tf-faster-rcnn icon indicating copy to clipboard operation
tf-faster-rcnn copied to clipboard

Nan in summary histogram when train Faster R-CNN on my own dataset?

Open weisq2691 opened this issue 7 years ago • 4 comments

  • set -e
  • export PYTHONUNBUFFERED=True
  • PYTHONUNBUFFERED=True
  • GPU_ID=0
  • DATASET=pascal_voc
  • NET=res101
  • array=($@)
  • len=3
  • EXTRA_ARGS=
  • EXTRA_ARGS_SLUG=
  • case ${DATASET} in
  • TRAIN_IMDB=voc_2007_trainval
  • TEST_IMDB=voc_2007_test
  • STEPSIZE='[50000]'
  • ITERS=70000
  • ANCHORS='[8,16,32]'
  • RATIOS='[0.5,1,2]' ++ date +%Y-%m-%d_%H-%M-%S
  • LOG=experiments/logs/res101_voc_2007_trainval__res101.txt.2018-04-01_14-44-43
  • exec ++ tee -a experiments/logs/res101_voc_2007_trainval__res101.txt.2018-04-01_14-44-43
  • echo Logging output to experiments/logs/res101_voc_2007_trainval__res101.txt.2018-04-01_14-44-43 Logging output to experiments/logs/res101_voc_2007_trainval__res101.txt.2018-04-01_14-44-43
  • set +x
  • '[' '!' -f output/res101/voc_2007_trainval/default/res101_faster_rcnn_iter_70000.ckpt.index ']'
  • [[ ! -z '' ]]
  • CUDA_VISIBLE_DEVICES=0
  • time python ./tools/trainval_net.py --weight data/imagenet_weights/res101.ckpt --imdb voc_2007_trainval --imdbval voc_2007_test --iters 70000 --cfg experiments/cfgs/res101.yml --net res101 --set ANCHOR_SCALES '[8,16,32]' ANCHOR_RATIOS '[0.5,1,2]' TRAIN.STEPSIZE '[50000]' Called with args: Namespace(cfg_file='experiments/cfgs/res101.yml', imdb_name='voc_2007_trainval', imdbval_name='voc_2007_test', max_iters=70000, net='res101', set_cfgs=['ANCHOR_SCALES', '[8,16,32]', 'ANCHOR_RATIOS', '[0.5,1,2]', 'TRAIN.STEPSIZE', '[50000]'], tag=None, weight='data/imagenet_weights/res101.ckpt') Using config: {'ANCHOR_RATIOS': [0.5, 1, 2], 'ANCHOR_SCALES': [8, 16, 32], 'DATA_DIR': '/home/w/tf-faster-rcnn/data', 'EXP_DIR': 'res101', 'MATLAB': 'matlab', 'MOBILENET': {'DEPTH_MULTIPLIER': 1.0, 'FIXED_LAYERS': 5, 'REGU_DEPTH': False, 'WEIGHT_DECAY': 4e-05}, 'PIXEL_MEANS': array([[[102.9801, 115.9465, 122.7717]]]), 'POOLING_MODE': 'crop', 'POOLING_SIZE': 7, 'RESNET': {'FIXED_BLOCKS': 1, 'MAX_POOL': False}, 'RNG_SEED': 3, 'ROOT_DIR': '/home/w/tf-faster-rcnn', 'RPN_CHANNELS': 512, 'TEST': {'BBOX_REG': True, 'HAS_RPN': True, 'MAX_SIZE': 1000, 'MODE': 'nms', 'NMS': 0.3, 'PROPOSAL_METHOD': 'gt', 'RPN_NMS_THRESH': 0.7, 'RPN_POST_NMS_TOP_N': 300, 'RPN_PRE_NMS_TOP_N': 6000, 'RPN_TOP_N': 5000, 'SCALES': [600], 'SVM': False}, 'TRAIN': {'ASPECT_GROUPING': False, 'BATCH_SIZE': 256, 'BBOX_INSIDE_WEIGHTS': [1.0, 1.0, 1.0, 1.0], 'BBOX_NORMALIZE_MEANS': [0.0, 0.0, 0.0, 0.0], 'BBOX_NORMALIZE_STDS': [0.1, 0.1, 0.2, 0.2], 'BBOX_NORMALIZE_TARGETS': True, 'BBOX_NORMALIZE_TARGETS_PRECOMPUTED': True, 'BBOX_REG': True, 'BBOX_THRESH': 0.5, 'BG_THRESH_HI': 0.5, 'BG_THRESH_LO': 0.0, 'BIAS_DECAY': False, 'DISPLAY': 20, 'DOUBLE_BIAS': False, 'FG_FRACTION': 0.25, 'FG_THRESH': 0.5, 'GAMMA': 0.1, 'HAS_RPN': True, 'IMS_PER_BATCH': 1, 'LEARNING_RATE': 0.001, 'MAX_SIZE': 1000, 'MOMENTUM': 0.9, 'PROPOSAL_METHOD': 'gt', 'RPN_BATCHSIZE': 256, 'RPN_BBOX_INSIDE_WEIGHTS': [1.0, 1.0, 1.0, 1.0], 'RPN_CLOBBER_POSITIVES': False, 'RPN_FG_FRACTION': 0.5, 'RPN_NEGATIVE_OVERLAP': 0.3, 'RPN_NMS_THRESH': 0.7, 'RPN_POSITIVE_OVERLAP': 0.7, 'RPN_POSITIVE_WEIGHT': -1.0, 'RPN_POST_NMS_TOP_N': 2000, 'RPN_PRE_NMS_TOP_N': 12000, 'SCALES': [600], 'SNAPSHOT_ITERS': 5000, 'SNAPSHOT_KEPT': 3, 'SNAPSHOT_PREFIX': 'res101_faster_rcnn', 'STEPSIZE': [50000], 'SUMMARY_INTERVAL': 180, 'TRUNCATED': False, 'USE_ALL_GT': True, 'USE_FLIPPED': True, 'USE_GT': False, 'WEIGHT_DECAY': 0.0001}, 'USE_GPU_NMS': True} Loaded dataset voc_2007_trainval for training Set proposal method: gt Appending horizontally-flipped training examples... voc_2007_trainval gt roidb loaded from /home/w/tf-faster-rcnn/data/cache/voc_2007_trainval_gt_roidb.pkl done Preparing training data... done 10176 roidb entries Output will be saved to /home/w/tf-faster-rcnn/output/res101/voc_2007_trainval/default TensorFlow summaries will be saved to /home/w/tf-faster-rcnn/tensorboard/res101/voc_2007_trainval/default Loaded dataset voc_2007_test for training Set proposal method: gt Preparing training data... voc_2007_test gt roidb loaded from /home/w/tf-faster-rcnn/data/cache/voc_2007_test_gt_roidb.pkl done 1697 validation roidb entries Filtered 0 roidb entries: 10176 -> 10176 Filtered 0 roidb entries: 1697 -> 1697 2018-04-01 14:44:49.674559: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations. 2018-04-01 14:44:49.674578: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations. 2018-04-01 14:44:49.674583: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations. 2018-04-01 14:44:49.674586: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations. 2018-04-01 14:44:49.674590: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations. 2018-04-01 14:44:49.767181: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:893] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2018-04-01 14:44:49.767466: I tensorflow/core/common_runtime/gpu/gpu_device.cc:940] Found device 0 with properties: name: GeForce GTX 1060 6GB major: 6 minor: 1 memoryClockRate (GHz) 1.7085 pciBusID 0000:01:00.0 Total memory: 5.93GiB Free memory: 5.64GiB 2018-04-01 14:44:49.767480: I tensorflow/core/common_runtime/gpu/gpu_device.cc:961] DMA: 0 2018-04-01 14:44:49.767499: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] 0: Y 2018-04-01 14:44:49.767509: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1060 6GB, pci bus id: 0000:01:00.0) Solving... /home/w/.local/lib/python2.7/site-packages/tensorflow/python/ops/gradients_impl.py:93: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory. "Converting sparse IndexedSlices to a dense Tensor of unknown shape. " Loading initial model weights from data/imagenet_weights/res101.ckpt Variables restored: resnet_v1_101/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/shortcut/weights:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/shortcut/BatchNorm/beta:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/shortcut/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/shortcut/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/shortcut/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block1/unit_1/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block1/unit_2/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block1/unit_2/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block1/unit_2/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block1/unit_2/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block1/unit_2/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block1/unit_2/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block1/unit_2/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block1/unit_2/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block1/unit_2/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block1/unit_2/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block1/unit_2/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block1/unit_2/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block1/unit_2/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block1/unit_2/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block1/unit_2/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block1/unit_3/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block1/unit_3/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block1/unit_3/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block1/unit_3/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block1/unit_3/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block1/unit_3/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block1/unit_3/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block1/unit_3/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block1/unit_3/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block1/unit_3/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block1/unit_3/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block1/unit_3/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block1/unit_3/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block1/unit_3/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block1/unit_3/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/shortcut/weights:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/shortcut/BatchNorm/beta:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/shortcut/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/shortcut/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/shortcut/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block2/unit_1/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block2/unit_2/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block2/unit_2/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block2/unit_2/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block2/unit_2/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block2/unit_2/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block2/unit_2/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block2/unit_2/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block2/unit_2/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block2/unit_2/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block2/unit_2/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block2/unit_2/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block2/unit_2/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block2/unit_2/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block2/unit_2/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block2/unit_2/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block2/unit_3/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block2/unit_3/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block2/unit_3/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block2/unit_3/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block2/unit_3/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block2/unit_3/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block2/unit_3/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block2/unit_3/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block2/unit_3/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block2/unit_3/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block2/unit_3/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block2/unit_3/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block2/unit_3/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block2/unit_3/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block2/unit_3/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block2/unit_4/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block2/unit_4/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block2/unit_4/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block2/unit_4/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block2/unit_4/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block2/unit_4/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block2/unit_4/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block2/unit_4/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block2/unit_4/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block2/unit_4/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block2/unit_4/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block2/unit_4/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block2/unit_4/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block2/unit_4/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block2/unit_4/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/shortcut/weights:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/shortcut/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/shortcut/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/shortcut/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/shortcut/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_1/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_2/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_2/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_2/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_2/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_2/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_2/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_2/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_2/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_2/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_2/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_2/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_2/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_2/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_2/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_2/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_3/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_3/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_3/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_3/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_3/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_3/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_3/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_3/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_3/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_3/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_3/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_3/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_3/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_3/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_3/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_4/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_4/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_4/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_4/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_4/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_4/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_4/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_4/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_4/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_4/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_4/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_4/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_4/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_4/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_4/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_5/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_5/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_5/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_5/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_5/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_5/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_5/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_5/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_5/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_5/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_5/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_5/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_5/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_5/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_5/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_6/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_6/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_6/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_6/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_6/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_6/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_6/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_6/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_6/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_6/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_6/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_6/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_6/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_6/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_6/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_7/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_7/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_7/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_7/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_7/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_7/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_7/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_7/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_7/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_7/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_7/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_7/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_7/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_7/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_7/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_8/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_8/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_8/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_8/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_8/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_8/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_8/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_8/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_8/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_8/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_8/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_8/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_8/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_8/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_8/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_9/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_9/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_9/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_9/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_9/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_9/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_9/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_9/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_9/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_9/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_9/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_9/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_9/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_9/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_9/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_10/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_10/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_10/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_10/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_10/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_10/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_10/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_10/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_10/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_10/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_10/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_10/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_10/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_10/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_10/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_11/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_11/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_11/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_11/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_11/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_11/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_11/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_11/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_11/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_11/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_11/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_11/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_11/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_11/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_11/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_12/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_12/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_12/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_12/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_12/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_12/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_12/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_12/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_12/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_12/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_12/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_13/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_13/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_13/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_13/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_13/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_13/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_13/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_13/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_13/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_13/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_13/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_13/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_13/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_13/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_13/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_14/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_14/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_14/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_14/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_14/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_14/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_14/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_14/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_14/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_14/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_14/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_14/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_14/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_14/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_14/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_15/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_15/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_15/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_15/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_15/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_15/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_15/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_15/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_15/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_15/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_15/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_15/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_15/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_15/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_15/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_16/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_16/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_16/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_16/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_16/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_16/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_16/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_16/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_16/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_16/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_16/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_16/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_16/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_16/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_16/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_17/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_17/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_17/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_17/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_17/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_17/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_17/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_17/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_17/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_17/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_17/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_17/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_17/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_17/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_17/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_18/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_18/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_18/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_18/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_18/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_18/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_18/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_18/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_18/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_18/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_18/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_18/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_18/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_18/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_18/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_19/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_19/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_19/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_19/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_19/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_19/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_19/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_19/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_19/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_19/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_19/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_19/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_19/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_19/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_19/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_20/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_20/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_20/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_20/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_20/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_20/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_20/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_20/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_20/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_20/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_20/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_20/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_20/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_20/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_20/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_21/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_21/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_21/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_21/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_21/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_21/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_21/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_21/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_21/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_21/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_21/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_21/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_21/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_21/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_21/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_22/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_22/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_22/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_22/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_22/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_22/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_22/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_22/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_22/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_22/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_22/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_22/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_22/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_22/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_22/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_23/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block3/unit_23/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_23/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_23/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_23/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_23/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block3/unit_23/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_23/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_23/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_23/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block3/unit_23/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block3/unit_23/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block3/unit_23/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block3/unit_23/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block3/unit_23/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/shortcut/weights:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/shortcut/BatchNorm/beta:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/shortcut/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/shortcut/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/shortcut/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block4/unit_1/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block4/unit_2/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block4/unit_2/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block4/unit_2/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block4/unit_2/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block4/unit_2/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block4/unit_2/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block4/unit_2/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block4/unit_2/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block4/unit_2/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block4/unit_2/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block4/unit_2/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block4/unit_2/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block4/unit_2/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block4/unit_2/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block4/unit_2/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block4/unit_3/bottleneck_v1/conv1/weights:0 Variables restored: resnet_v1_101/block4/unit_3/bottleneck_v1/conv1/BatchNorm/beta:0 Variables restored: resnet_v1_101/block4/unit_3/bottleneck_v1/conv1/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block4/unit_3/bottleneck_v1/conv1/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block4/unit_3/bottleneck_v1/conv1/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block4/unit_3/bottleneck_v1/conv2/weights:0 Variables restored: resnet_v1_101/block4/unit_3/bottleneck_v1/conv2/BatchNorm/beta:0 Variables restored: resnet_v1_101/block4/unit_3/bottleneck_v1/conv2/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block4/unit_3/bottleneck_v1/conv2/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block4/unit_3/bottleneck_v1/conv2/BatchNorm/moving_variance:0 Variables restored: resnet_v1_101/block4/unit_3/bottleneck_v1/conv3/weights:0 Variables restored: resnet_v1_101/block4/unit_3/bottleneck_v1/conv3/BatchNorm/beta:0 Variables restored: resnet_v1_101/block4/unit_3/bottleneck_v1/conv3/BatchNorm/gamma:0 Variables restored: resnet_v1_101/block4/unit_3/bottleneck_v1/conv3/BatchNorm/moving_mean:0 Variables restored: resnet_v1_101/block4/unit_3/bottleneck_v1/conv3/BatchNorm/moving_variance:0 Loaded. Fix Resnet V1 layers.. Fixed. /home/w/tf-faster-rcnn/tools/../lib/model/bbox_transform.py:27: RuntimeWarning: invalid value encountered in log targets_dw = np.log(gt_widths / ex_widths) 2018-04-01 14:45:01.170171: W tensorflow/core/framework/op_kernel.cc:1158] Invalid argument: Nan in summary histogram for: SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores [[Node: SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores/tag, resnet_v1_101_3/anchor/anchor_target:1)]] 2018-04-01 14:45:01.170211: W tensorflow/core/framework/op_kernel.cc:1158] Invalid argument: Nan in summary histogram for: SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores [[Node: SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores/tag, resnet_v1_101_3/anchor/anchor_target:1)]] 2018-04-01 14:45:01.170225: W tensorflow/core/framework/op_kernel.cc:1158] Invalid argument: Nan in summary histogram for: SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores [[Node: SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores/tag, resnet_v1_101_3/anchor/anchor_target:1)]] 2018-04-01 14:45:01.352346: W tensorflow/core/framework/op_kernel.cc:1158] Invalid argument: Nan in summary histogram for: SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores [[Node: SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores/tag, resnet_v1_101_3/anchor/anchor_target:1)]] 2018-04-01 14:45:01.352365: W tensorflow/core/framework/op_kernel.cc:1158] Invalid argument: Nan in summary histogram for: SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores [[Node: SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores/tag, resnet_v1_101_3/anchor/anchor_target:1)]] Traceback (most recent call last): File "./tools/trainval_net.py", line 139, in max_iters=args.max_iters) File "/home/w/tf-faster-rcnn/tools/../lib/model/train_val.py", line 377, in train_net sw.train_model(sess, max_iters) File "/home/w/tf-faster-rcnn/tools/../lib/model/train_val.py", line 284, in train_model self.net.train_step_with_summary(sess, blobs, train_op) File "/home/w/tf-faster-rcnn/tools/../lib/nets/network.py", line 490, in train_step_with_summary feed_dict=feed_dict) File "/home/w/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 789, in run run_metadata_ptr) File "/home/w/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 997, in _run feed_dict_string, options, run_metadata) File "/home/w/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1132, in _do_run target_list, options, run_metadata) File "/home/w/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1152, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.InvalidArgumentError: Nan in summary histogram for: SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores [[Node: SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores/tag, resnet_v1_101_3/anchor/anchor_target:1)]] [[Node: resnet_v1_101_3/rpn_rois/proposal_target/_1403 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_7092_resnet_v1_101_3/rpn_rois/proposal_target", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"]]

Caused by op u'SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores', defined at: File "./tools/trainval_net.py", line 139, in max_iters=args.max_iters) File "/home/w/tf-faster-rcnn/tools/../lib/model/train_val.py", line 377, in train_net sw.train_model(sess, max_iters) File "/home/w/tf-faster-rcnn/tools/../lib/model/train_val.py", line 248, in train_model lr, train_op = self.construct_graph(sess) File "/home/w/tf-faster-rcnn/tools/../lib/model/train_val.py", line 123, in construct_graph anchor_ratios=cfg.ANCHOR_RATIOS) File "/home/w/tf-faster-rcnn/tools/../lib/nets/network.py", line 423, in create_architecture self._add_score_summary(key, var) File "/home/w/tf-faster-rcnn/tools/../lib/nets/network.py", line 63, in _add_score_summary tf.summary.histogram('SCORE/' + tensor.op.name + '/' + key + '/scores', tensor) File "/home/w/.local/lib/python2.7/site-packages/tensorflow/python/summary/summary.py", line 221, in histogram tag=scope.rstrip('/'), values=values, name=scope) File "/home/w/.local/lib/python2.7/site-packages/tensorflow/python/ops/gen_logging_ops.py", line 131, in _histogram_summary name=name) File "/home/w/.local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op op_def=op_def) File "/home/w/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2506, in create_op original_op=self._default_original_op, op_def=op_def) File "/home/w/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1269, in init self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): Nan in summary histogram for: SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores [[Node: SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores = HistogramSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](SCORE/resnet_v1_101_3/anchor/anchor_target/rpn_bbox_targets/scores/tag, resnet_v1_101_3/anchor/anchor_target:1)]] [[Node: resnet_v1_101_3/rpn_rois/proposal_target/_1403 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/gpu:0", send_device="/job:localhost/replica:0/task:0/cpu:0", send_device_incarnation=1, tensor_name="edge_7092_resnet_v1_101_3/rpn_rois/proposal_target", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"]]

Command exited with non-zero status 1 19.26user 1.47system 0:18.07elapsed 114%CPU (0avgtext+0avgdata 1779808maxresident)k 0inputs+15568outputs (0major+598802minor)pagefaults 0swaps

weisq2691 avatar Apr 01 '18 06:04 weisq2691

weisq2691 , I have the same error! Have you found the solution?

andytung2019 avatar Jul 20 '18 22:07 andytung2019

weisq2691 , I have the same error! Have you found the solution?

chanyixialex avatar Aug 06 '18 17:08 chanyixialex

I have the same error! Have you found the solution?

jplnasa5 avatar Nov 21 '18 05:11 jplnasa5

I have the same error! Have you found the solution ? i have to try run my own dataset , after some iterations i am getting same problem , please help me to solve that problem

devendraswamy avatar Feb 07 '20 10:02 devendraswamy