Comments (2)
etale-cohomology
commented on June 3, 2024
Here's the output of train.py
I0102 23:06:55.323895 140562995341120 main.py:164] {'name': 'efficientdet-d3', 'act_type': 'swish', 'image_size': (896, 896), 'target_size': None, 'input_rand_hflip': True, 'jitter_min': 0.1, 'jitter_max': 2.0, 'autoaugment_policy': None, 'grid_mask': False, 'sample_image': None, 'map_freq': 5, 'num_classes': 586, 'seg_num_classes': 3, 'heads': ['object_detection'], 'skip_crowd_during_training': True, 'label_map': {1: 'Abel_NOT_Rec', 2: 'Abel_WHI_SinSco_12Yo_BUT_700ml_00_00', 3: 'Abel_WHI_SinSco_12Yo_BUT_700ml_01_00', 4: 'Abel_WHI_SinSco_12Yo_KAR_2SZK_700ml_00_00', 5: 'Abel_WHI_SinSco_12Yo_KAR_2SZK_700ml_01_00', 6: 'Abel_WHI_SinSco_12Yo_TUB_700ml_00_00', 7: 'Abel_WHI_SinSco_12Yo_TUB_700ml_01_00', 8: 'Abel_WHI_SinSco_14Yo_BUT_700ml_00_00', 9: 'Abel_WHI_SinSco_14Yo_TUB_700ml_00_00', 10: 'Abel_WHI_SinSco_16Yo_BUT_700ml_00_00', 11: 'Abel_WHI_SinSco_16Yo_BUT_700ml_01_00', 12: 'Abel_WHI_SinSco_16Yo_TUB_700ml_00_00', 13: 'Abel_WHI_SinSco_16Yo_TUB_700ml_01_00', 14: 'Abel_WHI_SinSco_18Yo_BUT_500ml_00_00', 15: 'Abel_WHI_SinSco_18Yo_BUT_500ml_01_00', 16: 'Abel_WHI_SinSco_18Yo_BUT_700ml_00_00', 17: 'Abel_WHI_SinSco_18Yo_BUT_700ml_01_00', 18: 'Abel_WHI_SinSco_18Yo_TUB_500ml_00_00', 19: 'Abel_WHI_SinSco_18Yo_TUB_500ml_01_00', 20: 'Abel_WHI_SinSco_18Yo_TUB_700ml_00_00', 21: 'Abel_WHI_SinSco_18Yo_TUB_700ml_01_00', 22: 'AbelAbuna_WHI_SinSco_BUT_700ml_00_00', 23: 'AbelAbuna_WHI_SinSco_BUT_700ml_01_00', 24: 'AbelAbuna_WHI_SinSco_TUB_700ml_00_00', 25: 'AbelAbuna_WHI_SinSco_TUB_700ml_01_00', 26: 'AbelCasgAnn_WHI_SinSco_BUT_700ml_00_00', 27: 'AbelCasgAnn_WHI_SinSco_BUT_700ml_01_00', 28: 'AbelCasgAnn_WHI_SinSco_TUB_700ml_00_00', 29: 'AbelCasgAnn_WHI_SinSco_TUB_700ml_01_00', 30: 'Absu_NOT_Rec', 31: 'Absu_WOD_Czy_BUT_1000ml_00_00', 32: 'Absu_WOD_Czy_BUT_1000ml_01_00', 33: 'Absu_WOD_Czy_BUT_4500ml_00_00', 34: 'Absu_WOD_Czy_BUT_500ml_00_00', 35: 'Absu_WOD_Czy_BUT_500ml_01_00', 36: 'Absu_WOD_Czy_BUT_50ml_00_00', 37: 'Absu_WOD_Czy_BUT_700ml_00_00', 38: 'Absu_WOD_Czy_BUT_700ml_01_00', 39: 'Absu_WOD_Czy_KAR_2KIE_700ml_00_00', 40: 'AbsuElyx_WOD_Czy_BUT_1000ml_00_00', 41: 'AbsuElyx_WOD_Czy_BUT_1750ml_00_00', 42: 'AbsuElyx_WOD_Czy_BUT_700ml_00_00', 43: 'AbsuElyx_WOD_Czy_BUT_700ml_01_00', 44: 'AbsuExtra_WOD_Sma_BUT_700ml_00_00', 45: 'AbsuGrape_WOD_Sma_BUT_700ml_00_00', 46: 'AbsuKuran_WOD_Sma_BUT_700ml_00_00', 47: 'AbsuKuran_WOD_Sma_BUT_700ml_01_00', 48: 'AbsuLime_WOD_Sma_BUT_700ml_00_00', 49: 'AbsuLime_WOD_Sma_BUT_700ml_01_00', 50: 'AbsuPears_WOD_Sma_BUT_700ml_00_00', 51: 'Ara_BRA_3Yo_BUT_500ml_00_00', 52: 'Ara_BRA_3Yo_BUT_500ml_01_00', 53: 'Ara_BRA_3Yo_BUT_700ml_00_00', 54: 'Ara_BRA_3Yo_BUT_700ml_01_00', 55: 'Ara_BRA_3Yo_KAR_500ml_00_00', 56: 'Ara_BRA_3Yo_KAR_500ml_01_00', 57: 'Ara_BRA_3Yo_KAR_700ml_00_00', 58: 'Ara_BRA_3Yo_KAR_700ml_01_00', 59: 'Ara_BRA_5Yo_BUT_500ml_01_00', 60: 'Ara_BRA_5Yo_BUT_700ml_00_00', 61: 'Ara_BRA_5Yo_BUT_700ml_01_00', 62: 'Ara_BRA_5Yo_KAR_500ml_00_00', 63: 'Ara_BRA_5Yo_KAR_500ml_01_00', 64: 'Ara_BRA_5Yo_KAR_700ml_00_00', 65: 'Ara_BRA_5Yo_KAR_700ml_01_00', 66: 'Ara_NOT_Rec', 67: 'AraAkhta_BRA_10Yo_BUT_700ml_00_00', 68: 'AraAkhta_BRA_10Yo_BUT_700ml_01_00', 69: 'AraAkhta_BRA_10Yo_KAR_700ml_00_00', 70: 'AraAkhta_BRA_10Yo_KAR_700ml_01_00', 71: 'AraAni_BRA_6Yo_BUT_700ml_00_00', 72: 'AraAni_BRA_6Yo_KAR_700ml_00_00', 73: 'AraDvin_BRA_BUT_700ml_00_00', 74: 'AraDvin_BRA_BUT_700ml_01_00', 75: 'AraDvin_BRA_KAR_700ml_00_00', 76: 'AraDvin_BRA_KAR_700ml_01_00', 77: 'AraNairi_BRA_20Yo_BUT_700ml_00_00', 78: 'AraNairi_BRA_20Yo_BUT_700ml_01_00', 79: 'AraNairi_BRA_20Yo_KAR_700ml_00_00', 80: 'AraNairi_BRA_20Yo_KAR_700ml_01_00', 81: 'AraOtbor_BRA_7Yo_BUT_700ml_00_00', 82: 'AraOtbor_BRA_7Yo_KAR_700ml_00_00', 83: 'AraVaspu_BRA_15Yo_BUT_700ml_00_00', 84: 'AraVaspu_BRA_15Yo_BUT_700ml_01_00', 85: 'AraVaspu_BRA_15Yo_KAR_700ml_00_00', 86: 'AraVaspu_BRA_15Yo_KAR_700ml_01_00', 87: 'Ball_NOT_Rec', 88: 'Ball_WHI_BleSco_12Yo_BUT_700ml_00_00', 89: 'Ball_WHI_BleSco_12Yo_BUT_700ml_01_00', 90: 'Ball_WHI_BleSco_12Yo_KAR_2SZK_700ml_00_00', 91: 'Ball_WHI_BleSco_12Yo_KAR_2SZK_700ml_01_00', 92: 'Ball_WHI_BleSco_12Yo_KAR_2SZK_700ml_03_00', 93: 'Ball_WHI_BleSco_12Yo_KAR_700ml_00_00', 94: 'Ball_WHI_BleSco_12Yo_KAR_700ml_02_00', 95: 'Ball_WHI_BleSco_12Yo_KAR_PIE_700ml_00_00', 96: 'Ball_WHI_BleSco_12Yo_KAR_PIE_700ml_01_00', 97: 'Ball_WHI_BleSco_12Yo_KAR_PIE_700ml_02_00', 98: 'Ball_WHI_BleSco_17Yo_BUT_700ml_00_00', 99: 'Ball_WHI_BleSco_17Yo_BUT_700ml_01_00', 100: 'Ball_WHI_BleSco_17Yo_KAR_700ml_00_00', 101: 'Ball_WHI_BleSco_17Yo_KAR_700ml_01_00', 102: 'Ball_WHI_BleSco_21Yo_BUT_700ml_00_00', 103: 'Ball_WHI_BleSco_21Yo_BUT_700ml_01_00', 104: 'Ball_WHI_BleSco_21Yo_KAR_700ml_00_00', 105: 'Ball_WHI_BleSco_21Yo_KAR_700ml_01_00', 106: 'Ball_WHI_BleSco_21Yo_KAR_700ml_02_00', 107: 'Ball_WHI_BleSco_30Yo_BUT_700ml_00_00', 108: 'Ball_WHI_BleSco_30Yo_BUT_700ml_01_00', 109: 'Ball_WHI_BleSco_30Yo_KAR_700ml_00_00', 110: 'Ball_WHI_BleSco_30Yo_KAR_700ml_01_00', 111: 'Ball_WHI_BleSco_30Yo_KAR_700ml_02_00', 112: 'Ball_WHI_BleSco_40Yo_BUT_700ml_00_00', 113: 'Ball_WHI_BleSco_40Yo_SKR_700ml_00_00', 114: 'Ball_WHI_BleSco_7Yo_BUT_700ml_00_00', 115: 'BallBrasi_WHI_BleSco_BUT_700ml_00_00', 116: 'BallFines_WHI_BleSco_BUT_1000ml_00_00', 117: 'BallFines_WHI_BleSco_BUT_1500ml_00_00', 118: 'BallFines_WHI_BleSco_BUT_200ml_00_00', 119: 'BallFines_WHI_BleSco_BUT_4500ml_00_00', 120: 'BallFines_WHI_BleSco_BUT_500ml_00_00', 121: 'BallFines_WHI_BleSco_BUT_50ml_00_00', 122: 'BallFines_WHI_BleSco_BUT_700ml_00_00', 123: 'BallFines_WHI_BleSco_BUT_700ml_01_00', 124: 'BallFines_WHI_BleSco_BUT_700ml_02_00', 125: 'BallFines_WHI_BleSco_KAR_SZK_700ml_01_00', 126: 'BallFines_WHI_BleSco_KAR_SZK_700ml_02_00', 127: 'BallFines_WHI_BleSco_KAR_SZKMIN_700ml_00_00', 128: 'BallGlenb_WHI_SinSco_15Yo_BUT_700ml_00_00', 129: 'BallGlenb_WHI_SinSco_15Yo_TUB_700ml_00_00', 130: 'BallGlent_WHI_SinSco_15Yo_BUT_700ml_00_00', 131: 'BallGlent_WHI_SinSco_15Yo_TUB_700ml_00_00', 132: 'BallMilto_WHI_SinSco_15Yo_BUT_700ml_00_00', 133: 'BallMilto_WHI_SinSco_15Yo_TUB_700ml_00_00', 134: 'BallPassi_WHI_BleSco_BUT_700ml_00_00', 135: 'BallWild_WHI_BleSco_BUT_700ml_00_00', 136: 'Bec_LIK_BUT_500ml_00_00', 137: 'Bec_LIK_BUT_500ml_01_00', 138: 'Bec_LIK_BUT_700ml_00_00', 139: 'Bec_LIK_BUT_700ml_01_00', 140: 'Bec_NOT_Rec', 141: 'Bee24_GIN_BUT_700ml_00_00', 142: 'Bee24_GIN_BUT_700ml_01_00', 143: 'Bee_GIN_BUT_700ml_00_00', 144: 'Bee_GIN_BUT_700ml_01_00', 145: 'Bee_GIN_BUT_700ml_02_00', 146: 'Bee_GIN_BUT_700ml_03_00', 147: 'Bee_NOT_Rec', 148: 'BeeBloodOra_GIN_BUT_700ml_00_00', 149: 'BeePink_GIN_BUT_700ml_00_00', 150: 'BeePink_GIN_BUT_700ml_01_00', 151: 'BeePink_GIN_BUT_700ml_02_00', 152: 'BraOfGle_NOT_Rec', 153: 'BraOfGle_WHI_SinSco_25Yo_BUT_700ml_00_00', 154: 'BraOfGle_WHI_SinSco_25Yo_KAR_700ml_00_00', 155: 'Bum_NOT_Rec', 156: 'BumCream_RUM_BUT_700ml_00_00', 157: 'BumOrigi_RUM_BUT_350ml_00_00', 158: 'BumOrigi_RUM_BUT_700ml_00_00', 159: 'BumXo_RUM_BUT_700ml_00_00', 160: 'CamVie_NOT_Rec', 161: 'CamVie_WIN_PolSloBia_BUT_750ml_00_00', 162: 'CamVie_WIN_PolSloBia_BUT_750ml_01_00', 163: 'CamVie_WIN_PolSloBia_BUT_750ml_02_00', 164: 'CamVieGranRes_WIN_WytCze_BUT_750ml_00_00', 165: 'CamVieReser_WIN_WytCze_BUT_750ml_00_00', 166: 'CamVieTempr_WIN_WytCze_BUT_750ml_00_00', 167: 'CanSpeOld_NOT_Rec', 168: 'CanSpeOld_WHI_BleKan_BUT_700ml_00_00', 169: 'ChiReg_NOT_Rec', 170: 'ChiReg_WHI_BleSco_12Yo_BUT_1000ml_00_00', 171: 'ChiReg_WHI_BleSco_12Yo_BUT_1000ml_01_00', 172: 'ChiReg_WHI_BleSco_12Yo_BUT_1000ml_02_00', 173: 'ChiReg_WHI_BleSco_12Yo_BUT_1500ml_00_00', 174: 'ChiReg_WHI_BleSco_12Yo_BUT_1500ml_01_00', 175: 'ChiReg_WHI_BleSco_12Yo_BUT_200ml_00_00', 176: 'ChiReg_WHI_BleSco_12Yo_BUT_200ml_01_00', 177: 'ChiReg_WHI_BleSco_12Yo_BUT_4500ml_00_00', 178: 'ChiReg_WHI_BleSco_12Yo_BUT_4500ml_01_00', 179: 'ChiReg_WHI_BleSco_12Yo_BUT_500ml_00_00', 180: 'ChiReg_WHI_BleSco_12Yo_BUT_500ml_01_00', 181: 'ChiReg_WHI_BleSco_12Yo_BUT_500ml_02_00', 182: 'ChiReg_WHI_BleSco_12Yo_BUT_50ml_00_00', 183: 'ChiReg_WHI_BleSco_12Yo_BUT_50ml_01_00', 184: 'ChiReg_WHI_BleSco_12Yo_BUT_700ml_00_00', 185: 'ChiReg_WHI_BleSco_12Yo_BUT_700ml_02_00', 186: 'ChiReg_WHI_BleSco_12Yo_KAR_1000ml_15_00', 187: 'ChiReg_WHI_BleSco_12Yo_KAR_1000ml_16_00', 188: 'ChiReg_WHI_BleSco_12Yo_KAR_2SZK_700ml_01_00', 189: 'ChiReg_WHI_BleSco_12Yo_KAR_2SZK_700ml_03_00', 190: 'ChiReg_WHI_BleSco_12Yo_KAR_2SZK_700ml_05_00', 191: 'ChiReg_WHI_BleSco_12Yo_KAR_2SZK_700ml_08_00', 192: 'ChiReg_WHI_BleSco_12Yo_KAR_700ml_00_00', 193: 'ChiReg_WHI_BleSco_12Yo_KAR_700ml_01_00', 194: 'ChiReg_WHI_BleSco_12Yo_KAR_700ml_07_00', 195: 'ChiReg_WHI_BleSco_12Yo_KAR_700ml_08_00', 196: 'ChiReg_WHI_BleSco_12Yo_KAR_700ml_15_00', 197: 'ChiReg_WHI_BleSco_18Yo_BUT_700ml_00_00', 198: 'ChiReg_WHI_BleSco_18Yo_KAR_2SZK_700ml_01_00', 199: 'ChiReg_WHI_BleSco_18Yo_KAR_700ml_01_00', 200: 'ChiReg_WHI_BleSco_18Yo_KAR_700ml_02_00', 201: 'ChiReg_WHI_BleSco_18Yo_KAR_700ml_03_00', 202: 'ChiReg_WHI_BleSco_25Yo_BUT_700ml_00_00', 203: 'ChiReg_WHI_BleSco_25Yo_KAR_700ml_00_00', 204: 'ChiReg_WHI_BleSco_25Yo_KAR_700ml_01_00', 205: 'ChiRegExtraAmeRyeCas_WHI_BleSco_13Yo_BUT_700ml_00_00', 206: 'ChiRegExtraAmeRyeCas_WHI_BleSco_13Yo_BUT_700ml_02_00', 207: 'ChiRegExtraAmeRyeCas_WHI_BleSco_13Yo_KAR_700ml_00_00', 208: 'ChiRegExtraAmeRyeCas_WHI_BleSco_13Yo_KAR_700ml_02_00', 209: 'ChiRegExtraShe_WHI_BleSco_13Yo_BUT_700ml_00_00', 210: 'ChiRegExtraShe_WHI_BleSco_13Yo_BUT_700ml_01_00', 211: 'ChiRegExtraShe_WHI_BleSco_13Yo_KAR_700ml_00_00', 212: 'ChiRegExtraShe_WHI_BleSco_13Yo_KAR_700ml_02_00', 213: 'ChiRegMizun_WHI_BleSco_BUT_700ml_00_00', 214: 'ChiRegMizun_WHI_BleSco_KAR_700ml_00_00', 215: 'ChiRegUltis_WHI_BleSco_BUT_700ml_00_00', 216: 'ChiRegUltis_WHI_BleSco_KAR_700ml_00_00', 217: 'ChiRegXv_WHI_BleSco_15Yo_BUT_700ml_00_00', 218: 'ChiRegXv_WHI_BleSco_15Yo_BUT_700ml_01_00', 219: 'ChiRegXv_WHI_BleSco_15Yo_KAR_700ml_00_00', 220: 'ChiRegXv_WHI_BleSco_15Yo_KAR_700ml_01_00', 221: 'ChiRegXv_WHI_BleSco_15Yo_KAR_700ml_02_00', 222: 'DeKuy_NOT_Rec', 223: 'DeKuyAmare_LIK_BUT_700ml_01_00', 224: 'DeKuyBlueCur_LIK_BUT_500ml_00_00', 225: 'DeKuyBlueCur_LIK_BUT_700ml_00_00', 226: 'DeKuyCremeDeCas_LIK_BUT_700ml_00_00', 227: 'DeKuyTriplSec_LIK_BUT_500ml_00_00', 228: 'DeKuyTriplSec_LIK_BUT_700ml_00_00', 229: 'DeKuyTriplSec_LIK_BUT_700ml_01_00', 230: 'FouRos_NOT_Rec', 231: 'FouRosSinglBar_WHI_Bou_BUT_700ml_00_00', 232: 'FouRosSmallBat_WHI_Bou_BUT_700ml_00_00', 233: 'GleKei_NOT_Rec', 234: 'GleKei_WHI_SinSco_21Yo_BUT_700ml_00_00', 235: 'GleKei_WHI_SinSco_21Yo_KAR_700ml_00_00', 236: 'Gol_NOT_Rec', 237: 'Gol_RUM_BUT_200ml_00_00', 238: 'Gol_RUM_BUT_200ml_01_00', 239: 'Gol_RUM_BUT_500ml_00_00', 240: 'Gol_RUM_BUT_500ml_01_00', 241: 'Hav_NOT_Rec', 242: 'HavClub_RUM_3Yo_BUT_700ml_00_00', 243: 'HavClub_RUM_3Yo_BUT_700ml_01_00', 244: 'HavClub_RUM_7Yo_BUT_700ml_00_00', 245: 'HavClubEsp_RUM_BUT_700ml_00_00', 246: 'HavClubEsp_RUM_BUT_700ml_01_00', 247: 'HavClubSelDeMae_RUM_BUT_700ml_01_00', 248: 'HavClubSelDeMae_RUM_BUT_700ml_02_00', 249: 'HavClubSelDeMae_RUM_KAR_700ml_00_00', 250: 'HavClubSelDeMae_RUM_TUB_700ml_00_00', 251: 'HavClubSelDeMae_RUM_TUB_700ml_01_00', 252: 'JacCre_NOT_Rec', 253: 'JacCreChard_WIN_WytBia_BUT_750ml_00_00', 254: 'JacCreChard_WIN_WytBia_BUT_750ml_01_00', 255: 'JacCreChardPinNoi_WIN_MusWytBia_BUT_750ml_00_00', 256: 'JacCreChardPinNoi_WIN_MusWytBia_BUT_750ml_01_00', 257: 'JacCreChardPinNoi_WIN_MusWytBia_BUT_750ml_02_00', 258: 'JacCreChardRes_WIN_WytBia_BUT_750ml_00_00', 259: 'JacCreChardRes_WIN_WytBia_BUT_750ml_01_00', 260: 'JacCreDoublBarCabSav_WIN_WytCze_BUT_750ml_00_00', 261: 'JacCreDoublBarCabSav_WIN_WytCze_BUT_750ml_01_00', 262: 'JacCreDoublBarShi_WIN_WytCze_BUT_750ml_00_00', 263: 'JacCreDoublBarShi_WIN_WytCze_BUT_750ml_01_00', 264: 'JacCreMerloShi_WIN_PolSloCze_BUT_750ml_00_00', 265: 'JacCreMerloShi_WIN_PolSloCze_BUT_750ml_01_00', 266: 'JacCreMerloShi_WIN_PolSloCze_BUT_750ml_02_00', 267: 'JacCreMoscaRos_WIN_SloRoz_BUT_750ml_00_00', 268: 'JacCreMoscaRos_WIN_SloRoz_BUT_750ml_01_00', 269: 'JacCreMoscaRos_WIN_SloRoz_BUT_750ml_02_00', 270: 'JacCreRiesl_WIN_WytBia_BUT_750ml_00_00', 271: 'JacCreSauviBla_WIN_PolWytBia_BUT_750ml_00_00', 272: 'JacCreSauviBla_WIN_PolWytBia_BUT_750ml_01_00', 273: 'JacCreSauviBla_WIN_PolWytBia_BUT_750ml_02_00', 274: 'JacCreSauviMosTwiPic_WIN_MusWytBia_BUT_750ml_00_00', 275: 'JacCreShiraCab_WIN_WytCze_BUT_750ml_00_00', 276: 'JacCreShiraCab_WIN_WytCze_BUT_750ml_01_00', 277: 'JacCreShiraCab_WIN_WytCze_BUT_750ml_02_00', 278: 'JacCreShiraGre_WIN_PolWytCze_BUT_750ml_00_00', 279: 'JacCreShiraGre_WIN_PolWytCze_BUT_750ml_01_00', 280: 'JacCreShiraGre_WIN_PolWytCze_BUT_750ml_02_00', 281: 'JacCreShiraRes_WIN_WytCze_BUT_750ml_00_00', 282: 'JacCreShiraRes_WIN_WytCze_BUT_750ml_01_00', 283: 'JacCreShiraRos_WIN_PolWytRoz_BUT_750ml_00_00', 284: 'JacCreSparkMos_WIN_MusSloBia_BUT_750ml_01_00', 285: 'JacCreStillMos_WIN_SloBia_BUT_750ml_00_00', 286: 'JacCreStillMos_WIN_SloBia_BUT_750ml_01_00', 287: 'JacCreStillMos_WIN_SloBia_BUT_750ml_02_00', 288: 'JacCreStillMos_WIN_SloBia_BUT_750ml_03_00', 289: 'JacCreStillMos_WIN_SloBia_BUT_750ml_04_00', 290: 'Jam_NOT_Rec', 291: 'Jam_WHI_BleIri_BUT_1000ml_00_00', 292: 'Jam_WHI_BleIri_BUT_200ml_00_00', 293: 'Jam_WHI_BleIri_BUT_200ml_01_00', 294: 'Jam_WHI_BleIri_BUT_500ml_00_00', 295: 'Jam_WHI_BleIri_BUT_700ml_00_00', 296: 'Jam_WHI_BleIri_BUT_700ml_01_00', 297: 'Jam_WHI_BleIri_BUT_STO_4500ml_00_00', 298: 'Jam_WHI_BleIri_KAR_2SZK_700ml_00_00', 299: 'Jam_WHI_BleIri_KAR_MIN_700ml_00_00', 300: 'Jam_WHI_BleIri_KAR_MIN_700ml_01_00', 301: 'Jam_WHI_BleIri_KAR_STO_4500ml_00_00', 302: 'JamBlackBar_WHI_BleIri_BUT_700ml_00_00', 303: 'JamBlackBar_WHI_BleIri_BUT_700ml_01_00', 304: 'JamBlackBar_WHI_BleIri_KAR_700ml_00_00', 305: 'JamBlackBar_WHI_BleIri_KAR_700ml_01_00', 306: 'JamBlendDog_WHI_BleIri_BUT_700ml_00_00', 307: 'JamCaskmIpa_WHI_BleIri_BUT_700ml_00_00', 308: 'JamCaskmIpa_WHI_BleIri_BUT_700ml_01_00', 309: 'JamCaskmIpa_WHI_BleIri_BUT_700ml_02_00', 310: 'JamCaskmIpa_WHI_BleIri_KAR_700ml_00_00', 311: 'JamCaskmIpa_WHI_BleIri_KAR_700ml_01_00', 312: 'JamCaskmSto_WHI_BleIri_BUT_700ml_00_00', 313: 'JamCaskmSto_WHI_BleIri_BUT_700ml_01_00', 314: 'JamCaskmSto_WHI_BleIri_BUT_700ml_02_00', 315: 'JamCaskmSto_WHI_BleIri_BUT_700ml_03_00', 316: 'JamCaskmSto_WHI_BleIri_KAR_700ml_00_00', 317: 'JamCaskmSto_WHI_BleIri_KAR_700ml_01_00', 318: 'JamCoopeCro_WHI_BleIri_BUT_700ml_00_00', 319: 'JamCrest_WHI_BleIri_BUT_700ml_00_00', 320: 'JamCrest_WHI_BleIri_BUT_700ml_01_00', 321: 'JamCrest_WHI_BleIri_KAR_700ml_00_00', 322: 'JamCrest_WHI_BleIri_KAR_700ml_01_00', 323: 'JamDistiSaf_WHI_BleIri_BUT_700ml_00_00', 324: 'JamOrang_WHI_BleIri_BUT_700ml_00_00', 325: 'Kah_LIK_BUT_700ml_00_00', 326: 'Kah_LIK_BUT_700ml_01_00', 327: 'Kah_LIK_BUT_700ml_02_00', 328: 'Kah_NOT_Rec', 329: 'Lil_NOT_Rec', 330: 'LilBlanc_LIK_BUT_750ml_01_00', 331: 'LilBlanc_LIK_BUT_750ml_02_00', 332: 'LilRose_LIK_BUT_750ml_00_00', 333: 'LilRose_LIK_BUT_750ml_01_00', 334: 'Lon_NOT_Rec', 335: 'Lon_WHI_SinSco_16Yo_KAR_700ml_00_00', 336: 'LonTheDisCho_WHI_SinSco_BUT_700ml_00_00', 337: 'LonTheDisCho_WHI_SinSco_KAR_700ml_00_00', 338: 'Luk_NOT_Rec', 339: 'Luk_WOD_Czy_BUT_1000ml_00_00', 340: 'Luk_WOD_Czy_BUT_1000ml_01_00', 341: 'Luk_WOD_Czy_BUT_200ml_00_00', 342: 'Luk_WOD_Czy_BUT_200ml_01_00', 343: 'Luk_WOD_Czy_BUT_500ml_00_00', 344: 'Luk_WOD_Czy_BUT_500ml_01_00', 345: 'Luk_WOD_Czy_BUT_700ml_00_00', 346: 'Luk_WOD_Czy_BUT_700ml_01_00', 347: 'LukWisni_WOD_Sma_BUT_500ml_00_00', 348: 'Mal_LIK_BUT_500ml_00_00', 349: 'Mal_LIK_BUT_700ml_00_00', 350: 'Mal_LIK_BUT_700ml_01_00', 351: 'Mal_LIK_BUT_700ml_02_00', 352: 'Mal_NOT_Rec', 353: 'Malf_NOT_Rec', 354: 'MalfConAra_GIN_BUT_700ml_00_00', 355: 'MalfConLim_GIN_BUT_700ml_00_00', 356: 'MalfOrigiIta_GIN_BUT_700ml_00_00', 357: 'MalfRosaIta_GIN_BUT_700ml_00_00', 358: 'MalLime_LIK_BUT_700ml_00_00', 359: 'MalPassiFru_LIK_BUT_700ml_00_00', 360: 'MalPassiFru_LIK_BUT_700ml_01_00', 361: 'MalPassiFru_LIK_BUT_700ml_02_00', 362: 'Mar_NOT_Rec', 363: 'MarBlueSwi_KON_BUT_700ml_00_00', 364: 'MarBlueSwi_KON_KAR_700ml_00_00', 365: 'MarCordoBle_KON_BUT_700ml_00_00', 366: 'MarCordoBle_KON_KAR_700ml_00_00', 367: 'MarLor_KON_BUT_700ml_00_00', 368: 'MarLor_KON_TUB_700ml_00_00', 369: 'MarMedai_KON_BUT_700ml_00_00', 370: 'MarMedai_KON_BUT_700ml_02_00', 371: 'MarMedai_KON_BUT_700ml_03_00', 372: 'MarMedai_KON_KAR_700ml_00_00', 373: 'MarMedai_KON_KAR_700ml_02_00', 374: 'MarMedai_KON_KAR_700ml_03_00', 375: 'MarMedai_KON_KAR_700ml_04_00', 376: 'MarMedai_KON_KAR_700ml_05_00', 377: 'MarMedai_KON_KAR_700ml_06_00', 378: 'MarVs_KON_BUT_700ml_00_00', 379: 'MarVs_KON_BUT_700ml_01_00', 380: 'MarVs_KON_KAR_2KIE_700ml_01_00', 381: 'MarVs_KON_KAR_700ml_00_00', 382: 'MarVs_KON_KAR_700ml_01_00', 383: 'MarVsopRedBar_KON_KAR_2SZK_700ml_00_00', 384: 'MarVsopRedBar_KON_KAR_2SZK_700ml_01_00', 385: 'MarVsopRedBar_KON_KAR_2SZK_700ml_02_00', 386: 'MarVsSinDis_KON_BUT_700ml_00_00', 387: 'MarVsSinDis_KON_KAR_700ml_00_00', 388: 'MarVsSinDis_KON_KAR_700ml_01_00', 389: 'MarVsSinDis_KON_KAR_700ml_02_00', 390: 'MarVsSinDis_KON_KAR_KIE_700ml_00_00', 391: 'MarXo_KON_BUT_700ml_00_00', 392: 'MarXo_KON_BUT_700ml_01_00', 393: 'MarXo_KON_KAR_700ml_00_00', 394: 'Mon47_NOT_Rec', 395: 'Mon47Dry_GIN_BUT_500ml_00_00', 396: 'Mon47Sloe_GIN_BUT_500ml_00_00', 397: 'Mum_NOT_Rec', 398: 'MumDemiSec_SZA_BUT_750ml_00_00', 399: 'MumDemiSec_SZA_BUT_750ml_01_00', 400: 'MumGrandCor_SZA_BUT_750ml_00_00', 401: 'MumGrandCor_SZA_KAR_2KIE_750ml_00_00', 402: 'MumGrandCor_SZA_KAR_750ml_00_00', 403: 'MumGrandCorRos_SZA_BUT_750ml_00_00', 404: 'MumIceExt_SZA_BUT_750ml_00_00', 405: 'MumOlymp_SZA_BUT_750ml_01_00', 406: 'MumRose_SZA_BUT_750ml_00_00', 407: 'MumRose_SZA_BUT_750ml_01_00', 408: 'MumRouge_SZA_BUT_1500ml_00_00', 409: 'MumRouge_SZA_BUT_3000ml_00_00', 410: 'MumRouge_SZA_BUT_375ml_00_00', 411: 'MumRouge_SZA_BUT_375ml_01_00', 412: 'MumRouge_SZA_BUT_750ml_00_00', 413: 'MumRouge_SZA_BUT_750ml_01_00', 414: 'MumRouge_SZA_KAR_750ml_00_00', 415: 'MumRouge_SZA_KAR_750ml_02_00', 416: 'MumRouge_SZA_KAR_750ml_03_00', 417: 'MumRouge_SZA_KAR_750ml_05_00', 418: 'MumRouge_SZA_KAR_750ml_06_00', 419: 'MumRouge_SZA_SKR_3000ml_00_00', 420: 'Olm_NOT_Rec', 421: 'OlmAltosPla_TEQ_BUT_700ml_00_00', 422: 'OlmAltosRep_TEQ_BUT_700ml_00_00', 423: 'OlmBlanc_TEQ_BUT_700ml_00_00', 424: 'OlmBlanc_TEQ_BUT_700ml_01_00', 425: 'OlmBlanc_TEQ_BUT_700ml_02_00', 426: 'OlmGold_TEQ_BUT_700ml_00_00', 427: 'OlmGold_TEQ_BUT_700ml_01_00', 428: 'OlmGold_TEQ_BUT_700ml_02_00', 429: 'Ost_NOT_Rec', 430: 'Ost_WOD_Czy_BUT_1000ml_00_00', 431: 'Ost_WOD_Czy_BUT_1750ml_00_00', 432: 'Ost_WOD_Czy_BUT_3000ml_00_00', 433: 'Ost_WOD_Czy_BUT_500ml_00_00', 434: 'Ost_WOD_Czy_BUT_700ml_00_00', 435: 'Ost_WOD_Czy_KAR_700ml_00_00', 436: 'Ost_WOD_Czy_KAR_KIEMIO_700ml_00_00', 437: 'OstBlack_WOD_Czy_BUT_700ml_00_00', 438: 'OstVap_WOD_Czy_KAR_700ml_00_00', 439: 'PanTad_NOT_Rec', 440: 'PanTad_WOD_Czy_BUT_500ml_00_00', 441: 'PanTad_WOD_Czy_BUT_500ml_01_00', 442: 'PanTad_WOD_Czy_BUT_500ml_02_00', 443: 'PanTad_WOD_Czy_BUT_500ml_03_00', 444: 'PanTad_WOD_Czy_BUT_500ml_05_00', 445: 'PanTad_WOD_Czy_BUT_700ml_00_00', 446: 'PanTad_WOD_Czy_BUT_700ml_01_00', 447: 'PanTad_WOD_Czy_BUT_700ml_02_00', 448: 'PanTad_WOD_Czy_BUT_700ml_03_00', 449: 'PanTad_WOD_Czy_BUT_700ml_06_00', 450: 'PanTadAroni_WOD_Sma_BUT_500ml_00_00', 451: 'PanTadAroni_WOD_Sma_BUT_500ml_01_00', 452: 'PanTadAroni_WOD_Sma_BUT_500ml_02_00', 453: 'PanTadAroni_WOD_Sma_BUT_500ml_03_00', 454: 'PanTadPrzep_WOD_Sma_BUT_500ml_00_00', 455: 'PanTadPrzep_WOD_Sma_BUT_500ml_01_00', 456: 'PanTadPrzep_WOD_Sma_BUT_500ml_02_00', 457: 'PanTadPrzep_WOD_Sma_BUT_500ml_03_00', 458: 'PanZosSlonyKar_LIK_BUT_500ml_00_00', 459: 'Pas_NOT_Rec', 460: 'Pas_WHI_BleSco_BUT_1000ml_00_00', 461: 'Pas_WHI_BleSco_BUT_1000ml_01_00', 462: 'Pas_WHI_BleSco_BUT_200ml_00_00', 463: 'Pas_WHI_BleSco_BUT_500ml_00_00', 464: 'Pas_WHI_BleSco_BUT_500ml_01_00', 465: 'Pas_WHI_BleSco_BUT_700ml_00_00', 466: 'Pas_WHI_BleSco_BUT_700ml_01_00', 467: 'PerJou_NOT_Rec', 468: 'PerJouBelleEpo_SZA_BUT_750ml_00_00', 469: 'PerJouBelleEpo_SZA_BUT_750ml_01_00', 470: 'PerJouBelleEpo_SZA_KAR_750ml_00_00', 471: 'PerJouGrandBru_SZA_BUT_750ml_00_00', 472: 'PerJouGrandBru_SZA_BUT_750ml_01_00', 473: 'PerJouGrandBru_SZA_KAR_750ml_01_00', 474: 'Pols_NOT_Rec', 475: 'PolsWisni_WOD_Sma_BUT_200ml_00_00', 476: 'PolsWisni_WOD_Sma_BUT_500ml_00_00', 477: 'Red_NOT_Rec', 478: 'Red_WHI_SinIri_12Yo_BUT_700ml_00_00', 479: 'Red_WHI_SinIri_12Yo_BUT_700ml_01_00', 480: 'Red_WHI_SinIri_12Yo_KAR_700ml_00_00', 481: 'Red_WHI_SinIri_12Yo_KAR_700ml_01_00', 482: 'Red_WHI_SinIri_21Yo_BUT_700ml_00_00', 483: 'Red_WHI_SinIri_21Yo_KAR_700ml_00_00', 484: 'Ric_LIK_BUT_700ml_00_00', 485: 'Ric_LIK_BUT_700ml_01_00', 486: 'Ric_NOT_Rec', 487: 'Robocza', 488: 'RoySal_NOT_Rec', 489: 'RoySal_WHI_BleSco_21Yo_BUT_700ml_00_00', 490: 'RoySal_WHI_BleSco_21Yo_BUT_700ml_01_00', 491: 'RoySal_WHI_BleSco_21Yo_KAR_700ml_00_00', 492: 'RoySal_WHI_BleSco_21Yo_KAR_700ml_01_00', 493: 'RoySalDiamoTri_WHI_BleSco_BUT_700ml_00_00', 494: 'RoySalDiamoTri_WHI_BleSco_KAR_700ml_00_00', 495: 'Sca_NOT_Rec', 496: 'ScaGlans_WHI_SinSco_BUT_700ml_00_00', 497: 'ScaGlans_WHI_SinSco_KAR_700ml_00_00', 498: 'ScaSkire_WHI_SinSco_BUT_700ml_00_00', 499: 'ScaSkire_WHI_SinSco_KAR_700ml_00_00', 500: 'SeaGin_GIN_BUT_350ml_01_00', 501: 'SeaGin_GIN_BUT_700ml_01_00', 502: 'SeaGin_NOT_Rec', 503: 'SeaGinLime_GIN_BUT_350ml_01_00', 504: 'SeaGinLime_GIN_BUT_700ml_01_00', 505: 'Siw_NOT_Rec', 506: 'Siw_WOD_Sma_BUT_500ml_00_00', 507: 'Siw_WOD_Sma_BUT_500ml_01_00', 508: 'TheGle_NOT_Rec', 509: 'TheGle_WHI_SinSco_12Yo_BUT_50ml_00_00', 510: 'TheGle_WHI_SinSco_12Yo_BUT_700ml_00_00', 511: 'TheGle_WHI_SinSco_12Yo_BUT_700ml_01_00', 512: 'TheGle_WHI_SinSco_12Yo_KAR_2SZK_700ml_00_00', 513: 'TheGle_WHI_SinSco_12Yo_KAR_2SZK_700ml_01_00', 514: 'TheGle_WHI_SinSco_12Yo_KAR_2SZK_700ml_02_00', 515: 'TheGle_WHI_SinSco_12Yo_KAR_2SZK_700ml_03_00', 516: 'TheGle_WHI_SinSco_12Yo_KAR_700ml_00_00', 517: 'TheGle_WHI_SinSco_12Yo_KAR_700ml_01_00', 518: 'TheGle_WHI_SinSco_12Yo_KAR_SKA_700ml_00_00', 519: 'TheGle_WHI_SinSco_15Yo_BUT_700ml_00_00', 520: 'TheGle_WHI_SinSco_15Yo_BUT_700ml_01_00', 521: 'TheGle_WHI_SinSco_15Yo_KAR_2SZK_700ml_00_00', 522: 'TheGle_WHI_SinSco_15Yo_KAR_700ml_00_00', 523: 'TheGle_WHI_SinSco_15Yo_KAR_700ml_01_00', 524: 'TheGle_WHI_SinSco_18Yo_BUT_700ml_00_00', 525: 'TheGle_WHI_SinSco_18Yo_BUT_700ml_01_00', 526: 'TheGle_WHI_SinSco_18Yo_KAR_700ml_00_00', 527: 'TheGle_WHI_SinSco_18Yo_KAR_700ml_01_00', 528: 'TheGle_WHI_SinSco_21Yo_BUT_700ml_00_00', 529: 'TheGle_WHI_SinSco_21Yo_KAR_700ml_00_00', 530: 'TheGle_WHI_SinSco_25Yo_BUT_700ml_00_00', 531: 'TheGle_WHI_SinSco_25Yo_SKR_700ml_00_00', 532: 'TheGleFoundRes_WHI_SinSco_BUT_700ml_00_00', 533: 'TheGleFoundRes_WHI_SinSco_BUT_700ml_01_00', 534: 'TheGleFoundRes_WHI_SinSco_KAR_700ml_00_00', 535: 'TheGleFoundRes_WHI_SinSco_KAR_700ml_01_00', 536: 'TheGleIllicSti_WHI_SinSco_12Yo_BUT_700ml_00_00', 537: 'TheGleLicenDra_WHI_SinSco_12Yo_BUT_700ml_00_00', 538: 'TheGleLicenDra_WHI_SinSco_12Yo_KAR_700ml_00_00', 539: 'TheGleSinglCasSheBut_WHI_SinSco_14Yo_BUT_700ml_00_00', 540: 'TheGleSinglCasSheBut_WHI_SinSco_14Yo_KAR_700ml_00_00', 541: 'TheGleSpect_WHI_SinSco_KAR_600ml_00_00', 542: 'Wyb_NOT_Rec', 543: 'Wyb_WOD_Czy_BUT_1000ml_00_00', 544: 'Wyb_WOD_Czy_BUT_200ml_00_00', 545: 'Wyb_WOD_Czy_BUT_500ml_00_00', 546: 'Wyb_WOD_Czy_BUT_50ml_00_00', 547: 'Wyb_WOD_Czy_BUT_700ml_00_00', 548: 'Wyb_WOD_Czy_BUT_700ml_01_00', 549: 'WybAgres_WOD_Sma_BUT_200ml_00_00', 550: 'WybAgres_WOD_Sma_BUT_500ml_00_00', 551: 'WybCzarnPor_WOD_Sma_BUT_200ml_00_00', 552: 'WybCzarnPor_WOD_Sma_BUT_500ml_00_00', 553: 'WybCzarnPor_WOD_Sma_BUT_500ml_01_00', 554: 'WybCzarnPor_WOD_Sma_BUT_500ml_02_00', 555: 'WybExqui_WOD_Czy_BUT_1750ml_00_00', 556: 'WybExqui_WOD_Czy_BUT_700ml_00_00', 557: 'WybExqui_WOD_Czy_KAR_700ml_00_00', 558: 'WybGrusz_WOD_Sma_BUT_200ml_00_00', 559: 'WybGrusz_WOD_Sma_BUT_500ml_00_00', 560: 'WybGrusz_WOD_Sma_BUT_500ml_01_00', 561: 'WybGrusz_WOD_Sma_BUT_500ml_02_00', 562: 'WybOdMis_WOD_Czy_BUT_500ml_00_00', 563: 'WybOdMis_WOD_Czy_BUT_700ml_00_00', 564: 'WybProst_WOD_Czy_BUT_500ml_00_00', 565: 'WybProst_WOD_Czy_BUT_500ml_01_00', 566: 'WybProst_WOD_Czy_BUT_500ml_02_00', 567: 'WybProst_WOD_Czy_BUT_700ml_00_00', 568: 'WybProst_WOD_Czy_BUT_700ml_01_00', 569: 'WybProst_WOD_Czy_BUT_700ml_02_00', 570: 'WybPszen_WOD_Czy_BUT_500ml_00_00', 571: 'WybPszen_WOD_Czy_BUT_500ml_01_00', 572: 'WybPszen_WOD_Czy_BUT_500ml_02_00', 573: 'WybSliwk_WOD_Sma_BUT_200ml_00_00', 574: 'WybSliwk_WOD_Sma_BUT_200ml_01_00', 575: 'WybSliwk_WOD_Sma_BUT_500ml_00_00', 576: 'WybSliwk_WOD_Sma_BUT_500ml_01_00', 577: 'WybSliwk_WOD_Sma_BUT_500ml_02_00', 578: 'WybWisni_WOD_Sma_BUT_200ml_00_00', 579: 'WybWisni_WOD_Sma_BUT_200ml_01_00', 580: 'WybWisni_WOD_Sma_BUT_500ml_00_00', 581: 'WybWisni_WOD_Sma_BUT_500ml_01_00', 582: 'WybWisni_WOD_Sma_BUT_500ml_02_00', 583: 'WybZiemn_WOD_Czy_BUT_500ml_00_00', 584: 'WybZiemn_WOD_Czy_BUT_500ml_01_00', 585: 'WybZiemn_WOD_Czy_BUT_500ml_02_00'}, 'max_instances_per_image': 100, 'regenerate_source_id': False, 'min_level': 3, 'max_level': 7, 'num_scales': 3, 'aspect_ratios': [1.0, 2.0, 0.5], 'anchor_scale': 4.0, 'is_training_bn': True, 'momentum': 0.9, 'optimizer': 'sgd', 'learning_rate': 0.8, 'lr_warmup_init': 0.08, 'lr_warmup_epoch': 1.0, 'first_lr_drop_epoch': 200.0, 'second_lr_drop_epoch': 250.0, 'poly_lr_power': 0.9, 'clip_gradients_norm': 10.0, 'num_epochs': 1, 'data_format': 'channels_last', 'mean_rgb': [123.675, 116.28, 103.53], 'stddev_rgb': [58.395, 57.120000000000005, 57.375], 'scale_range': False, 'label_smoothing': 0.0, 'alpha': 0.25, 'gamma': 1.5, 'delta': 0.1, 'box_loss_weight': 50.0, 'iou_loss_type': None, 'iou_loss_weight': 1.0, 'weight_decay': 4e-05, 'strategy': None, 'mixed_precision': False, 'loss_scale': None, 'box_class_repeats': 4, 'fpn_cell_repeats': 6, 'fpn_num_filters': 160, 'separable_conv': True, 'apply_bn_for_resampling': True, 'conv_after_downsample': False, 'conv_bn_act_pattern': False, 'drop_remainder': True, 'nms_configs': {'method': 'gaussian', 'iou_thresh': None, 'score_thresh': 0.0, 'sigma': None, 'pyfunc': False, 'max_nms_inputs': 0, 'max_output_size': 100}, 'tflite_max_detections': 100, 'fpn_name': None, 'fpn_weight_method': None, 'fpn_config': None, 'survival_prob': None, 'img_summary_steps': None, 'lr_decay_method': 'cosine', 'moving_average_decay': 0.9998, 'ckpt_var_scope': None, 'skip_mismatch': True, 'backbone_name': 'efficientnet-b3', 'backbone_config': None, 'var_freeze_expr': '(efficientnet|fpn_cells|resample_p6)', 'use_keras_model': True, 'dataset_type': None, 'positives_momentum': None, 'grad_checkpoint': False, 'verbose': 1, 'save_freq': 'epoch', 'model_name': 'efficientdet-d3', 'iterations_per_loop': 1000, 'model_dir': './tmp/efficientdet-d3-finetune', 'num_shards': 8, 'num_examples_per_epoch': 125, 'backbone_ckpt': '', 'ckpt': 'efficientdet-d3', 'val_json_file': None, 'testdev_dir': None, 'profile': False, 'mode': 'train'}
INFO:tensorflow:Using config: {'_model_dir': './tmp/efficientdet-d3-finetune', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': 1000, '_save_checkpoints_secs': None, '_session_config': allow_soft_placement: true
, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 1000, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}
I0102 23:06:55.367058 140562995341120 estimator.py:202] Using config: {'_model_dir': './tmp/efficientdet-d3-finetune', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': 1000, '_save_checkpoints_secs': None, '_session_config': allow_soft_placement: true
, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 1000, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}
INFO:tensorflow:Using config: {'_model_dir': './tmp/efficientdet-d3-finetune', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': 1000, '_save_checkpoints_secs': None, '_session_config': allow_soft_placement: true
, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 1000, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}
I0102 23:06:55.368503 140562995341120 estimator.py:202] Using config: {'_model_dir': './tmp/efficientdet-d3-finetune', '_tf_random_seed': None, '_save_summary_steps': 100, '_save_checkpoints_steps': 1000, '_save_checkpoints_secs': None, '_session_config': allow_soft_placement: true
, '_keep_checkpoint_max': 5, '_keep_checkpoint_every_n_hours': 10000, '_log_step_count_steps': 1000, '_train_distribute': None, '_device_fn': None, '_protocol': None, '_eval_distribute': None, '_experimental_distribute': None, '_experimental_max_worker_delay_secs': None, '_session_creation_timeout_secs': 7200, '_checkpoint_save_graph_def': True, '_service': None, '_cluster_spec': ClusterSpec({}), '_task_type': 'worker', '_task_id': 0, '_global_id_in_cluster': 0, '_master': '', '_evaluation_master': '', '_is_chief': True, '_num_ps_replicas': 0, '_num_worker_replicas': 1}
WARNING:tensorflow:From /home/da/py38/lib/python3.8/site-packages/tensorflow/python/training/training_util.py:396: Variable.initialized_value (from tensorflow.python.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Use Variable.read_value. Variables in 2.X are initialized automatically both in eager and graph (inside tf.defun) contexts.
W0102 23:06:55.376179 140562995341120 deprecation.py:337] From /home/da/py38/lib/python3.8/site-packages/tensorflow/python/training/training_util.py:396: Variable.initialized_value (from tensorflow.python.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Use Variable.read_value. Variables in 2.X are initialized automatically both in eager and graph (inside tf.defun) contexts.
I0102 23:06:55.816170 140562995341120 dataloader.py:84] target_size = (896, 896), output_size = (896, 896)
INFO:tensorflow:Calling model_fn.
I0102 23:06:56.385631 140562995341120 estimator.py:1173] Calling model_fn.
I0102 23:06:56.385888 140562995341120 utils.py:535] use mixed precision policy name float32
WARNING:tensorflow:From /home/da/git/woj/efficientdet/utils.py:536: The name tf.keras.layers.enable_v2_dtype_behavior is deprecated. Please use tf.compat.v1.keras.layers.enable_v2_dtype_behavior instead.
W0102 23:06:56.663122 140562995341120 module_wrapper.py:149] From /home/da/git/woj/efficientdet/utils.py:536: The name tf.keras.layers.enable_v2_dtype_behavior is deprecated. Please use tf.compat.v1.keras.layers.enable_v2_dtype_behavior instead.
I0102 23:06:56.668133 140562995341120 efficientnet_builder.py:215] global_params= GlobalParams(batch_norm_momentum=0.99, batch_norm_epsilon=0.001, dropout_rate=0.3, data_format='channels_last', num_classes=1000, width_coefficient=1.2, depth_coefficient=1.4, depth_divisor=8, min_depth=None, survival_prob=0.8, relu_fn=functools.partial(<function activation_fn at 0x7fd68a79b670>, act_type='swish'), batch_norm=<class 'utils.BatchNormalization'>, use_se=True, local_pooling=None, condconv_num_experts=None, clip_projection_output=False, blocks_args=['r1_k3_s11_e1_i32_o16_se0.25', 'r2_k3_s22_e6_i16_o24_se0.25', 'r2_k5_s22_e6_i24_o40_se0.25', 'r3_k3_s22_e6_i40_o80_se0.25', 'r3_k5_s11_e6_i80_o112_se0.25', 'r4_k5_s22_e6_i112_o192_se0.25', 'r1_k3_s11_e6_i192_o320_se0.25'], fix_head_stem=None, grad_checkpoint=False)
I0102 23:06:57.114061 140562995341120 efficientdet_keras.py:750] building FPNCell cell_0
I0102 23:06:57.114546 140562995341120 efficientdet_keras.py:761] fnode 0 : {'feat_level': 6, 'inputs_offsets': [3, 4]}
I0102 23:06:57.115497 140562995341120 efficientdet_keras.py:761] fnode 1 : {'feat_level': 5, 'inputs_offsets': [2, 5]}
I0102 23:06:57.116436 140562995341120 efficientdet_keras.py:761] fnode 2 : {'feat_level': 4, 'inputs_offsets': [1, 6]}
I0102 23:06:57.117397 140562995341120 efficientdet_keras.py:761] fnode 3 : {'feat_level': 3, 'inputs_offsets': [0, 7]}
I0102 23:06:57.119197 140562995341120 efficientdet_keras.py:761] fnode 4 : {'feat_level': 4, 'inputs_offsets': [1, 7, 8]}
I0102 23:06:57.120199 140562995341120 efficientdet_keras.py:761] fnode 5 : {'feat_level': 5, 'inputs_offsets': [2, 6, 9]}
I0102 23:06:57.121195 140562995341120 efficientdet_keras.py:761] fnode 6 : {'feat_level': 6, 'inputs_offsets': [3, 5, 10]}
I0102 23:06:57.122211 140562995341120 efficientdet_keras.py:761] fnode 7 : {'feat_level': 7, 'inputs_offsets': [4, 11]}
I0102 23:06:57.123452 140562995341120 efficientdet_keras.py:750] building FPNCell cell_1
I0102 23:06:57.123817 140562995341120 efficientdet_keras.py:761] fnode 0 : {'feat_level': 6, 'inputs_offsets': [3, 4]}
I0102 23:06:57.124748 140562995341120 efficientdet_keras.py:761] fnode 1 : {'feat_level': 5, 'inputs_offsets': [2, 5]}
I0102 23:06:57.125736 140562995341120 efficientdet_keras.py:761] fnode 2 : {'feat_level': 4, 'inputs_offsets': [1, 6]}
I0102 23:06:57.126750 140562995341120 efficientdet_keras.py:761] fnode 3 : {'feat_level': 3, 'inputs_offsets': [0, 7]}
I0102 23:06:57.127735 140562995341120 efficientdet_keras.py:761] fnode 4 : {'feat_level': 4, 'inputs_offsets': [1, 7, 8]}
I0102 23:06:57.128686 140562995341120 efficientdet_keras.py:761] fnode 5 : {'feat_level': 5, 'inputs_offsets': [2, 6, 9]}
I0102 23:06:57.129684 140562995341120 efficientdet_keras.py:761] fnode 6 : {'feat_level': 6, 'inputs_offsets': [3, 5, 10]}
I0102 23:06:57.130661 140562995341120 efficientdet_keras.py:761] fnode 7 : {'feat_level': 7, 'inputs_offsets': [4, 11]}
I0102 23:06:57.131980 140562995341120 efficientdet_keras.py:750] building FPNCell cell_2
I0102 23:06:57.132383 140562995341120 efficientdet_keras.py:761] fnode 0 : {'feat_level': 6, 'inputs_offsets': [3, 4]}
I0102 23:06:57.133302 140562995341120 efficientdet_keras.py:761] fnode 1 : {'feat_level': 5, 'inputs_offsets': [2, 5]}
I0102 23:06:57.134217 140562995341120 efficientdet_keras.py:761] fnode 2 : {'feat_level': 4, 'inputs_offsets': [1, 6]}
I0102 23:06:57.135276 140562995341120 efficientdet_keras.py:761] fnode 3 : {'feat_level': 3, 'inputs_offsets': [0, 7]}
I0102 23:06:57.136222 140562995341120 efficientdet_keras.py:761] fnode 4 : {'feat_level': 4, 'inputs_offsets': [1, 7, 8]}
I0102 23:06:57.137199 140562995341120 efficientdet_keras.py:761] fnode 5 : {'feat_level': 5, 'inputs_offsets': [2, 6, 9]}
I0102 23:06:57.138221 140562995341120 efficientdet_keras.py:761] fnode 6 : {'feat_level': 6, 'inputs_offsets': [3, 5, 10]}
I0102 23:06:57.139251 140562995341120 efficientdet_keras.py:761] fnode 7 : {'feat_level': 7, 'inputs_offsets': [4, 11]}
I0102 23:06:57.140518 140562995341120 efficientdet_keras.py:750] building FPNCell cell_3
I0102 23:06:57.140926 140562995341120 efficientdet_keras.py:761] fnode 0 : {'feat_level': 6, 'inputs_offsets': [3, 4]}
I0102 23:06:57.141898 140562995341120 efficientdet_keras.py:761] fnode 1 : {'feat_level': 5, 'inputs_offsets': [2, 5]}
I0102 23:06:57.142953 140562995341120 efficientdet_keras.py:761] fnode 2 : {'feat_level': 4, 'inputs_offsets': [1, 6]}
I0102 23:06:57.143951 140562995341120 efficientdet_keras.py:761] fnode 3 : {'feat_level': 3, 'inputs_offsets': [0, 7]}
I0102 23:06:57.144974 140562995341120 efficientdet_keras.py:761] fnode 4 : {'feat_level': 4, 'inputs_offsets': [1, 7, 8]}
I0102 23:06:57.145984 140562995341120 efficientdet_keras.py:761] fnode 5 : {'feat_level': 5, 'inputs_offsets': [2, 6, 9]}
I0102 23:06:57.147073 140562995341120 efficientdet_keras.py:761] fnode 6 : {'feat_level': 6, 'inputs_offsets': [3, 5, 10]}
I0102 23:06:57.148193 140562995341120 efficientdet_keras.py:761] fnode 7 : {'feat_level': 7, 'inputs_offsets': [4, 11]}
I0102 23:06:57.149541 140562995341120 efficientdet_keras.py:750] building FPNCell cell_4
I0102 23:06:57.149949 140562995341120 efficientdet_keras.py:761] fnode 0 : {'feat_level': 6, 'inputs_offsets': [3, 4]}
I0102 23:06:57.151009 140562995341120 efficientdet_keras.py:761] fnode 1 : {'feat_level': 5, 'inputs_offsets': [2, 5]}
I0102 23:06:57.152015 140562995341120 efficientdet_keras.py:761] fnode 2 : {'feat_level': 4, 'inputs_offsets': [1, 6]}
I0102 23:06:57.152967 140562995341120 efficientdet_keras.py:761] fnode 3 : {'feat_level': 3, 'inputs_offsets': [0, 7]}
I0102 23:06:57.154082 140562995341120 efficientdet_keras.py:761] fnode 4 : {'feat_level': 4, 'inputs_offsets': [1, 7, 8]}
I0102 23:06:57.155227 140562995341120 efficientdet_keras.py:761] fnode 5 : {'feat_level': 5, 'inputs_offsets': [2, 6, 9]}
I0102 23:06:57.156267 140562995341120 efficientdet_keras.py:761] fnode 6 : {'feat_level': 6, 'inputs_offsets': [3, 5, 10]}
I0102 23:06:57.157230 140562995341120 efficientdet_keras.py:761] fnode 7 : {'feat_level': 7, 'inputs_offsets': [4, 11]}
I0102 23:06:57.158569 140562995341120 efficientdet_keras.py:750] building FPNCell cell_5
I0102 23:06:57.158961 140562995341120 efficientdet_keras.py:761] fnode 0 : {'feat_level': 6, 'inputs_offsets': [3, 4]}
I0102 23:06:57.159890 140562995341120 efficientdet_keras.py:761] fnode 1 : {'feat_level': 5, 'inputs_offsets': [2, 5]}
I0102 23:06:57.160845 140562995341120 efficientdet_keras.py:761] fnode 2 : {'feat_level': 4, 'inputs_offsets': [1, 6]}
I0102 23:06:57.161807 140562995341120 efficientdet_keras.py:761] fnode 3 : {'feat_level': 3, 'inputs_offsets': [0, 7]}
I0102 23:06:57.162744 140562995341120 efficientdet_keras.py:761] fnode 4 : {'feat_level': 4, 'inputs_offsets': [1, 7, 8]}
I0102 23:06:57.163748 140562995341120 efficientdet_keras.py:761] fnode 5 : {'feat_level': 5, 'inputs_offsets': [2, 6, 9]}
I0102 23:06:57.164839 140562995341120 efficientdet_keras.py:761] fnode 6 : {'feat_level': 6, 'inputs_offsets': [3, 5, 10]}
I0102 23:06:57.165806 140562995341120 efficientdet_keras.py:761] fnode 7 : {'feat_level': 7, 'inputs_offsets': [4, 11]}
WARNING:tensorflow:From /home/da/py38/lib/python3.8/site-packages/keras/layers/normalization/batch_normalization.py:532: _colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
W0102 23:06:57.293271 140562995341120 deprecation.py:337] From /home/da/py38/lib/python3.8/site-packages/keras/layers/normalization/batch_normalization.py:532: _colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
I0102 23:06:57.308187 140562995341120 efficientnet_model.py:734] Built stem stem : (2, 448, 448, 40)
I0102 23:06:57.308448 140562995341120 efficientnet_model.py:755] block_0 survival_prob: 1.0
I0102 23:06:57.308863 140562995341120 efficientnet_model.py:373] Block blocks_0 input shape: (2, 448, 448, 40)
I0102 23:06:57.351354 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 448, 448, 40)
I0102 23:06:57.385758 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 40)
I0102 23:06:57.426656 140562995341120 efficientnet_model.py:413] Project shape: (2, 448, 448, 24)
I0102 23:06:57.427096 140562995341120 efficientnet_model.py:755] block_1 survival_prob: 0.9923076923076923
I0102 23:06:57.427569 140562995341120 efficientnet_model.py:373] Block blocks_1 input shape: (2, 448, 448, 24)
I0102 23:06:57.470309 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 448, 448, 24)
I0102 23:06:57.503290 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 24)
I0102 23:06:57.554880 140562995341120 efficientnet_model.py:413] Project shape: (2, 448, 448, 24)
I0102 23:06:57.555342 140562995341120 efficientnet_model.py:755] block_2 survival_prob: 0.9846153846153847
I0102 23:06:57.555924 140562995341120 efficientnet_model.py:373] Block blocks_2 input shape: (2, 448, 448, 24)
I0102 23:06:57.599646 140562995341120 efficientnet_model.py:389] Expand shape: (2, 448, 448, 144)
I0102 23:06:57.643708 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 224, 224, 144)
I0102 23:06:57.677206 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 144)
I0102 23:06:57.717100 140562995341120 efficientnet_model.py:413] Project shape: (2, 224, 224, 32)
I0102 23:06:57.717492 140562995341120 efficientnet_model.py:755] block_3 survival_prob: 0.9769230769230769
I0102 23:06:57.717926 140562995341120 efficientnet_model.py:373] Block blocks_3 input shape: (2, 224, 224, 32)
I0102 23:06:57.761598 140562995341120 efficientnet_model.py:389] Expand shape: (2, 224, 224, 192)
I0102 23:06:57.807198 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 224, 224, 192)
I0102 23:06:57.843380 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 192)
I0102 23:06:57.894041 140562995341120 efficientnet_model.py:413] Project shape: (2, 224, 224, 32)
I0102 23:06:57.894551 140562995341120 efficientnet_model.py:755] block_4 survival_prob: 0.9692307692307692
I0102 23:06:57.895071 140562995341120 efficientnet_model.py:373] Block blocks_4 input shape: (2, 224, 224, 32)
I0102 23:06:57.939154 140562995341120 efficientnet_model.py:389] Expand shape: (2, 224, 224, 192)
I0102 23:06:57.989865 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 224, 224, 192)
I0102 23:06:58.026333 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 192)
I0102 23:06:58.083609 140562995341120 efficientnet_model.py:413] Project shape: (2, 224, 224, 32)
I0102 23:06:58.084105 140562995341120 efficientnet_model.py:755] block_5 survival_prob: 0.9615384615384616
I0102 23:06:58.084609 140562995341120 efficientnet_model.py:373] Block blocks_5 input shape: (2, 224, 224, 32)
I0102 23:06:58.132211 140562995341120 efficientnet_model.py:389] Expand shape: (2, 224, 224, 192)
I0102 23:06:58.177023 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 112, 112, 192)
I0102 23:06:58.210987 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 192)
I0102 23:06:58.253363 140562995341120 efficientnet_model.py:413] Project shape: (2, 112, 112, 48)
I0102 23:06:58.253793 140562995341120 efficientnet_model.py:755] block_6 survival_prob: 0.9538461538461539
I0102 23:06:58.254362 140562995341120 efficientnet_model.py:373] Block blocks_6 input shape: (2, 112, 112, 48)
I0102 23:06:58.299015 140562995341120 efficientnet_model.py:389] Expand shape: (2, 112, 112, 288)
I0102 23:06:58.343600 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 112, 112, 288)
I0102 23:06:58.378880 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 288)
I0102 23:06:58.431383 140562995341120 efficientnet_model.py:413] Project shape: (2, 112, 112, 48)
I0102 23:06:58.431832 140562995341120 efficientnet_model.py:755] block_7 survival_prob: 0.9461538461538461
I0102 23:06:58.432401 140562995341120 efficientnet_model.py:373] Block blocks_7 input shape: (2, 112, 112, 48)
I0102 23:06:58.477589 140562995341120 efficientnet_model.py:389] Expand shape: (2, 112, 112, 288)
I0102 23:06:58.529271 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 112, 112, 288)
I0102 23:06:58.564348 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 288)
I0102 23:06:58.615775 140562995341120 efficientnet_model.py:413] Project shape: (2, 112, 112, 48)
I0102 23:06:58.616335 140562995341120 efficientnet_model.py:755] block_8 survival_prob: 0.9384615384615385
I0102 23:06:58.616868 140562995341120 efficientnet_model.py:373] Block blocks_8 input shape: (2, 112, 112, 48)
I0102 23:06:58.665363 140562995341120 efficientnet_model.py:389] Expand shape: (2, 112, 112, 288)
I0102 23:06:58.711553 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 56, 56, 288)
I0102 23:06:58.750468 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 288)
I0102 23:06:58.791332 140562995341120 efficientnet_model.py:413] Project shape: (2, 56, 56, 96)
I0102 23:06:58.791729 140562995341120 efficientnet_model.py:755] block_9 survival_prob: 0.9307692307692308
I0102 23:06:58.792159 140562995341120 efficientnet_model.py:373] Block blocks_9 input shape: (2, 56, 56, 96)
I0102 23:06:58.835121 140562995341120 efficientnet_model.py:389] Expand shape: (2, 56, 56, 576)
I0102 23:06:59.033549 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 56, 56, 576)
I0102 23:06:59.068808 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 576)
I0102 23:06:59.118613 140562995341120 efficientnet_model.py:413] Project shape: (2, 56, 56, 96)
I0102 23:06:59.119120 140562995341120 efficientnet_model.py:755] block_10 survival_prob: 0.9230769230769231
I0102 23:06:59.119661 140562995341120 efficientnet_model.py:373] Block blocks_10 input shape: (2, 56, 56, 96)
I0102 23:06:59.162073 140562995341120 efficientnet_model.py:389] Expand shape: (2, 56, 56, 576)
I0102 23:06:59.207022 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 56, 56, 576)
I0102 23:06:59.243650 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 576)
I0102 23:06:59.296999 140562995341120 efficientnet_model.py:413] Project shape: (2, 56, 56, 96)
I0102 23:06:59.297444 140562995341120 efficientnet_model.py:755] block_11 survival_prob: 0.9153846153846155
I0102 23:06:59.297930 140562995341120 efficientnet_model.py:373] Block blocks_11 input shape: (2, 56, 56, 96)
I0102 23:06:59.342265 140562995341120 efficientnet_model.py:389] Expand shape: (2, 56, 56, 576)
I0102 23:06:59.388134 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 56, 56, 576)
I0102 23:06:59.422876 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 576)
I0102 23:06:59.474277 140562995341120 efficientnet_model.py:413] Project shape: (2, 56, 56, 96)
I0102 23:06:59.474753 140562995341120 efficientnet_model.py:755] block_12 survival_prob: 0.9076923076923077
I0102 23:06:59.475201 140562995341120 efficientnet_model.py:373] Block blocks_12 input shape: (2, 56, 56, 96)
I0102 23:06:59.518475 140562995341120 efficientnet_model.py:389] Expand shape: (2, 56, 56, 576)
I0102 23:06:59.564408 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 56, 56, 576)
I0102 23:06:59.599868 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 576)
I0102 23:06:59.652817 140562995341120 efficientnet_model.py:413] Project shape: (2, 56, 56, 96)
I0102 23:06:59.653294 140562995341120 efficientnet_model.py:755] block_13 survival_prob: 0.9
I0102 23:06:59.653870 140562995341120 efficientnet_model.py:373] Block blocks_13 input shape: (2, 56, 56, 96)
I0102 23:06:59.697269 140562995341120 efficientnet_model.py:389] Expand shape: (2, 56, 56, 576)
I0102 23:06:59.742204 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 56, 56, 576)
I0102 23:06:59.778071 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 576)
I0102 23:06:59.822216 140562995341120 efficientnet_model.py:413] Project shape: (2, 56, 56, 136)
I0102 23:06:59.822714 140562995341120 efficientnet_model.py:755] block_14 survival_prob: 0.8923076923076924
I0102 23:06:59.823220 140562995341120 efficientnet_model.py:373] Block blocks_14 input shape: (2, 56, 56, 136)
I0102 23:06:59.871847 140562995341120 efficientnet_model.py:389] Expand shape: (2, 56, 56, 816)
I0102 23:06:59.917706 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 56, 56, 816)
I0102 23:06:59.953016 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 816)
I0102 23:07:00.005156 140562995341120 efficientnet_model.py:413] Project shape: (2, 56, 56, 136)
I0102 23:07:00.005595 140562995341120 efficientnet_model.py:755] block_15 survival_prob: 0.8846153846153847
I0102 23:07:00.006058 140562995341120 efficientnet_model.py:373] Block blocks_15 input shape: (2, 56, 56, 136)
I0102 23:07:00.052236 140562995341120 efficientnet_model.py:389] Expand shape: (2, 56, 56, 816)
I0102 23:07:00.098638 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 56, 56, 816)
I0102 23:07:00.134895 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 816)
I0102 23:07:00.185768 140562995341120 efficientnet_model.py:413] Project shape: (2, 56, 56, 136)
I0102 23:07:00.186198 140562995341120 efficientnet_model.py:755] block_16 survival_prob: 0.8769230769230769
I0102 23:07:00.186750 140562995341120 efficientnet_model.py:373] Block blocks_16 input shape: (2, 56, 56, 136)
I0102 23:07:00.238000 140562995341120 efficientnet_model.py:389] Expand shape: (2, 56, 56, 816)
I0102 23:07:00.283428 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 56, 56, 816)
I0102 23:07:00.319485 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 816)
I0102 23:07:00.372308 140562995341120 efficientnet_model.py:413] Project shape: (2, 56, 56, 136)
I0102 23:07:00.372743 140562995341120 efficientnet_model.py:755] block_17 survival_prob: 0.8692307692307693
I0102 23:07:00.373246 140562995341120 efficientnet_model.py:373] Block blocks_17 input shape: (2, 56, 56, 136)
I0102 23:07:00.418221 140562995341120 efficientnet_model.py:389] Expand shape: (2, 56, 56, 816)
I0102 23:07:00.464493 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 56, 56, 816)
I0102 23:07:00.500797 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 816)
I0102 23:07:00.552797 140562995341120 efficientnet_model.py:413] Project shape: (2, 56, 56, 136)
I0102 23:07:00.553343 140562995341120 efficientnet_model.py:755] block_18 survival_prob: 0.8615384615384616
I0102 23:07:00.553816 140562995341120 efficientnet_model.py:373] Block blocks_18 input shape: (2, 56, 56, 136)
I0102 23:07:00.598924 140562995341120 efficientnet_model.py:389] Expand shape: (2, 56, 56, 816)
I0102 23:07:00.645026 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 28, 28, 816)
I0102 23:07:00.681046 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 816)
I0102 23:07:00.722500 140562995341120 efficientnet_model.py:413] Project shape: (2, 28, 28, 232)
I0102 23:07:00.722957 140562995341120 efficientnet_model.py:755] block_19 survival_prob: 0.8538461538461539
I0102 23:07:00.723477 140562995341120 efficientnet_model.py:373] Block blocks_19 input shape: (2, 28, 28, 232)
I0102 23:07:00.774166 140562995341120 efficientnet_model.py:389] Expand shape: (2, 28, 28, 1392)
I0102 23:07:00.826123 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 28, 28, 1392)
I0102 23:07:00.863637 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 1392)
I0102 23:07:00.914356 140562995341120 efficientnet_model.py:413] Project shape: (2, 28, 28, 232)
I0102 23:07:00.914877 140562995341120 efficientnet_model.py:755] block_20 survival_prob: 0.8461538461538463
I0102 23:07:00.915332 140562995341120 efficientnet_model.py:373] Block blocks_20 input shape: (2, 28, 28, 232)
I0102 23:07:00.965972 140562995341120 efficientnet_model.py:389] Expand shape: (2, 28, 28, 1392)
I0102 23:07:01.018671 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 28, 28, 1392)
I0102 23:07:01.055501 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 1392)
I0102 23:07:01.105556 140562995341120 efficientnet_model.py:413] Project shape: (2, 28, 28, 232)
I0102 23:07:01.105966 140562995341120 efficientnet_model.py:755] block_21 survival_prob: 0.8384615384615385
I0102 23:07:01.106441 140562995341120 efficientnet_model.py:373] Block blocks_21 input shape: (2, 28, 28, 232)
I0102 23:07:01.156986 140562995341120 efficientnet_model.py:389] Expand shape: (2, 28, 28, 1392)
I0102 23:07:01.206625 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 28, 28, 1392)
I0102 23:07:01.243858 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 1392)
I0102 23:07:01.295665 140562995341120 efficientnet_model.py:413] Project shape: (2, 28, 28, 232)
I0102 23:07:01.296208 140562995341120 efficientnet_model.py:755] block_22 survival_prob: 0.8307692307692308
I0102 23:07:01.296733 140562995341120 efficientnet_model.py:373] Block blocks_22 input shape: (2, 28, 28, 232)
I0102 23:07:01.348539 140562995341120 efficientnet_model.py:389] Expand shape: (2, 28, 28, 1392)
I0102 23:07:01.400004 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 28, 28, 1392)
I0102 23:07:01.436683 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 1392)
I0102 23:07:01.486699 140562995341120 efficientnet_model.py:413] Project shape: (2, 28, 28, 232)
I0102 23:07:01.487220 140562995341120 efficientnet_model.py:755] block_23 survival_prob: 0.8230769230769232
I0102 23:07:01.487727 140562995341120 efficientnet_model.py:373] Block blocks_23 input shape: (2, 28, 28, 232)
I0102 23:07:01.539423 140562995341120 efficientnet_model.py:389] Expand shape: (2, 28, 28, 1392)
I0102 23:07:01.590515 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 28, 28, 1392)
I0102 23:07:01.627768 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 1392)
I0102 23:07:01.681534 140562995341120 efficientnet_model.py:413] Project shape: (2, 28, 28, 232)
I0102 23:07:01.682088 140562995341120 efficientnet_model.py:755] block_24 survival_prob: 0.8153846153846154
I0102 23:07:01.682664 140562995341120 efficientnet_model.py:373] Block blocks_24 input shape: (2, 28, 28, 232)
I0102 23:07:01.737749 140562995341120 efficientnet_model.py:389] Expand shape: (2, 28, 28, 1392)
I0102 23:07:01.792356 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 28, 28, 1392)
I0102 23:07:01.829598 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 1392)
I0102 23:07:01.871776 140562995341120 efficientnet_model.py:413] Project shape: (2, 28, 28, 384)
I0102 23:07:01.872180 140562995341120 efficientnet_model.py:755] block_25 survival_prob: 0.8076923076923077
I0102 23:07:01.872609 140562995341120 efficientnet_model.py:373] Block blocks_25 input shape: (2, 28, 28, 384)
I0102 23:07:01.924215 140562995341120 efficientnet_model.py:389] Expand shape: (2, 28, 28, 2304)
I0102 23:07:01.975001 140562995341120 efficientnet_model.py:392] DWConv shape: (2, 28, 28, 2304)
I0102 23:07:02.011464 140562995341120 efficientnet_model.py:194] Built SE se : (2, 1, 1, 2304)
I0102 23:07:02.062852 140562995341120 efficientnet_model.py:413] Project shape: (2, 28, 28, 384)
I0102 23:07:09.067493 140562995341120 det_model_fn.py:81] LR schedule method: cosine
I0102 23:07:09.566802 140562995341120 utils.py:332] Adding scalar summary ('lrn_rate', <tf.Tensor 'Select:0' shape=() dtype=float32>)
I0102 23:07:09.571111 140562995341120 utils.py:332] Adding scalar summary ('trainloss/cls_loss', <tf.Tensor 'AddN:0' shape=() dtype=float32>)
I0102 23:07:09.575444 140562995341120 utils.py:332] Adding scalar summary ('trainloss/box_loss', <tf.Tensor 'AddN_1:0' shape=() dtype=float32>)
I0102 23:07:09.579521 140562995341120 utils.py:332] Adding scalar summary ('trainloss/det_loss', <tf.Tensor 'add_3:0' shape=() dtype=float32>)
I0102 23:07:09.583730 140562995341120 utils.py:332] Adding scalar summary ('trainloss/reg_l2_loss', <tf.Tensor 'mul_14:0' shape=() dtype=float32>)
I0102 23:07:09.588010 140562995341120 utils.py:332] Adding scalar summary ('trainloss/loss', <tf.Tensor 'add_4:0' shape=() dtype=float32>)
I0102 23:07:09.594656 140562995341120 utils.py:332] Adding scalar summary ('train_epochs', <tf.Tensor 'truediv_7:0' shape=() dtype=float32>)
I0102 23:07:09.623888 140562995341120 det_model_fn.py:397] clip gradients norm by 10.000000
I0102 23:07:13.448079 140562995341120 utils.py:332] Adding scalar summary ('gradient_norm', <tf.Tensor 'clip/global_norm_1/global_norm:0' shape=() dtype=float32>)
I0102 23:07:34.193745 140562995341120 det_model_fn.py:539] restore variables from efficientdet-d3
I0102 23:07:34.193964 140562995341120 utils.py:77] Init model from checkpoint efficientdet-d3
I0102 23:07:34.204338 140562995341120 utils.py:135] Init efficientnet-b3/stem/conv2d/kernel from ckpt var efficientnet-b3/stem/conv2d/kernel
I0102 23:07:34.204492 140562995341120 utils.py:135] Init efficientnet-b3/stem/tpu_batch_normalization/gamma from ckpt var efficientnet-b3/stem/tpu_batch_normalization/gamma
I0102 23:07:34.204604 140562995341120 utils.py:135] Init efficientnet-b3/stem/tpu_batch_normalization/beta from ckpt var efficientnet-b3/stem/tpu_batch_normalization/beta
I0102 23:07:34.204746 140562995341120 utils.py:135] Init efficientnet-b3/stem/tpu_batch_normalization/moving_mean from ckpt var efficientnet-b3/stem/tpu_batch_normalization/moving_mean
I0102 23:07:34.214251 140562995341120 utils.py:127] skip class_net/class-predict/pointwise_kernel ((1, 1, 160, 5274) vs [1, 1, 160, 810]) -- shape mismatch
I0102 23:07:34.214484 140562995341120 utils.py:127] skip class_net/class-predict/bias ((5274,) vs [810]) -- shape mismatch
I0102 23:07:34.218290 140562995341120 utils.py:127] skip class_net/class-predict/pointwise_kernel/ExponentialMovingAverage ((1, 1, 160, 5274) vs [1, 1, 160, 810]) -- shape mismatch
I0102 23:07:34.222586 140562995341120 utils.py:127] skip class_net/class-predict/bias/ExponentialMovingAverage ((5274,) vs [810]) -- shape mismatch
INFO:tensorflow:Done calling model_fn.
I0102 23:07:42.476982 140562995341120 estimator.py:1175] Done calling model_fn.
INFO:tensorflow:Create CheckpointSaverHook.
I0102 23:07:42.478458 140562995341120 basic_session_run_hooks.py:558] Create CheckpointSaverHook.
INFO:tensorflow:Graph was finalized.
I0102 23:07:54.542574 140562995341120 monitored_session.py:243] Graph was finalized.
2023-01-02 23:07:54.543008: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-01-02 23:07:55.255160: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 9666 MB memory: -> device: 0, name: TITAN V, pci bus id: 0000:04:00.0, compute capability: 7.0
INFO:tensorflow:Running local_init_op.
I0102 23:08:12.012063 140562995341120 session_manager.py:527] Running local_init_op.
INFO:tensorflow:Done running local_init_op.
I0102 23:08:12.754739 140562995341120 session_manager.py:530] Done running local_init_op.
INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 0...
I0102 23:08:44.119423 140562995341120 basic_session_run_hooks.py:628] Calling checkpoint listeners before saving checkpoint 0...
INFO:tensorflow:Saving checkpoints for 0 into ./tmp/efficientdet-d3-finetune/model.ckpt.
I0102 23:08:44.146168 140562995341120 basic_session_run_hooks.py:633] Saving checkpoints for 0 into ./tmp/efficientdet-d3-finetune/model.ckpt.
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 0...
I0102 23:08:55.847828 140562995341120 basic_session_run_hooks.py:640] Calling checkpoint listeners after saving checkpoint 0...
2023-01-02 23:09:16.189110: W tensorflow/core/framework/cpu_allocator_impl.cc:82] Allocation of 529256448 exceeds 10% of free system memory.
2023-01-02 23:09:16.189178: W tensorflow/core/framework/cpu_allocator_impl.cc:82] Allocation of 529256448 exceeds 10% of free system memory.
2023-01-02 23:09:16.492752: W tensorflow/core/framework/cpu_allocator_impl.cc:82] Allocation of 529256448 exceeds 10% of free system memory.
2023-01-02 23:09:16.853836: W tensorflow/core/framework/cpu_allocator_impl.cc:82] Allocation of 132314112 exceeds 10% of free system memory.
2023-01-02 23:09:16.853907: W tensorflow/core/framework/cpu_allocator_impl.cc:82] Allocation of 132314112 exceeds 10% of free system memory.
2023-01-02 23:09:28.204211: I tensorflow/stream_executor/cuda/cuda_dnn.cc:368] Loaded cuDNN version 8204
INFO:tensorflow:loss = 303388.44, step = 0
I0102 23:09:32.140894 140562995341120 basic_session_run_hooks.py:266] loss = 303388.44, step = 0
INFO:tensorflow:box_loss = 0.0071479464, cls_loss = 303387.9, det_loss = 303388.25, step = 0
I0102 23:09:32.141317 140562995341120 basic_session_run_hooks.py:266] box_loss = 0.0071479464, cls_loss = 303387.9, det_loss = 303388.25, step = 0
INFO:tensorflow:Calling checkpoint listeners before saving checkpoint 62...
I0102 23:10:28.943011 140562995341120 basic_session_run_hooks.py:628] Calling checkpoint listeners before saving checkpoint 62...
INFO:tensorflow:Saving checkpoints for 62 into ./tmp/efficientdet-d3-finetune/model.ckpt.
I0102 23:10:28.943264 140562995341120 basic_session_run_hooks.py:633] Saving checkpoints for 62 into ./tmp/efficientdet-d3-finetune/model.ckpt.
INFO:tensorflow:Calling checkpoint listeners after saving checkpoint 62...
I0102 23:10:33.580776 140562995341120 basic_session_run_hooks.py:640] Calling checkpoint listeners after saving checkpoint 62...
INFO:tensorflow:Loss for final step: 2.9077873.
I0102 23:10:34.618134 140562995341120 estimator.py:361] Loss for final step: 2.9077873.
from automl.
n3011
commented on June 3, 2024
Use --hparams=config.yaml in the model export step to input the correct number of input classes.
python model_inspect.py --runmode=saved_model --hparams=config.yaml .....
from automl.
Related Issues (20)
- More inplace ops for pytorch lion's impl
- ERROR : 'ImageFont' object has no attribute 'getbbox' HOT 2
- Potentially wrong type inference
- How to apply quantization aware training on EfficientDet keras model?
- How to train ViT image classification model on our dataset using LION optimizer
- how to train model by lion optimizer with fp16? HOT 1
- how to fix (terminate called after throwing an instance of 'std::bad_alloc' what(): std::bad_alloc --------------------------------------------------------------------------- RuntimeError Traceback (most recent call last) Cell In[48], line 3 1 #!rm summary.h5 2 #!rm statepoint.*.h5 ----> 3 sp_filename = model.run() 5 sp = openmc.StatePoint(sp_filename)?
- Error during prediction within coreML framework of the converted Efficientdet-lite0 model
- why the text label is not showing on the bounding box HOT 1
- Question about Lion HOT 1
- TypeError: The `filenames` argument must contain `tf.string` elements. Got `tf.float32` elements error HOT 1
- buffer_size must be greater than zero error when use custom dataset HOT 1
- p.add_(..., inplace=True) error HOT 1
- efficientnetv2-bn parameters for progressive learning
- How to add class weights?
- Error reading original efficientdet-d3_frozen.pb on openCV`s readNetFromTensorflow HOT 2
- EfficienDet output format question
- Recommended way for EfficientDet-Lite Quantization
- Training on custom dataset of EfficientDet-0 model crash : TypeError: 'NoneType' object is not callable
- Exported tflite model is incompatible with MediaPipe
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from automl.