-
Notifications
You must be signed in to change notification settings - Fork 74k
Issues: tensorflow/tensorflow
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
INT4 and other low-precision conversion support status
comp:lite
TF Lite related issues
ModelOptimizationToolkit
TF Model Optimization Toolkit
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TFLiteConverter
For issues related to TFLite converter
type:feature
Feature requests
#64193
opened Mar 21, 2024 by
AIWintermuteAI
Full Integer Quantization Issue with Multiple Signatures in TensorFlow Lite
comp:lite
TF Lite related issues
ModelOptimizationToolkit
TF Model Optimization Toolkit
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TF 2.15
For issues related to 2.15.x
TFLiteConverter
For issues related to TFLite converter
type:performance
Performance Issue
#62996
opened Feb 20, 2024 by
lxzheng
TFLite Converter, add possibility to ignore some OPs from quantization
comp:lite
TF Lite related issues
ModelOptimizationToolkit
TF Model Optimization Toolkit
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TF 2.13
For issues related to Tensorflow 2.13
TFLiteConverter
For issues related to TFLite converter
type:feature
Feature requests
#62923
opened Feb 8, 2024 by
adamp87
Model conversion crashed when feed data during quantization
comp:lite
TF Lite related issues
ModelOptimizationToolkit
TF Model Optimization Toolkit
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TF 2.15
For issues related to 2.15.x
TFLiteConverter
For issues related to TFLite converter
type:bug
Bug
#62701
opened Dec 27, 2023 by
houcheng
Internal quantize ops don't match external quantization
comp:lite
TF Lite related issues
comp:ops
OPs related issues
ModelOptimizationToolkit
TF Model Optimization Toolkit
stale
This label marks the issue/pr stale - to be closed automatically if no activity
stat:awaiting response
Status - Awaiting response from author
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TF2.14
For issues related to Tensorflow 2.14.x
TFLiteConverter
For issues related to TFLite converter
type:bug
Bug
type:performance
Performance Issue
#62530
opened Dec 1, 2023 by
EClemMarq
PadV2 constant_values tensor not quantized using 16x8 quantization mode
comp:lite
TF Lite related issues
ModelOptimizationToolkit
TF Model Optimization Toolkit
stale
This label marks the issue/pr stale - to be closed automatically if no activity
stat:awaiting response
Status - Awaiting response from author
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TF 2.15
For issues related to 2.15.x
TFLiteConverter
For issues related to TFLite converter
#62499
opened Nov 29, 2023 by
riestmo-nxp
[RNN] TFLite converter segfaults with GRU models
comp:lite
TF Lite related issues
ModelOptimizationToolkit
TF Model Optimization Toolkit
regression issue
To spot regression issues in latest version
stale
This label marks the issue/pr stale - to be closed automatically if no activity
stat:awaiting response
Status - Awaiting response from author
TF2.14
For issues related to Tensorflow 2.14.x
TFLiteConverter
For issues related to TFLite converter
type:performance
Performance Issue
#62281
opened Oct 30, 2023 by
CNugteren
Quantization produces large scale coffiecient, which pervents the model from being loaded
comp:lite
TF Lite related issues
ModelOptimizationToolkit
TF Model Optimization Toolkit
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TF 2.13
For issues related to Tensorflow 2.13
TFLiteConverter
For issues related to TFLite converter
type:bug
Bug
#62196
opened Oct 23, 2023 by
FabianSchuetze
error with concatenation when converting QAT model to tflite model using EXPERIMENTAL_TFLITE_BUILTINS_ACTIVATIONS_INT16_WEIGHTS_INT8
comp:lite
TF Lite related issues
ModelOptimizationToolkit
TF Model Optimization Toolkit
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TF 2.13
For issues related to Tensorflow 2.13
TFLiteConverter
For issues related to TFLite converter
type:bug
Bug
type:feature
Feature requests
#62014
opened Sep 29, 2023 by
DerryFitz
TFLite model produces wrong output after fusion optimization
comp:lite
TF Lite related issues
ModelOptimizationToolkit
TF Model Optimization Toolkit
stale
This label marks the issue/pr stale - to be closed automatically if no activity
stat:awaiting response
Status - Awaiting response from author
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TFLiteConverter
For issues related to TFLite converter
type:bug
Bug
#61967
opened Sep 25, 2023 by
dengyinlin
Why are not all of my conv2d layer weights Int8 when converting with dynamic range quantization?
comp:lite
TF Lite related issues
ModelOptimizationToolkit
TF Model Optimization Toolkit
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TF 2.13
For issues related to Tensorflow 2.13
TFLiteConverter
For issues related to TFLite converter
type:bug
Bug
#61896
opened Sep 18, 2023 by
christian-steinmeyer
Uncompliant tflite model when converting "MultiHeadAttention" layer
comp:lite
TF Lite related issues
ModelOptimizationToolkit
TF Model Optimization Toolkit
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TF 2.13
For issues related to Tensorflow 2.13
TFLiteConverter
For issues related to TFLite converter
type:bug
Bug
#61796
opened Sep 5, 2023 by
kobygold
Full integer quantization not possible with grouped convolution
ModelOptimizationToolkit
TF Model Optimization Toolkit
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TF 2.13
For issues related to Tensorflow 2.13
TFLiteConverter
For issues related to TFLite converter
type:bug
Bug
#61760
opened Aug 31, 2023 by
justlike-prog
Looking for selective post training quantization for 8 bit weights and 16 bit activations
comp:lite
TF Lite related issues
ModelOptimizationToolkit
TF Model Optimization Toolkit
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TF 2.13
For issues related to Tensorflow 2.13
type:feature
Feature requests
#61720
opened Aug 28, 2023 by
Hrayo712
Segmentation Fault (Core Dumped) when convert whisper with int8 quantization
comp:lite
TF Lite related issues
ModelOptimizationToolkit
TF Model Optimization Toolkit
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TF 2.12
For issues related to Tensorflow 2.12
TFLiteConverter
For issues related to TFLite converter
type:bug
Bug
#61695
opened Aug 25, 2023 by
SantiagoMoreno-UdeA
converting LSTM layer to tflite with float16 fails
comp:lite
TF Lite related issues
ModelOptimizationToolkit
TF Model Optimization Toolkit
RNN
RNN related issues
stale
This label marks the issue/pr stale - to be closed automatically if no activity
stat:awaiting response
Status - Awaiting response from author
TF 2.13
For issues related to Tensorflow 2.13
TFLiteConverter
For issues related to TFLite converter
type:bug
Bug
#61370
opened Jul 24, 2023 by
sronen71
TensorFlow Lite Converter wraps unpack operator with dequantize/quantize
ModelOptimizationToolkit
TF Model Optimization Toolkit
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TF 2.12
For issues related to Tensorflow 2.12
TFLiteConverter
For issues related to TFLite converter
type:bug
Bug
#61323
opened Jul 19, 2023 by
willisacs-arm
[TFLite] Accumulator and bias types coherence for int16x8 FC operator
comp:lite
TF Lite related issues
comp:lite-kernels
TensorFlow Lite kernel issues
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
type:bug
Bug
#53763
opened Jan 14, 2022 by
Tessil
DSP Overflow - high pixel values are being clamped when running on DSP
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TF 2.7
Issues related to TF 2.7.0
TFLiteConverter
For issues related to TFLite converter
type:support
Support issues
#53552
opened Dec 27, 2021 by
aviaisr
Disable unroll batch matmul pass
TFLiteConverter
For issues related to TFLite converter
type:feature
Feature requests
#47425
opened Feb 26, 2021 by
WindQAQ
TFLite converter does not convert dilated conv to single conv op when spatial dimension is dynamic
comp:lite
TF Lite related issues
stat:awaiting tensorflower
Status - Awaiting response from tensorflower
TF 2.4
for issues related to TF 2.4
TFLiteConverter
For issues related to TFLite converter
type:bug
Bug
#46822
opened Feb 1, 2021 by
WindQAQ
ProTip!
Add no:assignee to see everything that’s not assigned.