User Ahmed - Stack Overflow

3 votes

1 answer

542 views

Implementation of F1-score, IOU and Dice Score

asked Jan 15, 2025 at 21:33

3 votes

1 answer

94 views

How to serialize and deserialize a Keras Layer when a submodule is passed as a class

asked Dec 31, 2025 at 3:36

3 votes

1 answer

98 views

Problem with DWT3D with Custom Keras Layer

asked Jan 7 at 17:04

2 votes

0 answers

83 views

Can't replicate the behaviour of loss calculation in keras

asked Dec 30, 2024 at 19:15

2 votes

0 answers

136 views

Warning when loading the model because of Adam optimizer

asked Mar 4, 2025 at 15:48

1 vote

1 answer

47 views

Do I need .repeat() or steps_per_epoch when training on a finite TFRecord dataset in Keras?

asked Oct 11, 2025 at 21:02

1 vote

1 answer

131 views

Will tf.keras.Sequential containing multiple custom layers be correctly fully serializable and deserializable in my case?

asked Nov 3, 2025 at 12:00

0 votes

0 answers

107 views

Is my use of tf.distribute.MirroredStrategy and strategy.scope() correct and safe for multi-GPU training in Keras?

asked Dec 27, 2025 at 22:27

0 votes

1 answer

73 views

How to determine the x, y, z axes in NIfTI volumes using NiBabel?

asked Sep 26, 2025 at 13:47

0 votes

1 answer

53 views

How dataset.repeat() works with model.fit()?

asked Oct 7, 2024 at 22:47

0 votes

1 answer

70 views

Always getting ' Your input ran out of data'

asked Jan 29, 2025 at 13:15

0 votes

1 answer

67 views

Cant Serialize and Deserialize ViT in Keras When Setting Classification = True

asked Jan 10 at 14:59

0 votes

0 answers

48 views

Parameter count difference between UNETR paper and MONAI implementation

asked Jan 12 at 10:27

Advice

0 votes

0 replies

36 views

Regarding's MONAI WarmupCosineSchedule with AdamW, should scheduler.step() be called per batch, and does optimizer lr define the peak lr?

asked Apr 27 at 10:05

0 votes

1 answer

58 views

Is it correct to use build() in Keras to create internal layers that depend on input_shape?

asked Jan 1 at 21:41

0 votes

0 answers

75 views

Keras Conv3D input shape clarification: spatial dimensions vs width/height/depth

asked Jan 4 at 3:00

0 votes

0 answers

82 views

Is using setattr + list to create a variable number of sublayers serializable?

asked Jan 4 at 3:58

Collectives™ on Stack Overflow

17 Questions

Implementation of F1-score, IOU and Dice Score

How to serialize and deserialize a Keras Layer when a submodule is passed as a class

Problem with DWT3D with Custom Keras Layer

Can't replicate the behaviour of loss calculation in keras

Warning when loading the model because of Adam optimizer

Do I need .repeat() or steps_per_epoch when training on a finite TFRecord dataset in Keras?

Will tf.keras.Sequential containing multiple custom layers be correctly fully serializable and deserializable in my case?

Is my use of tf.distribute.MirroredStrategy and strategy.scope() correct and safe for multi-GPU training in Keras?

How to determine the x, y, z axes in NIfTI volumes using NiBabel?

How dataset.repeat() works with model.fit()?

Always getting ' Your input ran out of data'

Cant Serialize and Deserialize ViT in Keras When Setting Classification = True

Parameter count difference between UNETR paper and MONAI implementation

Regarding's MONAI WarmupCosineSchedule with AdamW, should scheduler.step() be called per batch, and does optimizer lr define the peak lr?

Is it correct to use build() in Keras to create internal layers that depend on input_shape?

Keras Conv3D input shape clarification: spatial dimensions vs width/height/depth

Is using setattr + list to create a variable number of sublayers serializable?