Topics tagged model_optimization

Topic	Replies	Views	Activity
How to formulate a loss function that minimizes both cross-entropy and an additional term? TensorFlow help_request , model_optimization , custom-loss	4	503	July 11, 2023
None of the MLIR Optimization passes are enabled General Discussion help_request , mlir , model_optimization , model_garden	14	42100	January 30, 2023
While doing quantization, Is it possible to specify the scale and zero point to tensorflow int8 kernel? General Discussion models , help_request , tflite , model_optimization	3	2167	January 30, 2023
Please share the pruning & fine-tuning configuration of MobileNet V2 General Discussion help_request , model_optimization	1	706	October 26, 2022
Does not improve predictive performance --> ("pruning for on device inference") General Discussion help_request , model_optimization	0	521	September 22, 2022
Results of the pruning model General Discussion model_optimization , help_request	6	885	June 15, 2022
Weight tensors after applying Structural pruning General Discussion help_request , model_optimization	2	1158	June 2, 2022
Reducing XLA AOT compiled model size General Discussion models , help_request , xla , model_optimization	4	1840	May 17, 2022
Pruned Model Stripping General Discussion model_optimization , help_request	4	2018	May 16, 2022
Structured vs Unstructured Pruning General Discussion help_request , model_optimization	3	1542	May 13, 2022
Fine-tune pre-trained model with pruning General Discussion help_request , model_optimization , learning	1	1584	May 13, 2022
Customize structural pruning rate in each layer General Discussion keras , help_request , model_optimization	4	1583	May 13, 2022
Model quantization aware training problem General Discussion help_request , model_optimization	1	1109	May 13, 2022
Quantization aware training -> In/Output still float32? General Discussion models , help_request , keras , model_optimization	1	1590	May 13, 2022
How to use tensorflow model optimization for prune without any tf.keras support? General Discussion models , keras , help_request , model_optimization	2	1544	May 9, 2022
Quantization aware training with quantizationConfig -> 4 % Accuracy loss General Discussion models , help_request , keras , model_optimization	1	1676	April 25, 2022
Is it possible to use 8 bit integers instead of floating point numbers? General Discussion model_optimization , help_request	1	1099	April 20, 2022
Layers not pruned after using prune_low_magnitude General Discussion help_request , model_optimization	2	1427	February 14, 2022
Where can I find sysmetric TFlite quantization model? TensorFlow model_optimization , feature_request , tflite	1	1824	December 9, 2021
Transfer learning and Quantization aware training. Subclassed model General Discussion models , help_request , keras , model_optimization , learning	2	2992	December 3, 2021
4 bit quantization aware training General Discussion training , help_request , model_optimization	1	2064	October 19, 2021
Improvement of API: Measures to avoid ValueError when pruning low manitude General Discussion models , help_request , model_optimization	2	1395	September 8, 2021
How to convert a tensor to a numpy array without enabling the run_eagerly flag in keras General Discussion model_optimization , keras , help_request	3	11743	September 6, 2021
How do I quantize the weights of neural networks? General Discussion keras , help_request , model_optimization	1	441	August 5, 2021
Add quantization output configuration for QAT General Discussion keras , help_request , model_optimization , tflite	2	1630	August 4, 2021
Clustering after pruning General Discussion model_optimization , keras , help_request	2	1616	July 30, 2021
Why apply G-Zip after pruning or weight clustering? General Discussion tflite , model_optimization	5	1289	July 21, 2021
Pruning a trained Object Detection SavedModel General Discussion model_garden , models , model_optimization	2	1924	July 20, 2021
'function_optimizer.py' returns empty graph General Discussion model_optimization , keras , help_request , model_garden	18	3372	July 9, 2021
No model size reduction in Tflite model size with integer Quantisation General Discussion tflite , models , keras , help_request , model_optimization	6	2105	July 7, 2021