mct-nightly 2.2.0.20241222.533__py3-none-any.whl → 2.2.0.20241224.532__py3-none-any.whl

{mct_nightly-2.2.0.20241222.533.dist-info → mct_nightly-2.2.0.20241224.532.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mct-nightly
-Version: 2.2.0.20241222.533
+Version: 2.2.0.20241224.532
 Summary: A Model Compression Toolkit for neural networks
 Home-page: UNKNOWN
 License: UNKNOWN

{mct_nightly-2.2.0.20241222.533.dist-info → mct_nightly-2.2.0.20241224.532.dist-info}/RECORD

@@ -1,4 +1,4 @@
-model_compression_toolkit/__init__.py,sha256=jABMKR_HAdl9dzUBbLzsNkhudC3H3DbwbmMwxMkokpk,1573
+model_compression_toolkit/__init__.py,sha256=9suCm_ya-q7binwaiEyGExSDb8bJgOWwJ3wBnV_el2Y,1573
 model_compression_toolkit/constants.py,sha256=i_R6uXBfO1ph_X6DNJych2x59SUojfJbn7dNjs_mZnc,3846
 model_compression_toolkit/defaultdict.py,sha256=LSc-sbZYXENMCw3U9F4GiXuv67IKpdn0Qm7Fr11jy-4,2277
 model_compression_toolkit/logger.py,sha256=3DByV41XHRR3kLTJNbpaMmikL8icd9e1N-nkQAY9oDk,4567
@@ -32,8 +32,8 @@ model_compression_toolkit/core/common/fusion/__init__.py,sha256=Rf1RcYmelmdZmBV5
 model_compression_toolkit/core/common/fusion/graph_fuser.py,sha256=5VkHB2fW0ohfPQmISz6o4fCMV8QyFdj5_kU51lN0JS8,6214
 model_compression_toolkit/core/common/fusion/layer_fusing.py,sha256=lOubqpc18TslhXZijWUJQAa1c3jIB2S-M-5HK78wJPQ,5548
 model_compression_toolkit/core/common/graph/__init__.py,sha256=Xr-Lt_qXMdrCnnOaUS_OJP_3iTTGfPCLf8_vSrQgCs0,773
-model_compression_toolkit/core/common/graph/base_graph.py,sha256=GG13PAtndsMjIqINfrCN6llVkFrg5CBfij4z99ntieU,37815
-model_compression_toolkit/core/common/graph/base_node.py,sha256=QPV2PWpYGtS2qB-uioYeGEgEEnPuOy-UFOLVyjWWIvg,31877
+model_compression_toolkit/core/common/graph/base_graph.py,sha256=6jlwj4WDT3XJKf1QQ4Aougswhl-Xx51QzV58CePbjVg,37818
+model_compression_toolkit/core/common/graph/base_node.py,sha256=kENyhUfHuU0LiYJ1EiCPmtfOA5UANYteeS7JIbpLiHI,31886
 model_compression_toolkit/core/common/graph/edge.py,sha256=buoSEUZwilWBK3WeBKpJ-GeDaUA1SDdOHxDpxU_bGpk,3784
 model_compression_toolkit/core/common/graph/functional_node.py,sha256=GH5wStmw8SoAj5IdT_-ItN1Meo_P5NUTt_5bgJC4fak,3935
 model_compression_toolkit/core/common/graph/graph_matchers.py,sha256=CrDoHYq4iPaflgJWmoJ1K4ziLrRogJvFTVWg8P0UcDU,4744
@@ -111,7 +111,7 @@ model_compression_toolkit/core/common/quantization/quantization_fn_selection.py,
 model_compression_toolkit/core/common/quantization/quantization_params_fn_selection.py,sha256=MwIOBZ4BlZSTIOG75PDvlI3JmZ6t8YjPc1VP9Adei60,3847
 model_compression_toolkit/core/common/quantization/quantize_graph_weights.py,sha256=N005MSvx8UypVpa7XrxNrB2G732n2wHj3RmLyjTgd3I,2728
 model_compression_toolkit/core/common/quantization/quantize_node.py,sha256=cdzGNWfT4MRogIU8ehs0tr3lVjnzAI-jeoS9b4TwVBo,2854
-model_compression_toolkit/core/common/quantization/set_node_quantization_config.py,sha256=ChhXckn8E3Kot6g5R27KD2WSVMzPfqVwkeTJ0UeBdyg,21257
+model_compression_toolkit/core/common/quantization/set_node_quantization_config.py,sha256=94CQga1cg9zCHju8zBbuZYaXUR1wbbOjXHzzAwFxgUU,21269
 model_compression_toolkit/core/common/quantization/quantization_params_generation/__init__.py,sha256=eCDGwsWYLU6z7qbEVb4TozMW_nd5VEP_iCJ6PcvyEPw,1486
 model_compression_toolkit/core/common/quantization/quantization_params_generation/error_functions.py,sha256=fzUvqmXVgzp_IV5ER-20kKzl4m8U_shZsAKs-ehhjFo,23887
 model_compression_toolkit/core/common/quantization/quantization_params_generation/lut_kmeans_params.py,sha256=RL-PklAjGyC-26anSt8fU07a6pB_LBQFQy9o4e9giN0,8739
@@ -144,7 +144,7 @@ model_compression_toolkit/core/common/substitutions/linear_collapsing_substituti
 model_compression_toolkit/core/common/substitutions/remove_identity.py,sha256=TKU1TIU52UIkVnl0EZvWnDhLV9nIVZ4hqi-w1i4NXMk,2637
 model_compression_toolkit/core/common/substitutions/residual_collapsing.py,sha256=N82mso5j3EJQlKt9EMHjjEJ67FmdGQeCfN8U5grOFXo,4830
 model_compression_toolkit/core/common/substitutions/scale_equalization.py,sha256=p57u25qdW2pimxzGwgMXEBV4S-LzXuTVAlIM7830WfU,10966
-model_compression_toolkit/core/common/substitutions/shift_negative_activation.py,sha256=gFJ4Fs3358FLp0ZlZM9k6s56cD8EOcfLTxxXpuQSLqU,30063
+model_compression_toolkit/core/common/substitutions/shift_negative_activation.py,sha256=H-8gvU7em4gVUp_EYAi6Fa-fgOQ_ICJTA3Z68or2qpI,30069
 model_compression_toolkit/core/common/substitutions/softmax_shift.py,sha256=R-0ZqhYAuZLEFWHvB2UTPm52L6gWHGdRdEnwGxKSeGI,2625
 model_compression_toolkit/core/common/substitutions/virtual_activation_weights_composition.py,sha256=aXzUOJfgKPfQpEGfiIun26fgfCqazBG1mBpzoc4Ezxs,3477
 model_compression_toolkit/core/common/substitutions/weights_activation_split.py,sha256=h85L2VlDOqbLd-N98wA3SdYWiblBgSsPceNuLanJd70,4737
@@ -431,18 +431,19 @@ model_compression_toolkit/target_platform_capabilities/__init__.py,sha256=cco4Tm
 model_compression_toolkit/target_platform_capabilities/constants.py,sha256=iJXGy5um7vhC84Me4ld6EHMhy7jPks0T9ItZX23si6s,1519
 model_compression_toolkit/target_platform_capabilities/immutable.py,sha256=YhROBiXEIB3TU-bAFrnL3qbAsb1yuWPBAQ_CLOJbYUU,1827
 model_compression_toolkit/target_platform_capabilities/schema/__init__.py,sha256=pKAdbTCFM_2BrZXUtTIw0ouKotrWwUDF_hP3rPwCM2k,696
-model_compression_toolkit/target_platform_capabilities/schema/mct_current_schema.py,sha256=MxEMpEYHpcgGqHMn371jJU6SMCMvV9qXn1NvjQ4XFik,485
-model_compression_toolkit/target_platform_capabilities/schema/schema_functions.py,sha256=8Ek7nigw_RYLc5eRjbKr70aqysu_GD_hE1AtcKGi6yg,4610
-model_compression_toolkit/target_platform_capabilities/schema/v1.py,sha256=R_CjTWFiVja11WzOxRNqlOaj36zRJyaAE5s8FaP-Yx4,29147
-model_compression_toolkit/target_platform_capabilities/target_platform/__init__.py,sha256=0l1Y2EqivDkWRRRhirSRI3vwUzhUcSTrYgrwKIqO0IM,1548
-model_compression_toolkit/target_platform_capabilities/target_platform/current_tp_model.py,sha256=1Glr4qKDJfdk5TwM5fzZ12XzgbpQFioDOxb475905gk,2013
-model_compression_toolkit/target_platform_capabilities/target_platform/target_platform_model.py,sha256=TDJ65oCoMCVf2vqOlyioAZeOaPAILhNHcxLVMfszoII,1346
+model_compression_toolkit/target_platform_capabilities/schema/mct_current_schema.py,sha256=E6Zz8boibgfq8EVpZWyl0TOdFrv9qrwiVHUzYPIKVrQ,528
+model_compression_toolkit/target_platform_capabilities/schema/schema_functions.py,sha256=ZDFN2N4dRRP6qs0HxsHXEJbZCwYByo3JL9sBCJolDBs,4656
+model_compression_toolkit/target_platform_capabilities/schema/v1.py,sha256=GsToWecNswbQCnLPBNsFBK5uX8B69jN9N-tXEmmU6WI,25223
+model_compression_toolkit/target_platform_capabilities/target_platform/__init__.py,sha256=1FXmDVSqm-dr3xzH4vRo4NmAgyzBZjqHo5l63MUq4r0,1403
 model_compression_toolkit/target_platform_capabilities/target_platform/targetplatform2framework/__init__.py,sha256=WCP1wfFZgM4eFm-pPeUinr5R_aSx5qwfSQqLZCXUNBA,1513
+model_compression_toolkit/target_platform_capabilities/target_platform/targetplatform2framework/attach2fw.py,sha256=GK_eI9Oq-kgBdfXm0AwgXkYgGKL0FEthqrTd0X_XWg0,2872
+model_compression_toolkit/target_platform_capabilities/target_platform/targetplatform2framework/attach2keras.py,sha256=mkTjg9JZEKMT_QHtlQPGUZvcuF0lofZUs1DU1h43JjM,6671
+model_compression_toolkit/target_platform_capabilities/target_platform/targetplatform2framework/attach2pytorch.py,sha256=cn2sP9fnHJ8qfR1AMTwW58mXLOcdT6M7xyE3TLRjnY0,5443
 model_compression_toolkit/target_platform_capabilities/target_platform/targetplatform2framework/attribute_filter.py,sha256=jfhszvuD2Fyy6W2KjlLzXBQKFzTqGAaDZeFVr4-ONQw,8776
 model_compression_toolkit/target_platform_capabilities/target_platform/targetplatform2framework/current_tpc.py,sha256=fIheShGOnxWYKqT8saHpBJqOU5RG_1Hp9qHry7IviIw,2115
 model_compression_toolkit/target_platform_capabilities/target_platform/targetplatform2framework/layer_filter_params.py,sha256=Cl6-mACpje2jM8RJkibbqE3hvTkFR3r26-lW021mIiA,4019
-model_compression_toolkit/target_platform_capabilities/target_platform/targetplatform2framework/operations_to_layers.py,sha256=YcHsObQ0RFT-ETwRSqhQil3xPwik0euh_Y5V9bpWD8E,6865
-model_compression_toolkit/target_platform_capabilities/target_platform/targetplatform2framework/target_platform_capabilities.py,sha256=jQ7t1wCOa-h_OCYOCmNVhEwftkbU1O4d7bnd4PgbuLI,9865
+model_compression_toolkit/target_platform_capabilities/target_platform/targetplatform2framework/operations_to_layers.py,sha256=Yg3sUzn4lpZn7bvNeDU4pO7_Jgr9cuqB66SqNMTh5_U,6867
+model_compression_toolkit/target_platform_capabilities/target_platform/targetplatform2framework/target_platform_capabilities.py,sha256=eRRCUqy0yXd3_xrufd7jjaU6hIIXphzcT8yWqvRr8l8,9994
 model_compression_toolkit/target_platform_capabilities/target_platform/targetplatform2framework/target_platform_capabilities_component.py,sha256=FvrYI0Qy7DCmDp2gyUYyCZq5pY84JgLtJqSIiVTJ8Ss,1030
 model_compression_toolkit/target_platform_capabilities/tpc_models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 model_compression_toolkit/target_platform_capabilities/tpc_models/get_target_platform_capabilities.py,sha256=CWind2Kd91lzBTRAh1A9sHuNw17xXhMb3gV436RpK8c,3033
@@ -450,49 +451,49 @@ model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/__i
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/target_platform_capabilities.py,sha256=yIWwvfTpiT0wRf7GwPgK9elKbGh46jxCrkcLVEjvesU,6081
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/latest/__init__.py,sha256=eVIRpx5O0JQI7TSdw5JAWtwrG3MQ8-7hYThQvB9da5c,1528
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v1/__init__.py,sha256=1mMOREEMoNHu_KTMGDp4crN61opKWX6aFn1DrDLvqcc,717
-model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v1/tp_model.py,sha256=W-DxFuYuD6cclQHmHmVdUpILHqTL7VfOKFFosoUtcJw,11317
+model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v1/tp_model.py,sha256=S2KHNfxzj6X_xFprLIYqYC3dcozHYTlsiW1LqVBnQkc,11198
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v1/tpc_keras.py,sha256=DiEVKde6bZiRDcoeTKzbrfjFIDVEeES0Q_Ms50NbW7Y,6568
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v1/tpc_pytorch.py,sha256=rQY-ApvLKo9LbN2uKO2NsdOgX49TKcED3o8mBxWAFKw,5594
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v1_lut/__init__.py,sha256=vFDyiMymNZSRCdTgAyWn4A-tZD3vzze_PTLBSF2OYe8,721
-model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v1_lut/tp_model.py,sha256=ArqqPg3cxCuRFQzz5lGMrZcLxpx_8n8_6cdFzKNTtDU,11072
+model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v1_lut/tp_model.py,sha256=gW_Yw7w2eQAb70Nqghv1btc9CTubMVpzjt7b2kxj-Hs,11101
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v1_lut/tpc_keras.py,sha256=I3NnmCBSB6KB8ECXJsfXw6FD-ONj39RXL-yB2-nE1xI,6577
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v1_lut/tpc_pytorch.py,sha256=R6ZDXT2bwAmdZfmXxIoCo7-_h7oGfyr6cZoZmBJdPa0,5713
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v1_pot/__init__.py,sha256=NUuczImqUxzdfflqSdqkeAN8aCU6Tuiu6U0Fnj9Tzmw,721
-model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v1_pot/tp_model.py,sha256=fwbZoIOrQhPXbcC8kAo3Gl_hmLTbr7a2BxiRvB1DxV8,10827
+model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v1_pot/tp_model.py,sha256=7fplCIkjNlPXgJQiYJlWeHBBOxDcjKjDMD23h0g_nt0,10887
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v1_pot/tpc_keras.py,sha256=ovHI4lvlcP_haolXmL8TvIpPi9tglhdUxRxNxuf6QPk,6581
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v1_pot/tpc_pytorch.py,sha256=PgNAmXZx7hg46KwR16laU7jr2U35rnHiTcR25RaLxd0,5732
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v2/__init__.py,sha256=vKWAoQ2KkhuptS5HZB50zHG6KY8wHpHTxPugw_nGCRo,717
-model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v2/tp_model.py,sha256=3qQ-RQPFjTcE8WM3rzMYe89SFoMtkbJ1f6IjkWUam3Q,11372
+model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v2/tp_model.py,sha256=et3hrgpF2hm5zqfvhSc2B4peIYmBddGbKVF2eQb7Q4U,11273
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v2/tpc_keras.py,sha256=i6oEt_3FAeccU9QkVCVxWZf2aX17IExAljR8y13k9P4,6663
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v2/tpc_pytorch.py,sha256=Iwi-D_0iC19Lo3yWduuaItezXFrRxRhowUY4jGOtwXk,5700
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v2_lut/__init__.py,sha256=wUk4Xsg7jpxOWYjq2K3WUwLcI185p_sVPK-ttG0ydhA,721
-model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v2_lut/tp_model.py,sha256=yANACBcyagUsJ3D8oustmUCVNrKcwFlBMAMTCrQtac4,11124
+model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v2_lut/tp_model.py,sha256=DCuslGtM4NT-NvPK8dpINa0t9gIjyP4325YaqtNukSk,11153
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v2_lut/tpc_keras.py,sha256=e3su6KmNsc2ziP3eEICp-tcnY9YmGPiLoMJ3TreqVx4,6671
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v2_lut/tpc_pytorch.py,sha256=9W-pjOhONqgym1t2vDRTo7x-JQiVlxQsAKAG6HdAww4,5707
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v3/__init__.py,sha256=gAeebYCKyIXH9-Qwze7FwvTihudzAHk_Qsg94fQbkjQ,717
-model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v3/tp_model.py,sha256=acSYyoS6R6DVHtyExcj93zHz5g3YKiZ71dF6f7N3ygQ,13184
+model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v3/tp_model.py,sha256=ngIP70u-_tA-XKXu4pTbXu2GDaWjnYwz08BCRdOeVlQ,13228
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v3/tpc_keras.py,sha256=vbBgQfEd5mLnJKGX2CO-KA0x87_qTmDH7HbbtLgCIfg,6881
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v3/tpc_pytorch.py,sha256=oDG_Ln0mPmt8p5eKrjGQlHLHCApErLHazny9bIfu3iI,5968
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v3_lut/__init__.py,sha256=C2kwyDE1-rtukkbNSoKRv9q8Nt2GOCaBbl0BdOr3goA,721
-model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v3_lut/tp_model.py,sha256=QdicH7CpS7-wUdp4XnYLL9yGmly_RKPifB4sNf1pUNc,12014
+model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v3_lut/tp_model.py,sha256=pPEXKAzLKp7AWhN2ysIJElAcY7FID1dVTLxDvz5xAOo,12050
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v3_lut/tpc_keras.py,sha256=hHK7MY6xfSCRnXQ6Qz0hbN_hM18f-gf3uZmxdl44khU,6679
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v3_lut/tpc_pytorch.py,sha256=GmS3CuSQPwLSgPdruXCSHN49_fRiRBn9PKA9CPmtqM8,5789
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v4/__init__.py,sha256=tHTUvsaerSfbe22pU0kIDauPpFD7Pq5EmZytVIDkHz4,717
-model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v4/tp_model.py,sha256=4Gjb_6pSgnCi7xqUYKdUsBBZeRNcrBbQ7wvuprHHIms,17498
+model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v4/tp_model.py,sha256=Ya0IZVDO6TAe_fBGV6Rg1BvENkzeCsbULaEjKDtzjck,17779
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v4/tpc_keras.py,sha256=9LToJzBBCXEZ5AOj2zzJMRr6S0uwlKKEg3stLK2u1fw,8341
 model_compression_toolkit/target_platform_capabilities/tpc_models/imx500_tpc/v4/tpc_pytorch.py,sha256=v1Fyp9YKWfdxF9tLfD0fAV41mqEH0S9z-jqr4QFH5CQ,7221
 model_compression_toolkit/target_platform_capabilities/tpc_models/qnnpack_tpc/__init__.py,sha256=cco4TmeIDIh32nj9ZZXVkws4dd9F2UDrmjKzTN8G0V0,697
 model_compression_toolkit/target_platform_capabilities/tpc_models/qnnpack_tpc/target_platform_capabilities.py,sha256=is00rNrDmmirYsyMtMkWz0DwOA92-x7hAJwpd6z1n2E,2806
 model_compression_toolkit/target_platform_capabilities/tpc_models/qnnpack_tpc/latest/__init__.py,sha256=CXC-HQolSDu7j8V-Xm-SWGCd74gXB3XnAkEhI_TVbIQ,1516
 model_compression_toolkit/target_platform_capabilities/tpc_models/qnnpack_tpc/v1/__init__.py,sha256=t4JKsPcor-7KSCKzIwuaBv0NLNwfhuewAQGlDl6iBeo,717
-model_compression_toolkit/target_platform_capabilities/tpc_models/qnnpack_tpc/v1/tp_model.py,sha256=IsvJrhen1cj5ErBiHnbpHMbBqDJA2oSlYQ53bJ6mUJw,8485
+model_compression_toolkit/target_platform_capabilities/tpc_models/qnnpack_tpc/v1/tp_model.py,sha256=yNwypIat2hVgwDKitw7enfPJYzvOThB2E76dOT0jglY,8531
 model_compression_toolkit/target_platform_capabilities/tpc_models/qnnpack_tpc/v1/tpc_keras.py,sha256=JKJy4k7TBCRZQ_cSWNhEdvyg5ylvIcpjU_6GALBOaFI,4461
 model_compression_toolkit/target_platform_capabilities/tpc_models/qnnpack_tpc/v1/tpc_pytorch.py,sha256=x5ooqCuKtW6ULenncjwSs_HTps8yUylOBKOzpgJ4yYI,3788
 model_compression_toolkit/target_platform_capabilities/tpc_models/tflite_tpc/__init__.py,sha256=cco4TmeIDIh32nj9ZZXVkws4dd9F2UDrmjKzTN8G0V0,697
 model_compression_toolkit/target_platform_capabilities/tpc_models/tflite_tpc/target_platform_capabilities.py,sha256=_tf41m40fbax27y5A5JoGHw4p5NY-Kb3c8oxSTnRD_E,2802
 model_compression_toolkit/target_platform_capabilities/tpc_models/tflite_tpc/latest/__init__.py,sha256=LIUUQn42YU7oD2YfnEgP0gfqm7Hq9e0fD_8418aKzKI,1511
 model_compression_toolkit/target_platform_capabilities/tpc_models/tflite_tpc/v1/__init__.py,sha256=t4JKsPcor-7KSCKzIwuaBv0NLNwfhuewAQGlDl6iBeo,717
-model_compression_toolkit/target_platform_capabilities/tpc_models/tflite_tpc/v1/tp_model.py,sha256=D1aMSpT4E-WJ4V3rPfjbl_FNZTuFI3-AGsQiL4-6ujc,10389
+model_compression_toolkit/target_platform_capabilities/tpc_models/tflite_tpc/v1/tp_model.py,sha256=U-I3eFBeRhc_BC16RyP_i_8e6ZP-X0klCa10k8QvddE,10383
 model_compression_toolkit/target_platform_capabilities/tpc_models/tflite_tpc/v1/tpc_keras.py,sha256=4vQG9uaV5bAte1VP8oMT5dwiDisW84F1B-de0BdBusY,6808
 model_compression_toolkit/target_platform_capabilities/tpc_models/tflite_tpc/v1/tpc_pytorch.py,sha256=uG27HAOrD-JMSDXaEycDJeFGqhF8J3ZqKI4CJCW6zA4,5934
 model_compression_toolkit/trainable_infrastructure/__init__.py,sha256=uewpvlPkH9mBFt8IxoAgIfz6iEcvWbOImm_fb6_BxD8,1543
@@ -559,8 +560,8 @@ model_compression_toolkit/xquant/pytorch/model_analyzer.py,sha256=b93o800yVB3Z-i
 model_compression_toolkit/xquant/pytorch/pytorch_report_utils.py,sha256=bOc-hFL3gdoSM1Th_S2N_-9JJSlPGpZCTx_QLJHS6lg,3388
 model_compression_toolkit/xquant/pytorch/similarity_functions.py,sha256=CERxq5K8rqaiE-DlwhZBTUd9x69dtYJlkHOPLB54vm8,2354
 model_compression_toolkit/xquant/pytorch/tensorboard_utils.py,sha256=mkoEktLFFHtEKzzFRn_jCnxjhJolK12TZ5AQeDHzUO8,9767
-mct_nightly-2.2.0.20241222.533.dist-info/LICENSE.md,sha256=aYSSIb-5AFPeITTvXm1UAoe0uYBiMmSS8flvXaaFUks,10174
-mct_nightly-2.2.0.20241222.533.dist-info/METADATA,sha256=c4zTn_I6l8SBlsOORCbquQqCEGDul2XcIKiT-DWBV8k,26453
-mct_nightly-2.2.0.20241222.533.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-mct_nightly-2.2.0.20241222.533.dist-info/top_level.txt,sha256=gsYA8juk0Z-ZmQRKULkb3JLGdOdz8jW_cMRjisn9ga4,26
-mct_nightly-2.2.0.20241222.533.dist-info/RECORD,,
+mct_nightly-2.2.0.20241224.532.dist-info/LICENSE.md,sha256=aYSSIb-5AFPeITTvXm1UAoe0uYBiMmSS8flvXaaFUks,10174
+mct_nightly-2.2.0.20241224.532.dist-info/METADATA,sha256=TevkRWHqm2UgHf34bwK7NWHCKt4tIUfdOvpVaA4-CIU,26453
+mct_nightly-2.2.0.20241224.532.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+mct_nightly-2.2.0.20241224.532.dist-info/top_level.txt,sha256=gsYA8juk0Z-ZmQRKULkb3JLGdOdz8jW_cMRjisn9ga4,26
+mct_nightly-2.2.0.20241224.532.dist-info/RECORD,,

model_compression_toolkit/__init__.py

@@ -27,4 +27,4 @@ from model_compression_toolkit import data_generation
 from model_compression_toolkit import pruning
 from model_compression_toolkit.trainable_infrastructure.keras.load_model import keras_load_quantized_model
 
-__version__ = "2.2.0.20241222.000533"
+__version__ = "2.2.0.20241224.000532"

model_compression_toolkit/core/common/graph/base_graph.py

@@ -105,7 +105,7 @@ class Graph(nx.MultiDiGraph, GraphSearches):
                     Logger.critical(f'MCT does not support optimizing Keras custom layers. Found a layer of type {n.type}. '
                                     ' Please add the custom layer to Target Platform Capabilities (TPC), or file a feature '
                                     'request or an issue if you believe this should be supported.')  # pragma: no cover
-                if any([qc.default_weight_attr_config.enable_weights_quantization for qc in n.get_qco(tpc).quantization_config_list]):
+                if any([qc.default_weight_attr_config.enable_weights_quantization for qc in n.get_qco(tpc).quantization_configurations]):
                     Logger.critical(f'Layer identified: {n.type}. MCT does not support weight quantization for Keras custom layers.')  # pragma: no cover
 
         self.tpc = tpc

model_compression_toolkit/core/common/graph/base_node.py

@@ -582,12 +582,12 @@ class BaseNode:
         """
         # Filter quantization config options that don't match the graph.
         _base_config = node_qc_options.base_config
-        _node_qc_options = node_qc_options.quantization_config_list
+        _node_qc_options = node_qc_options.quantization_configurations
         if len(next_nodes):
             next_nodes_qc_options = [_node.get_qco(tpc) for _node in next_nodes]
             next_nodes_supported_input_bitwidth = min([max_input_activation_n_bits(op_cfg)
                                                        for qc_opts in next_nodes_qc_options
-                                                       for op_cfg in qc_opts.quantization_config_list])
+                                                       for op_cfg in qc_opts.quantization_configurations])
 
             # Filter node's QC options that match next nodes input bit-width.
             _node_qc_options = [_option for _option in _node_qc_options
@@ -599,7 +599,7 @@ class BaseNode:
             if any([node_qc_options.base_config.activation_n_bits > max_input_activation_n_bits(qc_opt.base_config)
                     for qc_opt in next_nodes_qc_options]):
                 # base_config activation bits doesn't match next node supported input bit-width -> replace with
-                # a qco from quantization_config_list with maximum activation bit-width.
+                # a qco from quantization_configurations with maximum activation bit-width.
                 if len(_node_qc_options) > 0:
                     output_act_bitwidth = {qco.activation_n_bits: i for i, qco in enumerate(_node_qc_options)}
                     _base_config = _node_qc_options[output_act_bitwidth[max(output_act_bitwidth)]]

model_compression_toolkit/core/common/quantization/set_node_quantization_config.py

@@ -101,7 +101,7 @@ def filter_node_qco_by_graph(node: BaseNode,
     """
     # Filter quantization config options that don't match the graph.
     _base_config = node_qc_options.base_config
-    _node_qc_options = node_qc_options.quantization_config_list
+    _node_qc_options = node_qc_options.quantization_configurations
 
     # Build next_nodes list by appending to the node's next nodes list all nodes that are quantization preserving.
     _next_nodes = graph.get_next_nodes(node)
@@ -109,7 +109,7 @@ def filter_node_qco_by_graph(node: BaseNode,
     while len(_next_nodes):
         n = _next_nodes.pop(0)
         qco = n.get_qco(tpc)
-        qp = [qc.quantization_preserving for qc in qco.quantization_config_list]
+        qp = [qc.quantization_preserving for qc in qco.quantization_configurations]
         if not all(qp) and any(qp):
             Logger.error(f'Attribute "quantization_preserving" should be the same for all QuantizaionConfigOptions in {n}.')
         if qp[0]:
@@ -120,7 +120,7 @@ def filter_node_qco_by_graph(node: BaseNode,
         next_nodes_qc_options = [_node.get_qco(tpc) for _node in next_nodes]
         next_nodes_supported_input_bitwidth = min([max_input_activation_n_bits(op_cfg)
                                                    for qc_opts in next_nodes_qc_options
-                                                   for op_cfg in qc_opts.quantization_config_list])
+                                                   for op_cfg in qc_opts.quantization_configurations])
 
         # Filter node's QC options that match next nodes input bit-width.
         _node_qc_options = [_option for _option in _node_qc_options
@@ -132,7 +132,7 @@ def filter_node_qco_by_graph(node: BaseNode,
         if any([node_qc_options.base_config.activation_n_bits > max_input_activation_n_bits(qc_opt.base_config)
                 for qc_opt in next_nodes_qc_options]):
             # base_config activation bits doesn't match next node supported input bit-width -> replace with
-            # a qco from quantization_config_list with maximum activation bit-width.
+            # a qco from quantization_configurations with maximum activation bit-width.
             if len(_node_qc_options) > 0:
                 output_act_bitwidth = {qco.activation_n_bits: i for i, qco in enumerate(_node_qc_options)}
                 _base_config = _node_qc_options[output_act_bitwidth[max(output_act_bitwidth)]]

model_compression_toolkit/core/common/substitutions/shift_negative_activation.py

@@ -392,7 +392,7 @@ def shift_negative_function(graph: Graph,
                     bypass_candidate_qc.activation_quantization_cfg.activation_quantization_params[SIGNED] = False
                     graph.shift_stats_collector(bypass_node, np.array(shift_value))
 
-    add_node_qco = add_node.get_qco(graph.tpc).quantization_config_list
+    add_node_qco = add_node.get_qco(graph.tpc).quantization_configurations
     for op_qc_idx, candidate_qc in enumerate(add_node.candidates_quantization_cfg):
         for attr in add_node.get_node_weights_attributes():
             candidate_qc.weights_quantization_cfg.get_attr_config(attr).enable_weights_quantization = False
@@ -535,7 +535,7 @@ def apply_shift_negative_correction(graph: Graph,
         # Skip substitution if QuantizationMethod is uniform.
         node_qco = n.get_qco(graph.tpc)
         if any([op_qc.activation_quantization_method is QuantizationMethod.UNIFORM
-                for op_qc in node_qco.quantization_config_list]):
+                for op_qc in node_qco.quantization_configurations]):
             continue
 
         if snc_node_types.apply(n):

model_compression_toolkit/target_platform_capabilities/schema/mct_current_schema.py

@@ -1,5 +1,6 @@
 import model_compression_toolkit.target_platform_capabilities.schema.v1 as schema
 
+OperatorSetNames = schema.OperatorSetNames
 Signedness = schema.Signedness
 AttributeQuantizationConfig = schema.AttributeQuantizationConfig
 OpQuantizationConfig = schema.OpQuantizationConfig

model_compression_toolkit/target_platform_capabilities/schema/schema_functions.py

@@ -64,10 +64,10 @@ def get_default_op_quantization_config(tp_model: TargetPlatformModel) -> OpQuant
     Raises:
         AssertionError: If the default quantization configuration list contains more than one configuration option.
     """
-    assert len(tp_model.default_qco.quantization_config_list) == 1, \
+    assert len(tp_model.default_qco.quantization_configurations) == 1, \
         f"Default quantization configuration options must contain only one option, " \
-        f"but found {len(tp_model.default_qco.quantization_config_list)} configurations." # pragma: no cover
-    return tp_model.default_qco.quantization_config_list[0]
+        f"but found {len(tp_model.default_qco.quantization_configurations)} configurations." # pragma: no cover
+    return tp_model.default_qco.quantization_configurations[0]
 
 
 def is_opset_in_model(tp_model: TargetPlatformModel, opset_name: str) -> bool:
@@ -82,8 +82,7 @@ def is_opset_in_model(tp_model: TargetPlatformModel, opset_name: str) -> bool:
         bool: True if an OperatorsSet with the given name exists in the target platform model,
               otherwise False.
     """
-    return opset_name in [x.name for x in tp_model.operator_set]
-
+    return tp_model.operator_set is not None and opset_name in [x.name for x in tp_model.operator_set]
 
 def get_opset_by_name(tp_model: TargetPlatformModel, opset_name: str) -> Optional[OperatorsSetBase]:
     """