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 2.2.028May2722212019161514652130Apr18161411109843131Mar2928272524232221201714121110765432128Feb272625232017151413121110631Jan2724232221161513109826Dec231916151411965432130Nov25242221209876542131Oct292726232218131143130Sep27212016429Aug279731Jul2522211917161513119854130Jun29262522211915141310729May221716151413107129Apr282524ADC: refactor rl_lib directory structureAdd missing **kwargs in on_epoch_begin of knowledge distill policyMerge branch 'master' into new_amcUpdate dataset_summaries.pymobilenet-ddpg-reconstruction___2019.05.27-000814Bug fix for shared module (#268)Added support for setting the PRNG seed (#269)Log pip freeze (#266)ncf.py - fix wrong nb_users/itemsStore qe_stats_file in output directory (#262)NCF scripts with Distiller integrationFix type hint usage which breaks on Python 3.5Fixed KeyError treatment in Quantizer._pre_process_container (#263)Thinning: added support for group-wise convolutionsChanges in activation stats collectorsdata_loaders.py: fix crash in case of fixed_subset=TrueBugfix in bias handling in quant-aware training (fixes issue #248)Bug fix in n_stds clipping calculation (fix issue #249)Update PostTrainQuantizer initialization sample in docs (add htmls)Update PostTrainQuantizer initialization sample in docsPost-training quantization: Scale factor approximation (#261)model_summaries.py: add simple Conv layer annotations to PNG exportRefactoring: utils.get_dummy_input()Fix test_onnx.pycompress_classifier.py: --summary related fixesMerge branch 'master' of https://github.com/NervanaSystems/distillerRefactor export to ONNX functionality (#258)collector.py: Switch matplotlib backend to one w/o dependenciesSummaryGraph: fix ‘weights_vol’ attribute for conv and linear layersRevert "SummaryGraph: fix ‘weights_vol’ attribute for conv and linear layers"Added convert_model_to_distiller_lstm (#259)Merge branch 'master' of https://github.com/NervanaSystems/distillerSummaryGraph: fix ‘weights_vol’ attribute for conv and linear layersActivation Histograms (#254)SummaryGraph changes: _force_outplace + OrderedDictsFix failing test after last post-train quant changeImproved logging when saving collectors data (#251)Post train quant - warn instead of exit when dynamic quant not supportedMerge branch 'master' of https://github.com/NervanaSystems/distillerFix broken load test (#245)