Skip to content
Snippets Groups Projects

Repository graph

You can move around the graph by using the arrow keys.
Select Git revision
  • 4-bit-qat
  • api_changes
  • ax_integration
  • gste
  • inception_support
  • kd_fixes
  • lattice_regularization
  • load_quant_aware_train_checkpoint
  • master default protected
  • ptq_propagate_settings
  • scale_approximation
  • update_links
  • v0.3.2
  • amc_before_pytorch1.1_merge
  • v0.3.1
  • v0.3.0
  • v0.2.1
  • v0.2.0
  • v0.1.0
19 results
Created with Raphaël 2.2.09Feb653219Jan1815630Dec29261812119843228Nov27262520181716141311108765431Oct30282725232276528Sep27252423181098752129Aug2827262423222120191413129876431Jul29262423222117161087432130Jun2625242322191817141311103230May29282722212019161514652130Apr18161411109843131Mar2928272524232221201714121110765432128Feb272625232017151413121110631Jan2724232221161513109826Dec231916151411965432130Nov25242221209876542131Oct292726232218131143130Sep27212016429Aug279731Jul2522211917161513119854130Jun292625Update _Regularizer docstrings for clarity of API.lattice_regular…lattice_regularizationAdded PotentialWellLattice regularizationConvert Distiller PTQ models to "native" PyTorch PTQ (#458)Merge branch 'master' into distribution_aware_trainingFix path in LAPQ yamlLoss Aware Post Train Quantization search (#432)Fix requirements.txt - due to torchvision/pillow mismatchranked_structures_pruner.py: fix error messageFix scale factor calculation in symmetric quantization (#463)Post-train quant: Refactor inputs quantization (#454)Separate LinearQuantMode for weights/activations (#451)Add Mobilenet v1 baseline training scriptFix broken links in image classification sample readmeIFM sparsity collector (#443)Bugfix - missing argument in post-quant training unitest (thanks @barrh)...Add support for wide-resnet models that exist in torchvisionQuantization stats collection minor updatesUpdate examples READMEUpdate READMEUpdate Examples Documentation (#441)Updated README.md in object_detection.Enable weights/activations-only PTQ for conv/linear modules (#439)Update PTQ ResNet-50 command line results.Flow working for quantizers that don't update the optimizerMerge branch 'master' into load_quant_aware_train_checkpointBugfix - Save stats to file when 'qe-calibration' arg is used (#437)object detection: remove unsupported summariesobject detection: fix model summary generationHotfix to sim_bn_fold.py after breaking mergeObject Detection Compression (#343)Added model_setattr - sets an parameter/buffer/moduleMerge branch 'master' into load_quant_aware_train_checkpointMerge branch 'master' of https://github.com/NervanaSystems/distillerAMC: fix problems reported in issue #429
Loading