keras-io

keras-io copied to clipboard

Request for tutorial on how to convert a channel first Keras model to channel last model?

3

Hello, I have a pre-trained Keras model (in h5 format) where all the layers operate on channel first data format. I want to convert this model to operate on the...

mrtpk123

Create visualizationkerascv.py

6

Discussion of visualization offerings from KerasCV Colab Notebook: https://colab.research.google.com/drive/1dFUekCag4s4Z94GTwnPVEv295jGLK3yp?usp=sharing @martin-gorner @ianstenbit

ushareng

Got an error in augmented_train_ds = ( train_ds.shuffle(BATCH_SIZE * 2) .map(augment_fn, num_parallel_calls=AUTOTUNE) .batch(BATCH_SIZE) .map(unpackage_inputs) .prefetch(buffer_size=tf.data.AUTOTUNE) ) Error details: Tensor("sequential_4/rand_augment_4/cond/random_choice_4/switch_case/indexed_case/Identity_1:0", shape=(160, 160, 1), dtype=float32) and Tensor("sequential_4/rand_augment_4/cond/random_choice_4/switch_case/indexed_case/Identity_1:0", shape=(160, 160, 1), dtype=int64) have...

pnl712

In the functional_api guide the link for serialization & saving at lin no.189 is not working due to formatting issues.The link has been introduced with new space like below. ```...

SuryanarayanaY

This is related to the PR #1467 , I had some issues with my base branch after the latest release, so I had to create another fork and another merge....

dimitreOliveira

Adding example on Physics-Informed Neural Networks for solving Eikonal equation

2

Hello, According to [my question](https://github.com/keras-team/keras-io/issues/1287), you might be interested in a new example of physics-informed neural networks (PINNs). I created a new folder `pinn` in the repo since it did...

sgrubas

Clarification: Does keras_tuner support inputting prior hyperparameter data?

2

Hello, I am trying to clarify whether or not keras_tuner objects such as the BayesianOptimization tuner have the ability to take as input prior hyperparameter combinations (for example, from a...

nilamandal

Create samplersv1.py

6

Sampling Discussion using KerasNLP Colab Notebook : https://colab.research.google.com/drive/13ZjB-skKvRtS3IXbFaTdnk4pSbHHNwpV?usp=sharing @martin-gorner @mattdangerw @jbischof

ushareng

Assign to @haifeng-jin

haifeng-jin

error in creating tensorflow dataset

3

def load_data(point_cloud_batch, label_cloud_batch): point_cloud_batch.set_shape([NUM_SAMPLE_POINTS, 7]) #NUM_SAMPLE_POINTS=1024 label_cloud_batch.set_shape([NUM_SAMPLE_POINTS, 9]) return point_cloud_batch, label_cloud_batch def augment(point_cloud_batch, label_cloud_batch): noise = tf.random.uniform( tf.shape(label_cloud_batch), -0.005, 0.005, dtype=tf.float64 ) point_cloud_batch += noise[:, :, :3] return point_cloud_batch, label_cloud_batch...

buffyhridoy