Open tobymu opened 6 years ago
(tensorflow_py3.5_tf1.9) aita@aita:~/AITA2/01Visual/19FaceID/chenyiyi/Mask_RCNN-master/mask_rcnn_example_demo$ python demo.py ROOT_DIR: /home/aita/AITA2/01Visual/19FaceID/chenyiyi/Mask_RCNN-master Using TensorFlow backend. COCO_MODEL_PATH /home/aita/AITA2/01Visual/19FaceID/chenyiyi/Mask_RCNN-master/mask_rcnn_coco.h5 IMAGE_DIR /home/aita/AITA2/01Visual/19FaceID/chenyiyi/Mask_RCNN-master/images 2018-09-17 20:48:30.754146: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2018-09-17 20:48:30.930634: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1392] Found device 0 with properties: name: GeForce GTX 1080 major: 6 minor: 1 memoryClockRate(GHz): 1.7335 pciBusID: 0000:03:00.0 totalMemory: 7.92GiB freeMemory: 7.58GiB 2018-09-17 20:48:30.930680: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1471] Adding visible gpu devices: 0 2018-09-17 20:48:31.132087: I tensorflow/core/common_runtime/gpu/gpu_device.cc:952] Device interconnect StreamExecutor with strength 1 edge matrix: 2018-09-17 20:48:31.132120: I tensorflow/core/common_runtime/gpu/gpu_device.cc:958] 0 2018-09-17 20:48:31.132126: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] 0: N 2018-09-17 20:48:31.132332: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1084] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 7317 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1080, pci bus id: 0000:03:00.0, compute capability: 6.1) ['8829708882_48f263491e_z.jpg', '3132016470_c27baa00e8_z.jpg', '2516944023_d00345997d_z.jpg', '8433365521_9252889f9a_z.jpg', '8053677163_d4c8f416be_z.jpg', '6821351586_59aa0dc110_z.jpg', '1045023827_4ec3e8ba5c_z.jpg', '25691390_f9944f61b5_z.jpg', '3878153025_8fde829928_z.jpg', '3651581213_f81963d1dd_z.jpg', '6584515005_fce9cec486_z.jpg', '8699757338_c3941051b6_z.jpg', '9118579087_f9ffa19e63_z.jpg', '8734543718_37f6b8bd45_z.jpg', '3800883468_12af3c0b50_z.jpg', '3862500489_6fd195d183_z.jpg', '262985539_1709e54576_z.jpg', '7933423348_c30bd9bd4e_z.jpg', '7581246086_cf7bbb7255_z.jpg', '3627527276_6fe8cd9bfe_z.jpg', '4782628554_668bc31826_z.jpg', '8512296263_5fc5458e20_z.jpg', '9247489789_132c0d534a_z.jpg', '5951960966_d4e1cda5d0_z.jpg', '2502287818_41e4b0c4fb_z.jpg', '12283150_12d37e6389_z.jpg', '4410436637_7b0ca36ee7_z.jpg', '2383514521_1fc8d7b0de_z.jpg', '8239308689_efa6c11b08_z.jpg'] Processing 1 images image shape: (491, 640, 3) min: 0.00000 max: 255.00000 uint8 molded_images shape: (1, 1024, 1024, 3) min: -123.70000 max: 151.10000 float64 image_metas shape: (1, 93) min: 0.00000 max: 1024.00000 float64 anchors shape: (1, 261888, 4) min: -0.35390 max: 1.29134 float32 No instances to display
Any news on this subject, running in to the same problem. In my case it is caused by a divide by zero in model.py, 2456: boxes = np.divide(boxes - shift, scale) using tensorflow 1.13 python 2.7 running demo.ipynb in jupyter.
Any news on this subject, running in to the same problem. In my case it is caused by a divide by zero in model.py, 2456: boxes = np.divide(boxes - shift, scale) using tensorflow 1.13 python 2.7 running demo.ipynb in jupyter.
@tabelh @tobymu I encountered exactly the same problem here. Any solution? Thanks al lot!
Any news on this subject, running in to the same problem. In my case it is caused by a divide by zero in model.py, 2456: boxes = np.divide(boxes - shift, scale) using tensorflow 1.13 python 2.7 running demo.ipynb in jupyter.
@tabelh @tobymu I encountered exactly the same problem here. Any solution? Thanks al lot!
I think it has something to do with the interpreter of python2.7 that does not allow simple training. I ended up simply running the code in a python3 virtualenvironment to do my training. The weight file can then be used for inference with python2 without issues, at least i haven't found them.
Any news on this subject, running in to the same problem. In my case it is caused by a divide by zero in model.py, 2456: boxes = np.divide(boxes - shift, scale) using tensorflow 1.13 python 2.7 running demo.ipynb in jupyter.
@tabelh @tobymu I encountered exactly the same problem here. Any solution? Thanks al lot!
I think it has something to do with the interpreter of python2.7 that does not allow simple training. I ended up simply running the code in a python3 virtualenvironment to do my training. The weight file can then be used for inference with python2 without issues, at least i haven't found them.
@tabelh Thank you very much! I've just found 'Working with py2 #515. A modification with model.py and visualize.py might also solve this problem.
@waleedka Hello, I use tensorflow1.9 + python3.5
When I run the demo, it shows "No instances to display"
I don't know why. Thanks for help!