Migrating Fully Convolutional Network example to Keras 3 #1691
Conversation
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
| @@ -48,14 +48,17 @@ | |||
| ## Setup Imports | |||
| """ | |||
|
|
|||
| import os | |||
| os.environ["KERAS_BACKEND"] = "tensorflow" | |||
There was a problem hiding this comment.
Does the code work with all backends, or just TF? If it works with all backends, there is no need to hardcode a backend.
There was a problem hiding this comment.
Yes, it is a TF-only example.
| @@ -147,10 +150,10 @@ def unpack_resize_data(section): | |||
| # for Matplotlib visualization. | |||
|
|
|||
| images, masks = next(iter(test_ds)) | |||
| random_idx = tf.random.uniform([], minval=0, maxval=BATCH_SIZE, dtype=tf.int32) | |||
| random_idx = keras.random.uniform([], minval=0, maxval=BATCH_SIZE, seed=seed_generator) | |||
There was a problem hiding this comment.
Outside of a layer, you can just use an integer seed value, it's simpler.
There was a problem hiding this comment.
Thank you for the suggestion! I've updated the code to use an integer seed value as recommended.
| @@ -556,13 +559,13 @@ def preprocess_data(image, segmentation_mask): | |||
| """ | |||
|
|
|||
| images, masks = next(iter(test_ds)) | |||
| random_idx = tf.random.uniform([], minval=0, maxval=BATCH_SIZE, dtype=tf.int32) | |||
| random_idx = keras.random.uniform([], minval=0, maxval=BATCH_SIZE,seed=seed_generator) | |||
…1691) * Migrated fully_convolutional_network example to Keras 3 * Initialised seed to integer values
This PR migrates the fully_convolutional_network example to keras 3.0[TF-Only Example] as requested in keras-team/keras-cv#2211