SforAiDl/KD_Lib

Issues

• Error in Documentation

  #150 opened 8 months ago by msalexms
  0

• Relational KD

  #147 opened 2 years ago by gadhane
  0

• Is there a suitable speech enhancement ?

  #144 opened 2 years ago by zuowanbushiwo
  1

• No module named 'KD_Lib.KD'

  #143 opened 2 years ago by tolusophy
  8

• Can I skip training the teacher network?

  #142 opened 2 years ago by Haalum
  1

• Test BERT2LSTM with mock data

  #137 opened 3 years ago by NeelayS
  0

• Create 'main' branch and set it as default

  #132 opened 3 years ago by NeelayS
  2

• Use mock data for unit tests

  #131 opened 3 years ago by NeelayS
  0

• Consider potential name change to 'kdlib'

  #133 opened 3 years ago by NeelayS
  2

• distillation of gelectra model

  #130 opened 3 years ago by OriAlpha
  0

• Issue with CUDA

  #129 opened 3 years ago by OriAlpha
  2

• custom dataloader for NLP dataset

  #128 opened 3 years ago by OriAlpha
  4

• Paper: Data-Distortion Guided Self-Distillation for Deep Neural Networks

  #127 opened 3 years ago by yiqings
  2

• Paper: Subclass Distillation

  #54 opened 4 years ago by NeelayS
  4

• RuntimeError: only batches of spatial targets supported (3D tensors) but got targets of dimension: 4

  #122 opened 3 years ago by GeneralJing
  7

• NameError: name 'best_student_id' is not defined

  #116 opened 3 years ago by PiaCuk
  1

• Implement Knowledge distillation by Functional Mapping

  #121 opened 3 years ago by manncodes
  1

• Pip install "stable" doesn't work

  #108 opened 4 years ago by BrunoGomesCoelho
  3

• Benchmarking KD

  #105 opened 4 years ago by avishreekh
  0

• Validation on the fly and saving models according to validation accuracy

  #95 opened 4 years ago by ashwinvaswani
  3

• Distributed Training

  #79 opened 4 years ago by Het-Shah
  5

• [Paper] Learning Deep Representations with Probabilistic Knowledge Transfer

  #46 opened 4 years ago by khizirsiddiqui
  0

• Docs

  #67 opened 4 years ago by Het-Shah
  4

• Restructuring KD_Lib

  #61 opened 4 years ago by NeelayS
  3

• Making a pipeline for Pruning, Quantization and Knowledge Distillation

  #107 opened 4 years ago by Het-Shah
  0

• Benchmarking Pruning and Quantization

  #106 opened 4 years ago by avishreekh
  0

• import error

  #104 opened 4 years ago by samo313
  14

• DML Loss function

  #102 opened 4 years ago by aryanasadianuoit
  2

• Update setup.py

  #82 opened 4 years ago by NeelayS
  14

• [Paper] Regularizing Class-wise Predictions via Self-knowledge Distillation

  #93 opened 4 years ago by ashwinvaswani
  0

• Refix and Benchmarking

  #56 opened 4 years ago by Het-Shah
  2

• Very minor bug in TAKD

  #92 opened 4 years ago by ashwinvaswani
  1

• ETA while logging or Progress Bar implementation

  #94 opened 4 years ago by ashwinvaswani
  1

• Evaluators missing in models

  #91 opened 4 years ago by ashwinvaswani
  0

• Quantization logs

  #87 opened 4 years ago by avishreekh
  0

• Quantization Aware Training

  #81 opened 4 years ago by Het-Shah
  1

• Optuna

  #80 opened 4 years ago by Het-Shah
  0

• Dynamic Quantization

  #72 opened 4 years ago by avishreekh
  2

• Restructure text-based models and utilities

  #57 opened 4 years ago by avishreekh
  3

• Paper: The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

  #50 opened 4 years ago by avishreekh
  0

• Paper: Deep Mutual Learning

  #49 opened 5 years ago by NeelayS
  4

• Paper: Distilling Task-Specific Knowledge from BERT into Simple Neural Networks

  #38 opened 5 years ago by avishreekh
  0

• Paper: Improving Generalization Robustness with Noisy Collaboration in Knowledge Distillation

  #47 opened 5 years ago by NeelayS
  0

• Paper: Preparing Lessons: Improve Knowledge Distillation with Better Supervision

  #44 opened 5 years ago by NeelayS
  0

• Born Again Neural Networks

  #42 opened 5 years ago by khizirsiddiqui
  0

• Paper: Knowledge Distillation via Route Constrained Optimization

  #31 opened 5 years ago by NeelayS
  0

• Paper : Mean Teachers are Better Role Models

  #30 opened 5 years ago by khizirsiddiqui
  1

• Paper: Revisit Knowledge Distillation: A Teacher Free Framework

  #36 opened 5 years ago by NeelayS
  0

• Device parameter of Base class

  #33 opened 5 years ago by avishreekh
  2

• Documentation

  #28 opened 5 years ago by khizirsiddiqui
  2