You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Following the discussion on slack, I am trying to compile a list of questions from the last 3 days for the purpose of finding trends and updating FAQ. The current idea is to compile a summary page for issues during a period, say weekly, and picking candidates to add to FAQ.
You are welcome to share your thoughts, specially on
whether this is useful
how to go about it by using community efforts - commitment from specific people might not be a long term solution.
I have spent almost 2 hours compiling the questions from last 3 days - somehow longer than I expected.
collection of questions fr om both issue pages and gitter, slack groups
formats of this sharing
For this experiment, I have put questions in the following categories.
_bug_: bug reporting
_documentation_: chance for revision of documentation
_configuration_: installation, configuration, integration with other tools
_performance_: need suggestions for performance improvments
_customization_: lego-building new layers/models by Keras
_enhancement_: feature requests, modifications for Keras itself
Following the discussion on slack, I am trying to compile a list of questions from the last 3 days for the purpose of finding trends and updating FAQ. The current idea is to compile a summary page for issues during a period, say weekly, and picking candidates to add to FAQ.
You are welcome to share your thoughts, specially on
I have spent almost 2 hours compiling the questions from last 3 days - somehow longer than I expected.
For this experiment, I have put questions in the following categories.
See the compilation below.
Bug
Gradients may become inf/nan through merge(mode = 'cos') #3941
merge(mode='cos')
implementation to avoidinf/nan
gradients errorCompatibility models keras 1.0.4 and 1.1.0 #3957
fail to load model with multiple outputs that have multiple metrics #3958
load_model
doesn't work for multiple output with multiple metricsCifar-10 example not converging when image_dim_ordering == 'tf' #3959
tf
image_dim_orderingload_model fails to load optimizer #3964
load_model
fails to load optimizer butmodel_from_json
andload_weights
work fineNone type on input size does not seem to work. #3965
None
ininput_shape
forConvolution2D
withtf
backend throws errorDocumentation
Dimension conventions #3925
Unable to Call model.predict_classes() #3938
predict_classes
on a non-sequential model throws an errorKeras MaxPooling2D gives ValueError: Negative dimension size caused by subtracting 2 from 1 for 'MaxPool_x' #3945
dim_ordering
flow_from_directory seems to find no images #3946
ImageDataGenerator.flow_from_directory
didn't work if there is no subdir createdInput, InputLayer, Embedding, Merge does not import #3951
keras.layers.core
doesn't work any moreConfiguration
Theano backend will not work on AWS Ubuntu:14.04 #3936
Performance
Memory not released from the gpu #3939
gc.collect()
doesn't workOut of memory after 4 epochs #3954
gc.collect()
doesn't workHow to normalize input #3943
BatchNorm with statistics from whole dataset #3949
BatchNormalization
has a highmomentum
value which influences performanceskeras 1.1.0 conv problems? #3956
Convolution2D
,MaxPooling2D
from 1.0.6 to 1.1.0Customization
SRGAN - Bypass check_array_lengths(X, Y, W) in training.py for different input and output batch sizes #3940
Implementing Custom Bilinear tensor product layer in keras #3944
error making simple FFT layer #3950
How to create multiple outputs of sigmoid activation with shared layers #3960
softmax
with nsigmoid
activationsHow to parallelize fit_generator? (PicklingError) #3962
Enhancement
GlobalPooling for 3D inputs #3942
GlobalMaxPooling3D
andGlobalAveragePooling3D
Feature Request: Output transformation in ImageDataGenerator #3953
ImageDataGeneator
The text was updated successfully, but these errors were encountered: