issues Search Results · repo:keras-team/keras language:Python
Filter by
12k results
(70 ms)12k results
inkeras-team/keras (press backspace or delete to remove)created this layer to monitor what s happening:
class ReportingConv1D(Conv1D): def call(self, inputs): print(f {inputs.dtype} {inputs.shape} {self.kernel.dtype}
{self.kernel.shape} {self.kernel.path} ...
type:Bug
pumpnineteen
- 4
- Opened 5 days ago
- #21448
Page:
https://www.tensorflow.org/api_docs/python/tf/keras/losses/SparseCategoricalCrossentropy
The first example no longer functions.
y_true = [1, 2]
y_pred = [[0.05, 0.95, 0], [0.1, 0.8, 0.1]]
# Using ...
type:Bug
bibhas2
- Opened 11 days ago
- #21426
I ve been playing around with Keras s built-in visualizations tool for a while and I feel like it could be improved a
lot. The current visualization system doesn t provide much information at a glance ...
stat:awaiting keras-eng
type:feature
Soontosh
- 2
- Opened 12 days ago
- #21421
Seems to be an issue with keras.ops.image.map_coordinates and TF backend. Seems to happen on both CPU and GPU.
details closed summary Versions /summary br TF: 2.19.0 Keras: 3.10.0 JAX: 0.5.2 PyTorch: ...
type:Bug
tristan-deep
- 1
- Opened 12 days ago
- #21420
The skip_mismatch flag when loading H5 weights is not respected unless by_name is also specified. Otherwise, it just
fails with an error:
ValueError Traceback (most recent ...
type:Bug
DLumi
- 1
- Opened 18 days ago
- #21404
import tensorflow as tf import keras from keras.src import ops
keras.backend.set_image_data_format( channels_first )
x = tf.zeros((3, 12, 224, 224))
output_upsampling_layer = keras.layers.UpSampling2D(size=(2, ...
type:Bug
tristandb8
- 5
- Opened 19 days ago
- #21401
This is very nit-picky, but I happened to look at the RNN constructor and see that a ValueError is raised when, by
definition, the exception should be a TypeError, right?
https://github.com/keras-team/keras/blob/764ed95651c1c7dfa71ca523287f6eeb514ccf77/keras/src/layers/rnn/rnn.py#L221-L225 ...
stat:awaiting response from contributor
type:Bug
jfdev001
- 3
- Opened 20 days ago
- #21391
Not sure if this is Torch or Keras issue, but simple LSTM models cannot be exported as ONNX.
TypeError: Exception encountered when calling LSTM.call().
unsupported operand type(s) for -: torch.return_types.max ...
backend:torch
stat:contributions welcome
type:Bug
- 2
- Opened 20 days ago
- #21390
When using SKLearnClassifier or SKLearnRegressor wrappers with no other scikit-learn imports (such as
make_classification) the following error is raised:
AttributeError: module sklearn.utils has no ...
type:Bug
timovdk
- Opened 21 days ago
- #21386
The examples in the docstrings for SKLearnClassifier and SKLearnRegressor are currently not working. This is because of
several small issues:
- General issues:
- Importing layers from keras.src.layers ...
type:docs-bug
- Opened 21 days ago
- #21384
Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.