time python ./tools/test_net.py --imdb plums_day_test --model /media/jasper/bigData/FasterRCNN-Output/Results/DayResults/vgg16_faster_rcnn_iter_14500.ckpt --cfg experiments/cfgs/vgg16.yml --net vgg16 --set ANCHOR_SCALES '[8,16,32]' ANCHOR_RATIOS '[0.5,1,2]'
Called with args:
Namespace(cfg_file='experiments/cfgs/vgg16.yml', comp_mode=False, imdb_name='plums_day_test', max_per_image=100, model='/media/jasper/bigData/FasterRCNN-Output/Results/DayResults/vgg16_faster_rcnn_iter_14500.ckpt', net='vgg16', set_cfgs=['ANCHOR_SCALES', '[8,16,32]', 'ANCHOR_RATIOS', '[0.5,1,2]'], tag='')
/home/jasper/git/tf-faster-rcnn/tools/../lib/model/config.py:362: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
  yaml_cfg = edict(yaml.load(f))
Using config:
{'ANCHOR_RATIOS': [0.5, 1, 2],
 'ANCHOR_SCALES': [8, 16, 32],
 'DATA_DIR': '/home/jasper/git/tf-faster-rcnn/data',
 'EXP_DIR': 'vgg16',
 '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/jasper/git/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': True,
           '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': 250,
           'SNAPSHOT_KEPT': 150,
           'SNAPSHOT_PREFIX': 'vgg16_faster_rcnn',
           'STEPSIZE': [10000],
           'SUMMARY_INTERVAL': 180,
           'TRUNCATED': False,
           'USE_ALL_GT': True,
           'USE_FLIPPED': True,
           'USE_GT': False,
           'WEIGHT_DECAY': 0.0001},
 'USE_E2E_TF': True,
 'USE_GPU_NMS': True}
2020-07-14 15:58:17.983868: 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.
2020-07-14 15:58:17.983882: 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.
2020-07-14 15:58:17.983888: 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.
2020-07-14 15:58:17.983892: 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.
2020-07-14 15:58:17.983897: 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.
2020-07-14 15:58:18.066661: 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
2020-07-14 15:58:18.066913: I tensorflow/core/common_runtime/gpu/gpu_device.cc:940] Found device 0 with properties: 
name: GeForce GTX 1080 Ti
major: 6 minor: 1 memoryClockRate (GHz) 1.721
pciBusID 0000:01:00.0
Total memory: 10.91GiB
Free memory: 9.89GiB
2020-07-14 15:58:18.066927: I tensorflow/core/common_runtime/gpu/gpu_device.cc:961] DMA: 0 
2020-07-14 15:58:18.066932: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] 0:   Y 
2020-07-14 15:58:18.066941: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:01:00.0)
Loading model check point from /media/jasper/bigData/FasterRCNN-Output/Results/DayResults/vgg16_faster_rcnn_iter_14500.ckpt
Loaded.
im_detect: 1/87 1.042s 0.001s
im_detect: 2/87 0.574s 0.001s
im_detect: 3/87 0.421s 0.001s
im_detect: 4/87 0.342s 0.001s
im_detect: 5/87 0.298s 0.001s
im_detect: 6/87 0.269s 0.001s
im_detect: 7/87 0.247s 0.001s
im_detect: 8/87 0.233s 0.001s
im_detect: 9/87 0.219s 0.001s
im_detect: 10/87 0.209s 0.001s
im_detect: 11/87 0.201s 0.001s
im_detect: 12/87 0.193s 0.001s
im_detect: 13/87 0.187s 0.001s
im_detect: 14/87 0.182s 0.001s
im_detect: 15/87 0.177s 0.001s
im_detect: 16/87 0.173s 0.001s
im_detect: 17/87 0.168s 0.001s
im_detect: 18/87 0.165s 0.001s
im_detect: 19/87 0.163s 0.001s
im_detect: 20/87 0.160s 0.001s
im_detect: 21/87 0.159s 0.001s
im_detect: 22/87 0.157s 0.001s
im_detect: 23/87 0.156s 0.001s
im_detect: 24/87 0.154s 0.001s
im_detect: 25/87 0.153s 0.001s
im_detect: 26/87 0.152s 0.001s
im_detect: 27/87 0.151s 0.001s
im_detect: 28/87 0.150s 0.001s
im_detect: 29/87 0.149s 0.001s
im_detect: 30/87 0.148s 0.001s
im_detect: 31/87 0.146s 0.001s
im_detect: 32/87 0.145s 0.001s
im_detect: 33/87 0.145s 0.001s
im_detect: 34/87 0.144s 0.001s
im_detect: 35/87 0.144s 0.001s
im_detect: 36/87 0.143s 0.001s
im_detect: 37/87 0.143s 0.001s
im_detect: 38/87 0.142s 0.001s
im_detect: 39/87 0.141s 0.001s
im_detect: 40/87 0.141s 0.001s
im_detect: 41/87 0.141s 0.001s
im_detect: 42/87 0.140s 0.001s
im_detect: 43/87 0.139s 0.001s
im_detect: 44/87 0.138s 0.001s
im_detect: 45/87 0.138s 0.001s
im_detect: 46/87 0.138s 0.001s
im_detect: 47/87 0.137s 0.001s
im_detect: 48/87 0.137s 0.001s
im_detect: 49/87 0.137s 0.001s
im_detect: 50/87 0.137s 0.001s
im_detect: 51/87 0.136s 0.001s
im_detect: 52/87 0.136s 0.001s
im_detect: 53/87 0.136s 0.001s
im_detect: 54/87 0.135s 0.001s
im_detect: 55/87 0.135s 0.001s
im_detect: 56/87 0.135s 0.001s
im_detect: 57/87 0.134s 0.001s
im_detect: 58/87 0.134s 0.001s
im_detect: 59/87 0.134s 0.001s
im_detect: 60/87 0.134s 0.001s
im_detect: 61/87 0.133s 0.001s
im_detect: 62/87 0.133s 0.001s
im_detect: 63/87 0.133s 0.001s
im_detect: 64/87 0.133s 0.001s
im_detect: 65/87 0.133s 0.001s
im_detect: 66/87 0.132s 0.001s
im_detect: 67/87 0.132s 0.001s
im_detect: 68/87 0.132s 0.001s
im_detect: 69/87 0.132s 0.001s
im_detect: 70/87 0.132s 0.001s
im_detect: 71/87 0.131s 0.001s
im_detect: 72/87 0.131s 0.001s
im_detect: 73/87 0.131s 0.001s
im_detect: 74/87 0.131s 0.001s
im_detect: 75/87 0.131s 0.001s
im_detect: 76/87 0.130s 0.001s
im_detect: 77/87 0.130s 0.001s
im_detect: 78/87 0.130s 0.001s
im_detect: 79/87 0.130s 0.001s
im_detect: 80/87 0.129s 0.001s
im_detect: 81/87 0.129s 0.001s
im_detect: 82/87 0.129s 0.001s
im_detect: 83/87 0.129s 0.001s
im_detect: 84/87 0.129s 0.001s
im_detect: 85/87 0.129s 0.001s
im_detect: 86/87 0.129s 0.001s
im_detect: 87/87 0.129s 0.001s
Detection saved to pickle

real    0m13.617s
user    0m11.555s
sys     0m1.489s
(venv2.7) jasper@jasper-Ubuntu16-Desktop:~/git/tf-faster-rcnn$ ^C
(venv2.7) jasper@jasper-Ubuntu16-Desktop:~/git/tf-faster-rcnn$ CUDA_VISIBLE_DEVICES=0
(venv2.7) jasper@jasper-Ubuntu16-Desktop:~/git/tf-faster-rcnn$ 
(venv2.7) jasper@jasper-Ubuntu16-Desktop:~/git/tf-faster-rcnn$ time python ./tools/test_net.py --imdb plums_night_test --model /media/jasper/bigData/FasterRCNN-Output/Results/NightResults/vgg16_faster_rcnn_iter_28500.ckpt --cfg experiments/cfgs/vgg16.yml --net vgg16 --set ANCHOR_SCALES '[8,16,32]' ANCHOR_RATIOS '[0.5,1,2]'
Called with args:
Namespace(cfg_file='experiments/cfgs/vgg16.yml', comp_mode=False, imdb_name='plums_night_test', max_per_image=100, model='/media/jasper/bigData/FasterRCNN-Output/Results/NightResults/vgg16_faster_rcnn_iter_28500.ckpt', net='vgg16', set_cfgs=['ANCHOR_SCALES', '[8,16,32]', 'ANCHOR_RATIOS', '[0.5,1,2]'], tag='')
/home/jasper/git/tf-faster-rcnn/tools/../lib/model/config.py:362: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
  yaml_cfg = edict(yaml.load(f))
Using config:
{'ANCHOR_RATIOS': [0.5, 1, 2],
 'ANCHOR_SCALES': [8, 16, 32],
 'DATA_DIR': '/home/jasper/git/tf-faster-rcnn/data',
 'EXP_DIR': 'vgg16',
 '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/jasper/git/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': True,
           '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': 250,
           'SNAPSHOT_KEPT': 150,
           'SNAPSHOT_PREFIX': 'vgg16_faster_rcnn',
           'STEPSIZE': [10000],
           'SUMMARY_INTERVAL': 180,
           'TRUNCATED': False,
           'USE_ALL_GT': True,
           'USE_FLIPPED': True,
           'USE_GT': False,
           'WEIGHT_DECAY': 0.0001},
 'USE_E2E_TF': True,
 'USE_GPU_NMS': True}
2020-07-14 16:12:19.589744: 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.
2020-07-14 16:12:19.589760: 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.
2020-07-14 16:12:19.589765: 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.
2020-07-14 16:12:19.589769: 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.
2020-07-14 16:12:19.589773: 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.
2020-07-14 16:12:19.697180: 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
2020-07-14 16:12:19.69