Wahaha1314
commented
3 years ago I am sorry that I did not reply to your message in time. Recently, I have been doing too much academic work. For your question, you should not download the pre-trained weight file "mask_rcnn_coco.h5" trained on the coco dataset and put it under the project folder. You can go to the Internet to look up the file and download it.
------------------ 原始邮件 ------------------ 发件人: "Wahaha1314/Fish-characteristic-measurement" <notifications@github.com>; 发送时间: 2020年10月1日(星期四) 晚上8:49 收件人: "Wahaha1314/Fish-characteristic-measurement"<Fish-characteristic-measurement@noreply.github.com>; 抄送: "无名何许人"<y149167@foxmail.com>;"Mention"<mention@noreply.github.com>; 主题: [Wahaha1314/Fish-characteristic-measurement] Error running \Fish-characteristic-measurement\Complete code\train_model.py (#1)
Started by doing the right dataset training:
Configurations: BACKBONE resnet101 BACKBONE_STRIDES [4, 8, 16, 32, 64] BATCH_SIZE 1 BBOX_STD_DEV [0.1 0.1 0.2 0.2] COMPUTE_BACKBONE_SHAPE None DETECTION_MAX_INSTANCES 100 DETECTION_MIN_CONFIDENCE 0.95 DETECTION_NMS_THRESHOLD 0.3 FPN_CLASSIF_FC_LAYERS_SIZE 1024 GPU_COUNT 1 GRADIENT_CLIP_NORM 5.0 IMAGES_PER_GPU 1 IMAGE_MAX_DIM 1024 IMAGE_META_SIZE 14 IMAGE_MIN_DIM 704 IMAGE_MIN_SCALE 0 IMAGE_RESIZE_MODE square IMAGE_SHAPE [1024 1024 3] LEARNING_MOMENTUM 0.9 LEARNING_RATE 0.001 LOSS_WEIGHTS {'rpn_class_loss': 1.0, 'rpn_bbox_loss': 1.0, 'mrcnn_class_loss': 1.0, 'mrcnn_bbox_loss': 1.0, 'mrcnn_mask_loss': 1.0} MASK_POOL_SIZE 14 MASK_SHAPE [28, 28] MAX_GT_INSTANCES 30 MEAN_PIXEL [123.7 116.8 103.9] MINI_MASK_SHAPE (56, 56) NAME shapes NUM_CLASSES 2 POOL_SIZE 7 POST_NMS_ROIS_INFERENCE 1000 POST_NMS_ROIS_TRAINING 2000 ROI_POSITIVE_RATIO 0.33 RPN_ANCHOR_RATIOS [0.5, 1, 2] RPN_ANCHOR_SCALES (48, 96, 192, 384, 768) RPN_ANCHOR_STRIDE 1 RPN_BBOX_STD_DEV [0.1 0.1 0.2 0.2] RPN_NMS_THRESHOLD 0.7 RPN_TRAIN_ANCHORS_PER_IMAGE 256 STEPS_PER_EPOCH 3500 TOP_DOWN_PYRAMID_SIZE 256 TRAIN_BN False TRAIN_ROIS_PER_IMAGE 300 USE_MINI_MASK True USE_RPN_ROIS True VALIDATION_STEPS 300 WEIGHT_DECAY 0.0001 train_data/labelme_json/DSCN46592_json/img.png train_data/labelme_json/DSCN46601_json/img.png train_data/labelme_json/DSCN46602_json/img.png train_data/labelme_json/DSCN46611_json/img.png train_data/labelme_json/DSCN46612_json/img.png train_data/labelme_json/DSCN46615_json/img.png train_data/labelme_json/DSCN46621_json/img.png train_data/labelme_json/DSCN46622_json/img.png train_data/labelme_json/DSCN46625_json/img.png train_data/labelme_json/DSCN46631_json/img.png train_data/labelme_json/DSCN46632_json/img.png train_data/labelme_json/DSCN46635_json/img.png train_data/labelme_json/DSCN46641_json/img.png train_data/labelme_json/DSCN46642_json/img.png train_data/labelme_json/DSCN46645_json/img.png train_data/labelme_json/DSCN46651_json/img.png train_data/labelme_json/DSCN46652_json/img.png train_data/labelme_json/DSCN46655_json/img.png train_data/labelme_json/DSCN46661_json/img.png train_data/labelme_json/DSCN46662_json/img.png train_data/labelme_json/DSCN46665_json/img.png train_data/labelme_json/DSCN46671_json/img.png train_data/labelme_json/DSCN46672_json/img.png train_data/labelme_json/DSCN46675_json/img.png train_data/labelme_json/DSCN46681_json/img.png train_data/labelme_json/DSCN46682_json/img.png train_data/labelme_json/DSCN46685_json/img.png train_data/labelme_json/DSCN46691_json/img.png train_data/labelme_json/DSCN46692_json/img.png train_data/labelme_json/DSCN46695_json/img.png train_data/labelme_json/DSCN46701_json/img.png train_data/labelme_json/DSCN46702_json/img.png train_data/labelme_json/DSCN46705_json/img.png train_data/labelme_json/DSCN46711_json/img.png train_data/labelme_json/DSCN46712_json/img.png train_data/labelme_json/DSCN46713_json/img.png train_data/labelme_json/DSCN46715_json/img.png train_data/labelme_json/DSCN46721_json/img.png train_data/labelme_json/DSCN46722_json/img.png train_data/labelme_json/DSCN46723_json/img.png train_data/labelme_json/DSCN46725_json/img.png train_data/labelme_json/DSCN46731_json/img.png train_data/labelme_json/DSCN46732_json/img.png train_data/labelme_json/DSCN46733_json/img.png train_data/labelme_json/DSCN46735_json/img.png train_data/labelme_json/DSCN46741_json/img.png train_data/labelme_json/DSCN46742_json/img.png train_data/labelme_json/DSCN46743_json/img.png train_data/labelme_json/DSCN46745_json/img.png train_data/labelme_json/DSCN46751_json/img.png train_data/labelme_json/DSCN46752_json/img.png train_data/labelme_json/DSCN46753_json/img.png train_data/labelme_json/DSCN46755_json/img.png train_data/labelme_json/DSCN46761_json/img.png train_data/labelme_json/DSCN46762_json/img.png train_data/labelme_json/DSCN46763_json/img.png train_data/labelme_json/DSCN46765_json/img.png train_data/labelme_json/DSCN46771_json/img.png train_data/labelme_json/DSCN46772_json/img.png train_data/labelme_json/DSCN46773_json/img.png train_data/labelme_json/DSCN46775_json/img.png train_data/labelme_json/DSCN46781_json/img.png train_data/labelme_json/DSCN46782_json/img.png train_data/labelme_json/DSCN46783_json/img.png train_data/labelme_json/DSCN46785_json/img.png train_data/labelme_json/DSCN46791_json/img.png train_data/labelme_json/DSCN46792_json/img.png train_data/labelme_json/DSCN46793_json/img.png train_data/labelme_json/DSCN46795_json/img.png train_data/labelme_json/DSCN46801_json/img.png train_data/labelme_json/DSCN46802_json/img.png train_data/labelme_json/DSCN46803_json/img.png train_data/labelme_json/DSCN46805_json/img.png train_data/labelme_json/DSCN46811_json/img.png train_data/labelme_json/DSCN46812_json/img.png train_data/labelme_json/DSCN46813_json/img.png train_data/labelme_json/DSCN46815_json/img.png train_data/labelme_json/DSCN46821_json/img.png train_data/labelme_json/DSCN46822_json/img.png train_data/labelme_json/DSCN46823_json/img.png train_data/labelme_json/DSCN46825_json/img.png train_data/labelme_json/DSCN46831_json/img.png train_data/labelme_json/DSCN46832_json/img.png train_data/labelme_json/DSCN46833_json/img.png train_data/labelme_json/DSCN46835_json/img.png train_data/labelme_json/DSCN46841_json/img.png train_data/labelme_json/DSCN46842_json/img.png train_data/labelme_json/DSCN46843_json/img.png train_data/labelme_json/DSCN46845_json/img.png train_data/labelme_json/DSCN46851_json/img.png train_data/labelme_json/DSCN46852_json/img.png train_data/labelme_json/DSCN46853_json/img.png train_data/labelme_json/DSCN46855_json/img.png train_data/labelme_json/DSCN46861_json/img.png train_data/labelme_json/DSCN46862_json/img.png train_data/labelme_json/DSCN46863_json/img.png train_data/labelme_json/DSCN46865_json/img.png train_data/labelme_json/DSCN46871_json/img.png train_data/labelme_json/DSCN46872_json/img.png train_data/labelme_json/DSCN46873_json/img.png train_data/labelme_json/DSCN46875_json/img.png train_data/labelme_json/DSCN46881_json/img.png train_data/labelme_json/DSCN46882_json/img.png train_data/labelme_json/DSCN46883_json/img.png train_data/labelme_json/DSCN46885_json/img.png train_data/labelme_json/DSCN46891_json/img.png train_data/labelme_json/DSCN46892_json/img.png train_data/labelme_json/DSCN46893_json/img.png train_data/labelme_json/DSCN46895_json/img.png train_data/labelme_json/DSCN46901_json/img.png train_data/labelme_json/DSCN46902_json/img.png train_data/labelme_json/DSCN46903_json/img.png train_data/labelme_json/DSCN46905_json/img.png train_data/labelme_json/DSCN46911_json/img.png train_data/labelme_json/DSCN46912_json/img.png train_data/labelme_json/DSCN46913_json/img.png train_data/labelme_json/DSCN46915_json/img.png train_data/labelme_json/DSCN46921_json/img.png train_data/labelme_json/DSCN46922_json/img.png train_data/labelme_json/DSCN46923_json/img.png train_data/labelme_json/DSCN46925_json/img.png train_data/labelme_json/DSCN46931_json/img.png train_data/labelme_json/DSCN46932_json/img.png train_data/labelme_json/DSCN46933_json/img.png train_data/labelme_json/DSCN46935_json/img.png train_data/labelme_json/DSCN46941_json/img.png train_data/labelme_json/DSCN46942_json/img.png train_data/labelme_json/DSCN46943_json/img.png train_data/labelme_json/DSCN46945_json/img.png train_data/labelme_json/DSCN46951_json/img.png train_data/labelme_json/DSCN46952_json/img.png train_data/labelme_json/DSCN46953_json/img.png train_data/labelme_json/DSCN46955_json/img.png train_data/labelme_json/DSCN46961_json/img.png train_data/labelme_json/DSCN46962_json/img.png train_data/labelme_json/DSCN46963_json/img.png train_data/labelme_json/DSCN46965_json/img.png train_data/labelme_json/DSCN46971_json/img.png train_data/labelme_json/DSCN46972_json/img.png train_data/labelme_json/DSCN46973_json/img.png train_data/labelme_json/DSCN46975_json/img.png train_data/labelme_json/DSCN46981_json/img.png train_data/labelme_json/DSCN46982_json/img.png train_data/labelme_json/DSCN46983_json/img.png train_data/labelme_json/DSCN46985_json/img.png train_data/labelme_json/DSCN46991_json/img.png train_data/labelme_json/DSCN46992_json/img.png train_data/labelme_json/DSCN46993_json/img.png train_data/labelme_json/DSCN46995_json/img.png train_data/labelme_json/DSCN47001_json/img.png train_data/labelme_json/DSCN47002_json/img.png train_data/labelme_json/DSCN47003_json/img.png train_data/labelme_json/DSCN47005_json/img.png train_data/labelme_json/DSCN47011_json/img.png train_data/labelme_json/DSCN47012_json/img.png train_data/labelme_json/DSCN47013_json/img.png train_data/labelme_json/DSCN47015_json/img.png train_data/labelme_json/DSCN47021_json/img.png train_data/labelme_json/DSCN47022_json/img.png train_data/labelme_json/DSCN47023_json/img.png train_data/labelme_json/DSCN47025_json/img.png train_data/labelme_json/DSCN47031_json/img.png train_data/labelme_json/DSCN47032_json/img.png train_data/labelme_json/DSCN47033_json/img.png train_data/labelme_json/DSCN47035_json/img.png train_data/labelme_json/DSCN47041_json/img.png train_data/labelme_json/DSCN47042_json/img.png train_data/labelme_json/DSCN47043_json/img.png train_data/labelme_json/DSCN47045_json/img.png train_data/labelme_json/DSCN47051_json/img.png train_data/labelme_json/DSCN47052_json/img.png train_data/labelme_json/DSCN47053_json/img.png train_data/labelme_json/DSCN47055_json/img.png train_data/labelme_json/DSCN47061_json/img.png train_data/labelme_json/DSCN47062_json/img.png train_data/labelme_json/DSCN47063_json/img.png train_data/labelme_json/DSCN47065_json/img.png train_data/labelme_json/DSCN47071_json/img.png train_data/labelme_json/DSCN47072_json/img.png train_data/labelme_json/DSCN47073_json/img.png train_data/labelme_json/DSCN47075_json/img.png train_data/labelme_json/DSCN47081_json/img.png train_data/labelme_json/DSCN47082_json/img.png train_data/labelme_json/DSCN47083_json/img.png train_data/labelme_json/DSCN47085_json/img.png train_data/labelme_json/DSCN47091_json/img.png train_data/labelme_json/DSCN47092_json/img.png train_data/labelme_json/DSCN47093_json/img.png train_data/labelme_json/DSCN47095_json/img.png train_data/labelme_json/DSCN47101_json/img.png train_data/labelme_json/DSCN47102_json/img.png train_data/labelme_json/DSCN47103_json/img.png train_data/labelme_json/DSCN47105_json/img.png train_data/labelme_json/DSCN47111_json/img.png train_data/labelme_json/DSCN47112_json/img.png train_data/labelme_json/DSCN47113_json/img.png train_data/labelme_json/DSCN47115_json/img.png train_data/labelme_json/DSCN47121_json/img.png train_data/labelme_json/DSCN47122_json/img.png train_data/labelme_json/DSCN47123_json/img.png train_data/labelme_json/DSCN47125_json/img.png train_data/labelme_json/DSCN47131_json/img.png train_data/labelme_json/DSCN47132_json/img.png train_data/labelme_json/DSCN47133_json/img.png train_data/labelme_json/DSCN47135_json/img.png train_data/labelme_json/DSCN47141_json/img.png train_data/labelme_json/DSCN47142_json/img.png train_data/labelme_json/DSCN47143_json/img.png train_data/labelme_json/DSCN47145_json/img.png train_data/labelme_json/DSCN47151_json/img.png train_data/labelme_json/DSCN47152_json/img.png train_data/labelme_json/DSCN47153_json/img.png train_data/labelme_json/DSCN47155_json/img.png train_data/labelme_json/DSCN47161_json/img.png train_data/labelme_json/DSCN47162_json/img.png train_data/labelme_json/DSCN47163_json/img.png train_data/labelme_json/DSCN47165_json/img.png train_data/labelme_json/DSCN47171_json/img.png train_data/labelme_json/DSCN47172_json/img.png train_data/labelme_json/DSCN47173_json/img.png train_data/labelme_json/DSCN47175_json/img.png train_data/labelme_json/DSCN47181_json/img.png train_data/labelme_json/DSCN47182_json/img.png train_data/labelme_json/DSCN47183_json/img.png train_data/labelme_json/DSCN47185_json/img.png train_data/labelme_json/DSCN47191_json/img.png train_data/labelme_json/DSCN47192_json/img.png train_data/labelme_json/DSCN47193_json/img.png train_data/labelme_json/DSCN47195_json/img.png train_data/labelme_json/DSCN47201_json/img.png train_data/labelme_json/DSCN47202_json/img.png train_data/labelme_json/DSCN47203_json/img.png train_data/labelme_json/DSCN47205_json/img.png train_data/labelme_json/DSCN47211_json/img.png train_data/labelme_json/DSCN47212_json/img.png train_data/labelme_json/DSCN47213_json/img.png train_data/labelme_json/DSCN47215_json/img.png train_data/labelme_json/DSCN47221_json/img.png train_data/labelme_json/DSCN47222_json/img.png train_data/labelme_json/DSCN47223_json/img.png train_data/labelme_json/DSCN47225_json/img.png train_data/labelme_json/DSCN47231_json/img.png train_data/labelme_json/DSCN47232_json/img.png train_data/labelme_json/DSCN47233_json/img.png train_data/labelme_json/DSCN47235_json/img.png train_data/labelme_json/DSCN47241_json/img.png train_data/labelme_json/DSCN47242_json/img.png train_data/labelme_json/DSCN47243_json/img.png train_data/labelme_json/DSCN47245_json/img.png train_data/labelme_json/DSCN47251_json/img.png train_data/labelme_json/DSCN47252_json/img.png train_data/labelme_json/DSCN47253_json/img.png train_data/labelme_json/DSCN47255_json/img.png train_data/labelme_json/DSCN47261_json/img.png train_data/labelme_json/DSCN47262_json/img.png train_data/labelme_json/DSCN47263_json/img.png train_data/labelme_json/DSCN47265_json/img.png train_data/labelme_json/DSCN47271_json/img.png train_data/labelme_json/DSCN47272_json/img.png train_data/labelme_json/DSCN47273_json/img.png train_data/labelme_json/DSCN47275_json/img.png train_data/labelme_json/DSCN47281_json/img.png train_data/labelme_json/DSCN47282_json/img.png train_data/labelme_json/DSCN47283_json/img.png train_data/labelme_json/DSCN47285_json/img.png train_data/labelme_json/DSCN47291_json/img.png train_data/labelme_json/DSCN47292_json/img.png train_data/labelme_json/DSCN47293_json/img.png train_data/labelme_json/DSCN47295_json/img.png train_data/labelme_json/DSCN47301_json/img.png train_data/labelme_json/DSCN47302_json/img.png train_data/labelme_json/DSCN47303_json/img.png train_data/labelme_json/DSCN47305_json/img.png train_data/labelme_json/DSCN47311_json/img.png train_data/labelme_json/DSCN47312_json/img.png train_data/labelme_json/DSCN47313_json/img.png train_data/labelme_json/DSCN47315_json/img.png train_data/labelme_json/DSCN47321_json/img.png train_data/labelme_json/DSCN47322_json/img.png train_data/labelme_json/DSCN47323_json/img.png train_data/labelme_json/DSCN47325_json/img.png train_data/labelme_json/DSCN47331_json/img.png train_data/labelme_json/DSCN47332_json/img.png train_data/labelme_json/DSCN47333_json/img.png train_data/labelme_json/DSCN47335_json/img.png train_data/labelme_json/DSCN47341_json/img.png train_data/labelme_json/DSCN47342_json/img.png train_data/labelme_json/DSCN47343_json/img.png train_data/labelme_json/DSCN47345_json/img.png train_data/labelme_json/DSCN47351_json/img.png train_data/labelme_json/DSCN47352_json/img.png train_data/labelme_json/DSCN47353_json/img.png train_data/labelme_json/DSCN47355_json/img.png train_data/labelme_json/DSCN47361_json/img.png train_data/labelme_json/DSCN47362_json/img.png train_data/labelme_json/DSCN47363_json/img.png train_data/labelme_json/DSCN47365_json/img.png train_data/labelme_json/DSCN47371_json/img.png train_data/labelme_json/DSCN47372_json/img.png train_data/labelme_json/DSCN47373_json/img.png train_data/labelme_json/DSCN47375_json/img.png train_data/labelme_json/DSCN47381_json/img.png train_data/labelme_json/DSCN47382_json/img.png train_data/labelme_json/DSCN47383_json/img.png train_data/labelme_json/DSCN47385_json/img.png train_data/labelme_json/DSCN47391_json/img.png train_data/labelme_json/DSCN47392_json/img.png train_data/labelme_json/DSCN47393_json/img.png train_data/labelme_json/DSCN47395_json/img.png train_data/labelme_json/DSCN47401_json/img.png train_data/labelme_json/DSCN47402_json/img.png train_data/labelme_json/DSCN47403_json/img.png train_data/labelme_json/DSCN47405_json/img.png train_data/labelme_json/DSCN47411_json/img.png train_data/labelme_json/DSCN47412_json/img.png train_data/labelme_json/DSCN47413_json/img.png train_data/labelme_json/DSCN47415_json/img.png train_data/labelme_json/DSCN47421_json/img.png train_data/labelme_json/DSCN47422_json/img.png train_data/labelme_json/DSCN47423_json/img.png train_data/labelme_json/DSCN47425_json/img.png train_data/labelme_json/DSCN47431_json/img.png train_data/labelme_json/DSCN47432_json/img.png train_data/labelme_json/DSCN47433_json/img.png train_data/labelme_json/DSCN47435_json/img.png train_data/labelme_json/DSCN47441_json/img.png train_data/labelme_json/DSCN47442_json/img.png train_data/labelme_json/DSCN47443_json/img.png train_data/labelme_json/DSCN47445_json/img.png train_data/labelme_json/DSCN47451_json/img.png train_data/labelme_json/DSCN47452_json/img.png train_data/labelme_json/DSCN47453_json/img.png train_data/labelme_json/DSCN47455_json/img.png train_data/labelme_json/DSCN47461_json/img.png train_data/labelme_json/DSCN47462_json/img.png train_data/labelme_json/DSCN47463_json/img.png train_data/labelme_json/DSCN47465_json/img.png train_data/labelme_json/DSCN47471_json/img.png train_data/labelme_json/DSCN47472_json/img.png train_data/labelme_json/DSCN47475_json/img.png train_data/labelme_json/DSCN47491_json/img.png train_data/labelme_json/DSCN47492_json/img.png train_data/labelme_json/DSCN47495_json/img.png train_data/labelme_json/DSCN47501_json/img.png train_data/labelme_json/DSCN47502_json/img.png train_data/labelme_json/DSCN47505_json/img.png train_data/labelme_json/DSCN47511_json/img.png train_data/labelme_json/DSCN47512_json/img.png train_data/labelme_json/DSCN47515_json/img.png train_data/labelme_json/DSCN47521_json/img.png train_data/labelme_json/DSCN47522_json/img.png train_data/labelme_json/DSCN47525_json/img.png train_data/labelme_json/DSCN47531_json/img.png train_data/labelme_json/DSCN47532_json/img.png train_data/labelme_json/DSCN47535_json/img.png train_data/labelme_json/DSCN47541_json/img.png train_data/labelme_json/DSCN47542_json/img.png train_data/labelme_json/DSCN47545_json/img.png train_data/labelme_json/DSCN47551_json/img.png train_data/labelme_json/DSCN47552_json/img.png train_data/labelme_json/DSCN47555_json/img.png train_data/labelme_json/DSCN47561_json/img.png train_data/labelme_json/DSCN47562_json/img.png train_data/labelme_json/DSCN47565_json/img.png train_data/labelme_json/DSCN47571_json/img.png train_data/labelme_json/DSCN47572_json/img.png train_data/labelme_json/DSCN47575_json/img.png train_data/labelme_json/DSCN47581_json/img.png train_data/labelme_json/DSCN47582_json/img.png train_data/labelme_json/DSCN47585_json/img.png train_data/labelme_json/DSCN47591_json/img.png train_data/labelme_json/DSCN47592_json/img.png train_data/labelme_json/DSCN47595_json/img.png train_data/labelme_json/DSCN47601_json/img.png train_data/labelme_json/DSCN47602_json/img.png train_data/labelme_json/DSCN47605_json/img.png train_data/labelme_json/DSCN47611_json/img.png train_data/labelme_json/DSCN47612_json/img.png train_data/labelme_json/DSCN47615_json/img.png train_data/labelme_json/DSCN47621_json/img.png train_data/labelme_json/DSCN47622_json/img.png train_data/labelme_json/DSCN47625_json/img.png train_data/labelme_json/DSCN47631_json/img.png train_data/labelme_json/DSCN47632_json/img.png train_data/labelme_json/DSCN47635_json/img.png train_data/labelme_json/DSCN47641_json/img.png train_data/labelme_json/DSCN47642_json/img.png train_data/labelme_json/DSCN47645_json/img.png train_data/labelme_json/DSCN47651_json/img.png train_data/labelme_json/DSCN47652_json/img.png train_data/labelme_json/DSCN47655_json/img.png train_data/labelme_json/DSCN47661_json/img.png train_data/labelme_json/DSCN47662_json/img.png train_data/labelme_json/DSCN47665_json/img.png train_data/labelme_json/DSCN47671_json/img.png train_data/labelme_json/DSCN47672_json/img.png train_data/labelme_json/DSCN47675_json/img.png train_data/labelme_json/DSCN47681_json/img.png train_data/labelme_json/DSCN47682_json/img.png train_data/labelme_json/DSCN47685_json/img.png train_data/labelme_json/DSCN46592_json/img.png train_data/labelme_json/DSCN46601_json/img.png train_data/labelme_json/DSCN46602_json/img.png train_data/labelme_json/DSCN46611_json/img.png train_data/labelme_json/DSCN46612_json/img.png train_data/labelme_json/DSCN46615_json/img.png train_data/labelme_json/DSCN46621_json/img.png
However, an error occurred after that:
Could you help me with this problem @Wahaha1314 PLEASE !!!
--------------------------------------------------------------------------- ValueError Traceback (most recent call last) <ipython-input-1-50b8c26e8d29> in <module> 214 # Create model in training mode 215 model = modellib.MaskRCNN(mode="training", config=config, --> 216 model_dir=MODEL_DIR) 217 218 # Which weights to start with? ~\Fish-characteristic-measurement\Complete code\mrcnn\model.py in init(self, mode, config, model_dir) 1830 self.model_dir = model_dir 1831 self.set_log_dir() -> 1832 self.keras_model = self.build(mode=mode, config=config) 1833 1834 def build(self, mode, config): ~\Fish-characteristic-measurement\Complete code\mrcnn\model.py in build(self, mode, config) 1927 anchors = np.broadcast_to(anchors, (config.BATCH_SIZE,) + anchors.shape) 1928 # A hack to get around Keras's bad support for constants -> 1929 anchors = KL.Lambda(lambda x: tf.Variable(anchors), name="anchors")(input_image) 1930 else: 1931 anchors = input_anchors ~\Anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py in call(self, *args, *kwargs) 920 not base_layer_utils.is_in_eager_or_tf_function()): 921 with auto_control_deps.AutomaticControlDependencies() as acd: --> 922 outputs = call_fn(cast_inputs, args, kwargs) 923 # Wrap Tensors in outputs in tf.identity to avoid 924 # circular dependencies. ~\Anaconda3\lib\site-packages\tensorflow\python\keras\layers\core.py in call(self, inputs, mask, training) 887 variable_scope.variable_creator_scope(_variable_creator): 888 result = self.function(inputs, kwargs) --> 889 self._check_variables(created_variables, tape.watched_variables()) 890 return result 891 ~\Anaconda3\lib\site-packages\tensorflow\python\keras\layers\core.py in _check_variables(self, created_variables, accessed_variables) 914 Variables.''' 915 ).format(name=self.name, variable_str=variable_str) --> 916 raise ValueError(error_str) 917 918 untracked_used_vars = [ ValueError: The following Variables were created within a Lambda layer (anchors) but are not tracked by said layer: <tf.Variable 'anchors/Variable:0' shape=(1, 261888, 4) dtype=float32> The layer cannot safely ensure proper Variable reuse across multiple calls, and consquently this behavior is disallowed for safety. Lambda layers are not well suited to stateful computation; instead, writing a subclassed Layer is the recommend way to define layers with Variables.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
morganaribeiro
Started by doing the right dataset training:
However, an error occurred after that:
~\Fish-characteristic-measurement\Complete code\mrcnn\model.py in init(self, mode, config, model_dir) 1830 self.model_dir = model_dir 1831 self.set_log_dir() -> 1832 self.keras_model = self.build(mode=mode, config=config) 1833 1834 def build(self, mode, config):
~\Fish-characteristic-measurement\Complete code\mrcnn\model.py in build(self, mode, config) 1927 anchors = np.broadcast_to(anchors, (config.BATCH_SIZE,) + anchors.shape) 1928 # A hack to get around Keras's bad support for constants -> 1929 anchors = KL.Lambda(lambda x: tf.Variable(anchors), name="anchors")(input_image) 1930 else: 1931 anchors = input_anchors
~\Anaconda3\lib\site-packages\tensorflow\python\keras\engine\base_layer.py in call(self, *args, *kwargs) 920 not base_layer_utils.is_in_eager_or_tf_function()): 921 with auto_control_deps.AutomaticControlDependencies() as acd: --> 922 outputs = call_fn(cast_inputs, args, **kwargs) 923 # Wrap Tensors in
outputsintf.identityto avoid 924 # circular dependencies.~\Anaconda3\lib\site-packages\tensorflow\python\keras\layers\core.py in call(self, inputs, mask, training) 887 variable_scope.variable_creator_scope(_variable_creator): 888 result = self.function(inputs, **kwargs) --> 889 self._check_variables(created_variables, tape.watched_variables()) 890 return result 891
~\Anaconda3\lib\site-packages\tensorflow\python\keras\layers\core.py in _check_variables(self, created_variables, accessed_variables) 914 Variables.''' 915 ).format(name=self.name, variable_str=variable_str) --> 916 raise ValueError(error_str) 917 918 untracked_used_vars = [
ValueError: The following Variables were created within a Lambda layer (anchors) but are not tracked by said layer: <tf.Variable 'anchors/Variable:0' shape=(1, 261888, 4) dtype=float32> The layer cannot safely ensure proper Variable reuse across multiple calls, and consquently this behavior is disallowed for safety. Lambda layers are not well suited to stateful computation; instead, writing a subclassed Layer is the recommend way to define layers with Variables.