sep 17 00:00:00 2001 From: Mikko Kotila Date: Mon, 22 Apr 2024 12:53:00 +0300 Subject: [PATCH 2/4] improved the tagline --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 30f7207..5775708 100755 --- a/README.md +++ b/README.md @@ -4,7 +4,7 @@
-

Bullet-Proof Hyperparameter Experiments for TensorFlow and Keras

+

Bullet-Proof Hyperparameter Experiments with TensorFlow and Keras

Talos • From d74eb16f3176cf3ce21a38d48027ebca290b074e Mon Sep 17 00:00:00 2001 From: Mikko Kotila Date: Mon, 22 Apr 2024 13:00:14 +0300 Subject: [PATCH 3/4] replace quantum with uniform in tests --- tests/commands/test_templates.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/commands/test_templates.py b/tests/commands/test_templates.py index f1339f7..2f6eba8 100644 --- a/tests/commands/test_templates.py +++ b/tests/commands/test_templates.py @@ -40,7 +40,7 @@ def test_templates(): x, y = talos.templates.datasets.cervical_cancer() x, y = talos.templates.datasets.titanic() - talos.templates.pipelines.breast_cancer(random_method='quantum') + talos.templates.pipelines.breast_cancer(random_method='uniform_mersenne') talos.templates.pipelines.cervical_cancer(random_method='sobol') talos.templates.pipelines.iris(random_method='uniform_crypto') talos.templates.pipelines.titanic(random_method='korobov_matrix') From 715d2b6477c775d0444dbaa88a37624d4577e07b Mon Sep 17 00:00:00 2001 From: Mikko Kotila Date: Mon, 22 Apr 2024 13:00:54 +0300 Subject: [PATCH 4/4] change the mentioned stats in readme --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 5775708..4d140f0 100755 --- a/README.md +++ b/README.md @@ -69,7 +69,7 @@ Get the below code [here](https://gist.github.com/mikkokotila/4c0d6298ff0a22dc56 -The *Simple* example below is more than enough for starting to use Talos with any Keras model. *Field Report* has +2,600 claps on Medium because it's more entertaining. +The *Simple* example below is more than enough for starting to use Talos with any Keras model. *Field Report* has +4,400 claps on Medium because it's more entertaining. [Simple](https://nbviewer.jupyter.org/github/autonomio/talos/blob/master/examples/A%20Very%20Short%20Introduction%20to%20Hyperparameter%20Optimization%20of%20Keras%20Models%20with%20Talos.ipynb) [1-2 mins]