issues Search Results · repo:keras-team/keras language:Python
Filter by
12k results
(83 ms)12k results
inkeras-team/keras (press backspace or delete to remove)Hello,
I would like to get the inputs of a given layer linked to a previous layer.
My code with Keras 2.x was the following
def get_inputs(layer):
Get the inputs of a layer.
inputs = [] ...
type:support
jfthuong
- Opened yesterday
- #21205
In the class Embedding(Layer) keras/src/layers/core/embedding.py
def build(self, input_shape=None):
if self.built:
return
if self.quantization_mode is not None:
...
Fricker95
- Opened yesterday
- #21201
1. For a specific reason, I need to run some operations into specific device while keeping other operations runable
with global distribution. In torch, we can do .to(device_id) to place operations ...
keras-team-review-pending
type:feature
innat
- Opened 3 days ago
- #21190
When using a Keras SimpleRNN layer with stateful=True, the documentation states that a fixed batch size is required.
However, when a model is built with batch_size=N (e.g. 4), and later called with an ...
type:Bug
El3ssar
- Opened 6 days ago
- #21183
Inference with TimeDistributed(Dense(1, activation= sigmoid )) in Keras 3 is a lot slower than in Keras 2 (tf.keras)
Profiling shows TimeDistributed is the bottleneck.
Model: Conv1D → LSTM → Conv1DTranspose ...
type:performance
Moublrs
- 2
- Opened 6 days ago
- #21179
https://github.com/keras-team/keras/issues/21025#issuecomment-2808020133
The following code is tested with keras-nightly.
Basically two issue.
1.
import tensorflow as tf
import os
import numpy as ...
type:Bug
- 1
- Opened 8 days ago
- #21173
It seems as though distributed training with keras version 3.7 and above with tensorflow isn t supported.
https://stackoverflow.com/questions/79285532/multi-gpu-training-in-tensorflow-results-in-nans?noredirect=1#comment140127186_79285532 ...
stat:awaiting response from contributor
type:Bug
DarrenR96
- 1
- Opened 8 days ago
- #21172
In tensorflow graph mode, RandAugment will repeatedly use the same augmentations, which were sampled during graph
tracing.
It relies on shuffling a python list using random.shuffle, which only works during ...
type:Bug
gregstarr
- 5
- Opened 8 days ago
- #21169
When using multiple GPUs (n 1) with a batch size that s not divisible by the number of GPUs, you ll encounter a
ZeroDivisionError. I understand that library needs to split the batch evenly across devices. ...
type:Bug
- 4
- Opened 9 days ago
- #21167
Ordinarily, when serializing layers, we get a flat hierarchy in the resulting file. For example, the following code
@keras.saving.register_keras_serializable()
class TestModel(keras.Model):
def __init__(self, ...
stat:awaiting response from contributor
type:Bug
niels-leif-bracher
- 1
- Opened 9 days ago
- #21166
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!
Restrict your search to the title by using the in:title qualifier.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!
Restrict your search to the title by using the in:title qualifier.