From 50f7e6dcc0275f9caff095dc0000d882e7b50dcd Mon Sep 17 00:00:00 2001 From: Dobiasd Date: Mon, 18 Mar 2024 16:45:22 +0100 Subject: [PATCH] Remove type remark from readme, the assertion alone should suffice and is more DRY --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 4e8c3821..6b8737eb 100644 --- a/README.md +++ b/README.md @@ -86,7 +86,7 @@ Would you like to build/train a model using Keras/Python? And would you like to Usage ----- -1) Use Keras/Python to build (`model.compile(...)`), train (`model.fit(...)`) and test (`model.evaluate(...)`) your model as usual. Then save it to a single file using `model.save('....keras')`. The `image_data_format` in your model must be `channels_last`, which is the default when using the TensorFlow backend. Models created with a different `image_data_format` and other backends are not supported. The model must be of type `tensorflow.keras.models.Model`. +1) Use Keras/Python to build (`model.compile(...)`), train (`model.fit(...)`) and test (`model.evaluate(...)`) your model as usual. Then save it to a single file using `model.save('....keras')`. The `image_data_format` in your model must be `channels_last`, which is the default when using the TensorFlow backend. Models created with a different `image_data_format` and other backends are not supported. 2) Now convert it to the frugally-deep file format with `keras_export/convert_model.py`