when i prepare all condition including python2.7 and libraries
ValueError: "unregistered extension code 57" is appear at ”self.data_dict = np.load(vgg16_npy_path, encoding='latin1').item() in FCN8VGG.
the same error appear in python3.5
do you have some idea to salve this problem??

it was salved by redownload vgg16.npy

Hi
I would like to ask How is Possible to manage And Control the different Trained weights data

1:

I probably understand how to modify a Hypes to train on own dataset,

"train_file": "KittiBox/train.txt",
        "val_file": "KittiBox/val.txt",
        "truncate_data": false,
        "eval_cmd": "../submodules/KittiObjective2/./evaluate_object2",
        "label_dir": "KittiBox/training/label_2"

to modify label_dir to own path with label Folder together with same path like label_2 with Images-Folder...:?

2:
But isn't too clear for me how to Run to prediction the specific Trained Weights data

For example: in Folder :/KittiBox/DATA
I Have the vgg16.npy weights and I would like to Run another weight-data-file.

Or it will be every time re-writing in folder DATA, when I will be train on another dataset????

Hello. Whenever I try to run the demo code from terminal it works. But whenever I try to run from an IDLE , by changing the image path to the image path , this error shows up
ArgumentError: argument --logdir: conflicting option string(s): --logdir

My idle is Spyder with tensorflow 1.1.0. Please help

Hello,

I cannot get train.py to run. I get this verbose error message. Any suggestions?
I can run evaluate and demo without issue

(py2) anthony@aZ68MA-D2H-B3:~/KittiBox$ python train.py
2017-06-12 13:52:22,864 INFO No environment variable 'TV_PLUGIN_DIR' found. Set to '/home/anthony/tv-plugins'.
2017-06-12 13:52:22,864 INFO No environment variable 'TV_STEP_SHOW' found. Set to '50'.
2017-06-12 13:52:22,864 INFO No environment variable 'TV_STEP_EVAL' found. Set to '250'.
2017-06-12 13:52:22,864 INFO No environment variable 'TV_STEP_WRITE' found. Set to '1000'.
2017-06-12 13:52:22,864 INFO No environment variable 'TV_MAX_KEEP' found. Set to '10'.
2017-06-12 13:52:22,864 INFO No environment variable 'TV_STEP_STR' found. Set to 'Step {step}/{total_steps}: loss = {loss_value:.2f}; lr = {lr_value:.2e}; {sec_per_batch:.3f} sec (per Batch); {examples_per_sec:.1f} imgs/sec'.
2017-06-12 13:52:22,865 INFO f: <open file 'hypes/kittiBox.json', mode 'r' at 0x7feb344ba270>
2017-06-12 13:52:22,865 INFO Initialize training folder
2017-06-12 13:52:22,870 INFO Start training
2017-06-12 13:52:22.872836: 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.
2017-06-12 13:52:22.872856: 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.
2017-06-12 13:52:22.872863: 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.
2017-06-12 13:52:22.986751: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:901] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2017-06-12 13:52:22.987118: I tensorflow/core/common_runtime/gpu/gpu_device.cc:887] Found device 0 with properties: 
name: GeForce GTX 1070
major: 6 minor: 1 memoryClockRate (GHz) 1.7845
pciBusID 0000:01:00.0
Total memory: 7.92GiB
Free memory: 6.89GiB
2017-06-12 13:52:22.987143: I tensorflow/core/common_runtime/gpu/gpu_device.cc:908] DMA: 0 
2017-06-12 13:52:22.987150: I tensorflow/core/common_runtime/gpu/gpu_device.cc:918] 0:   Y 
2017-06-12 13:52:22.987163: I tensorflow/core/common_runtime/gpu/gpu_device.cc:977] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 1070, pci bus id: 0000:01:00.0)
npy file loaded
Layer name: conv1_1
Layer shape: (3, 3, 3, 64)
2017-06-12 13:52:23,261 INFO Creating Summary for: conv1_1/filter
2017-06-12 13:52:23,278 INFO Creating Summary for: conv1_1/biases
Layer name: conv1_2
Layer shape: (3, 3, 64, 64)
2017-06-12 13:52:23,299 INFO Creating Summary for: conv1_2/filter
2017-06-12 13:52:23,315 INFO Creating Summary for: conv1_2/biases
Layer name: conv2_1
Layer shape: (3, 3, 64, 128)
2017-06-12 13:52:23,337 INFO Creating Summary for: conv2_1/filter
2017-06-12 13:52:23,353 INFO Creating Summary for: conv2_1/biases
Layer name: conv2_2
Layer shape: (3, 3, 128, 128)
2017-06-12 13:52:23,375 INFO Creating Summary for: conv2_2/filter
2017-06-12 13:52:23,391 INFO Creating Summary for: conv2_2/biases
Layer name: conv3_1
Layer shape: (3, 3, 128, 256)
2017-06-12 13:52:23,413 INFO Creating Summary for: conv3_1/filter
2017-06-12 13:52:23,430 INFO Creating Summary for: conv3_1/biases
Layer name: conv3_2
Layer shape: (3, 3, 256, 256)
2017-06-12 13:52:23,453 INFO Creating Summary for: conv3_2/filter
2017-06-12 13:52:23,469 INFO Creating Summary for: conv3_2/biases
Layer name: conv3_3
Layer shape: (3, 3, 256, 256)
2017-06-12 13:52:23,491 INFO Creating Summary for: conv3_3/filter
2017-06-12 13:52:23,507 INFO Creating Summary for: conv3_3/biases
Layer name: conv4_1
Layer shape: (3, 3, 256, 512)
2017-06-12 13:52:23,533 INFO Creating Summary for: conv4_1/filter
2017-06-12 13:52:23,550 INFO Creating Summary for: conv4_1/biases
Layer name: conv4_2
Layer shape: (3, 3, 512, 512)
2017-06-12 13:52:23,578 INFO Creating Summary for: conv4_2/filter
2017-06-12 13:52:23,594 INFO Creating Summary for: conv4_2/biases
Layer name: conv4_3
Layer shape: (3, 3, 512, 512)
2017-06-12 13:52:23,621 INFO Creating Summary for: conv4_3/filter
2017-06-12 13:52:23,638 INFO Creating Summary for: conv4_3/biases
Layer name: conv5_1
Layer shape: (3, 3, 512, 512)
2017-06-12 13:52:23,664 INFO Creating Summary for: conv5_1/filter
2017-06-12 13:52:23,681 INFO Creating Summary for: conv5_1/biases
Layer name: conv5_2
Layer shape: (3, 3, 512, 512)
2017-06-12 13:52:23,707 INFO Creating Summary for: conv5_2/filter
2017-06-12 13:52:23,723 INFO Creating Summary for: conv5_2/biases
Layer name: conv5_3
Layer shape: (3, 3, 512, 512)
2017-06-12 13:52:23,750 INFO Creating Summary for: conv5_3/filter
2017-06-12 13:52:23,765 INFO Creating Summary for: conv5_3/biases
Layer name: fc6
Layer shape: [7, 7, 512, 4096]
2017-06-12 13:52:24,032 INFO Creating Summary for: fc6/weights
2017-06-12 13:52:24,049 INFO Creating Summary for: fc6/biases
Layer name: fc7
Layer shape: [1, 1, 4096, 4096]
2017-06-12 13:52:24,117 INFO Creating Summary for: fc7/weights
2017-06-12 13:52:24,134 INFO Creating Summary for: fc7/biases
2017-06-12 13:52:24,163 INFO Creating Summary for: score_fr/weights
2017-06-12 13:52:24,179 INFO Creating Summary for: score_fr/biases
2017-06-12 13:52:24,209 INFO Creating Summary for: upscore2/up_filter
2017-06-12 13:52:24,234 INFO Creating Summary for: score_pool4/weights
2017-06-12 13:52:24,250 INFO Creating Summary for: score_pool4/biases
2017-06-12 13:52:24,298 INFO Creating Summary for: upscore4/up_filter
2017-06-12 13:52:24,333 INFO Creating Summary for: score_pool3/weights
2017-06-12 13:52:24,355 INFO Creating Summary for: score_pool3/biases
2017-06-12 13:52:24,422 INFO Creating Summary for: upscore32/up_filter
INFO:tensorflow:Summary name /delta_hist0_x is illegal; using delta_hist0_x instead.
2017-06-12 13:52:24,909 INFO Summary name /delta_hist0_x is illegal; using delta_hist0_x instead.
INFO:tensorflow:Summary name /delta_hist0_y is illegal; using delta_hist0_y instead.
2017-06-12 13:52:24,912 INFO Summary name /delta_hist0_y is illegal; using delta_hist0_y instead.
INFO:tensorflow:Summary name /delta_hist0_w is illegal; using delta_hist0_w instead.
2017-06-12 13:52:24,915 INFO Summary name /delta_hist0_w is illegal; using delta_hist0_w instead.
INFO:tensorflow:Summary name /delta_hist0_h is illegal; using delta_hist0_h instead.
2017-06-12 13:52:24,918 INFO Summary name /delta_hist0_h is illegal; using delta_hist0_h instead.
INFO:tensorflow:Summary name /pred_boxes is illegal; using pred_boxes instead.
2017-06-12 13:52:26,754 INFO Summary name /pred_boxes is illegal; using pred_boxes instead.
INFO:tensorflow:Summary name /true_boxes is illegal; using true_boxes instead.
2017-06-12 13:52:26,755 INFO Summary name /true_boxes is illegal; using true_boxes instead.
npy file loaded
Layer name: conv1_1
Layer shape: (3, 3, 3, 64)
Layer name: conv1_2
Layer shape: (3, 3, 64, 64)
Layer name: conv2_1
Layer shape: (3, 3, 64, 128)
Layer name: conv2_2
Layer shape: (3, 3, 128, 128)
Layer name: conv3_1
Layer shape: (3, 3, 128, 256)
Layer name: conv3_2
Layer shape: (3, 3, 256, 256)
Layer name: conv3_3
Layer shape: (3, 3, 256, 256)
Layer name: conv4_1
Layer shape: (3, 3, 256, 512)
Layer name: conv4_2
Layer shape: (3, 3, 512, 512)
Layer name: conv4_3
Layer shape: (3, 3, 512, 512)
Layer name: conv5_1
Layer shape: (3, 3, 512, 512)
Layer name: conv5_2
Layer shape: (3, 3, 512, 512)
Layer name: conv5_3
Layer shape: (3, 3, 512, 512)
Layer name: fc6
Layer shape: [7, 7, 512, 4096]
Layer name: fc7
Layer shape: [1, 1, 4096, 4096]
2017-06-12 13:52:39,734 INFO Step 0/140000: loss = 7.10; lr = 1.00e-05; 0.094 sec (per Batch); 31.9 imgs/sec
2017-06-12 13:52:40,000 INFO       (raw)  Acc.: 0.42,Conf: 0.85,Box: 2.04,Weight: 0.38,Delta: 2.32
2017-06-12 13:52:40,000 INFO    (smooth)  Acc.: 0.42,Conf: 0.85,Box: 2.04,Weight: 0.38,Delta: 2.32
Traceback (most recent call last):
  File "/home/anthony/miniconda3/envs/py2/lib/python2.7/site-packages/tensorflow/python/ops/script_ops.py", line 82, in __call__
    ret = func(*args)
  File "/home/anthony/KittiBox/hypes/../decoder/fastBox.py", line 460, in log_image
    plot_image = data_utils.draw_encoded(
AttributeError: 'module' object has no attribute 'draw_encoded'
2017-06-12 13:52:41.271263: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
2017-06-12 13:52:41.540951: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.541169: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.541397: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.541553: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.541776: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.541936: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.612397: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.612638: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.613163: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.613290: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.613442: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.664624: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.664875: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.665110: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.665352: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.665449: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.665539: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:41.665630: W tensorflow/core/framework/op_kernel.cc:1152] Internal: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
2017-06-12 13:52:45.969701: W tensorflow/core/kernels/queue_base.cc:294] _0_Queues/fifo_queue: Skipping cancelled enqueue attempt with queue not closed
Traceback (most recent call last):
  File "train.py", line 82, in <module>
    tf.app.run()
  File "/home/anthony/miniconda3/envs/py2/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "train.py", line 78, in main
    train.do_training(hypes)
  File "incl/tensorvision/train.py", line 397, in do_training
    run_training(hypes, modules, tv_graph, tv_sess)
  File "incl/tensorvision/train.py", line 266, in run_training
    feed_dict=feed_dict)
  File "/home/anthony/miniconda3/envs/py2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 778, in run
    run_metadata_ptr)
  File "/home/anthony/miniconda3/envs/py2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 982, in _run
    feed_dict_string, options, run_metadata)
  File "/home/anthony/miniconda3/envs/py2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1032, in _do_run
    target_list, options, run_metadata)
  File "/home/anthony/miniconda3/envs/py2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1052, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InternalError: Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
	 [[Node: Evaluation/PyFunc/_549 = _Recv[client_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_2255_Evaluation/PyFunc", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"]()]]

Caused by op u'Evaluation/PyFunc_1', defined at:
  File "train.py", line 82, in <module>
    tf.app.run()
  File "/home/anthony/miniconda3/envs/py2/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "train.py", line 78, in main
    train.do_training(hypes)
  File "incl/tensorvision/train.py", line 378, in do_training
    tv_graph = core.build_training_graph(hypes, queue, modules)
  File "incl/tensorvision/core.py", line 105, in build_training_graph
    hypes, image, labels, decoded_logits, losses, global_step)
  File "/home/anthony/KittiBox/hypes/../decoder/fastBox.py", line 481, in evaluation
    [tf.uint8])
  File "/home/anthony/miniconda3/envs/py2/lib/python2.7/site-packages/tensorflow/python/ops/script_ops.py", line 189, in py_func
    input=inp, token=token, Tout=Tout, name=name)
  File "/home/anthony/miniconda3/envs/py2/lib/python2.7/site-packages/tensorflow/python/ops/gen_script_ops.py", line 40, in _py_func
    name=name)
  File "/home/anthony/miniconda3/envs/py2/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
    op_def=op_def)
  File "/home/anthony/miniconda3/envs/py2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2336, in create_op
    original_op=self._default_original_op, op_def=op_def)
  File "/home/anthony/miniconda3/envs/py2/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1228, in __init__
    self._traceback = _extract_stack()

InternalError (see above for traceback): Failed to run py callback pyfunc_1: see error log.
	 [[Node: Evaluation/PyFunc_1 = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_UINT8], token="pyfunc_1", _device="/job:localhost/replica:0/task:0/cpu:0"](Inputs/Maximum/_519, Inputs/fifo_queue_DequeueMany:1, Inputs/fifo_queue_DequeueMany:3, Optimizer/Variable/read, Evaluation/PyFunc_1/input_4)]]
	 [[Node: Evaluation/PyFunc/_549 = _Recv[client_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_2255_Evaluation/PyFunc", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/gpu:0"]()]]

(py2) 

My computer to slow,so set max_steps to 1000.Is training result ineffective?
what means
display_iter
eval_iter
save_iter
write_iter

Thanks

Hi,
How can we prepare labels for our own dataset just like kitti image detection label? "Misc 0.00 0 -1.82 804.79 167.34 995.43 327.94 1.63 1.48 2.37 3.23 1.59 8.55 -1.47
Car 0.00 0 -1.67 657.39 190.13 700.07 223.39 1.41 1.58 4.36 3.18 2.27 34.38 -1.58
"
Do you have any idea how can we generate these vectors form our image? Any software that can generate the rectangle vector numbers. I want to use it for my own dataset.

Thanks.

i found that in tensorvision/core.py line 115-116 is:
'graph['learning_rate'] = learning_rate'
'graph['decoded_logits'] = learning_rate'
is there something wrong?
apologize for my pool English

They appear to be different in as much as the hypes.json contains parameters not included in kittiBox.json and references python files not included in github, e.g., decoder/yolo_ish.py.

there seem to be 3 instances of each file type. for example:

yolo_ish.py (referenced in hypes.json)
objective.py (in model_files directory)
decoder/fastBox.py (in github)

what is the relationship between these?

thanks!

Hi, when I Runing "python demo.py --input_image data/demo.png", it shows the IOError. I can't got the "KittiBox_pretrained.zip" from "ftp://mi.eng.cam.ac.uk/pub/mttt2/models/KittiBox_pretrained.zip".
Is there something wrong about it?

Hi, Thank you for sharing the code.

I have been trying to run demo.py. However, architeucture.py gives the following error message, looks like it comes from loading vgg16.npy. Would you like to see what can be the reason? Thanks.

2017-08-17 12:02:06,779 INFO Hypes loaded successfully. 2017-08-17 12:02:07,055 INFO Modules loaded successfully. Starting to build tf graph. npy file loaded Traceback (most recent call last): File "demo.py", line 223, in <module> tf.app.run() File "/data/dsp_emerging/anaconda/Anaconda27/envs/python27/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "demo.py", line 142, in main image=image) File "/home/DL-Phase3/KittiBox-master/submodules/TensorVision/tensorvision/core.py", line 137, in build_inference_graph logits = modules['arch'].inference(hypes, image, train=False) File "/data/dsp_emerging/DL-Phase3/KittiBox/KittiBox_pretrained/model_files/architecture.py", line 29, in inference random_init_fc8=True) File "/home/DL-Phase3/KittiBox-master/submodules/tensorflowfcn/fcn8_vgg.py", line 74, in build self.conv1_1 = self._conv_layer(bgr, "conv1_1") File "/home/DL-Phase3/KittiBox-master/submodules/tensorflowfcn/fcn8_vgg.py", line 154, in _conv_layer filt = self.get_conv_filter(name) File "/home/DL-Phase3/KittiBox-master/submodules/tensorflowfcn/fcn8_vgg.py", line 281, in get_conv_filter init = tf.constant_initializer(value=self.data_dict[name][0],dtype=tf.float32) KeyError: 0

the URL cannot work. in demo.py
Could you give us another available URL to download it?

It is mistake. It can be download by browser or create a folder RUNS

hi @MarvinTeichmann
I just touched tensorflow soon.I want run kiitiBox in windows environment，but i do not understand the last step.
Run cd submodules/utils && make to build cython code
Can you tell me how to build cython code?
thanks~

When I run python train.py, there is an error below.
My tensorflow is r1.0.rc.
Also there is no evaluate.py in the repository

I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcublas.so.7.5 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcudnn.so.5 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcufft.so.7.5 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcurand.so.7.5 locally
2017-02-02 16:57:58,427 INFO No environment variable 'TV_PLUGIN_DIR' found. Set to '/home/fc/tv-plugins'.
2017-02-02 16:57:58,427 INFO No environment variable 'TV_STEP_SHOW' found. Set to '50'.
2017-02-02 16:57:58,428 INFO No environment variable 'TV_STEP_EVAL' found. Set to '250'.
2017-02-02 16:57:58,428 INFO No environment variable 'TV_STEP_WRITE' found. Set to '1000'.
2017-02-02 16:57:58,428 INFO No environment variable 'TV_MAX_KEEP' found. Set to '10'.
2017-02-02 16:57:58,428 INFO No environment variable 'TV_STEP_STR' found. Set to 'Step {step}/{total_steps}: loss = {loss_value:.2f}; lr = {lr_value:.2e}; {sec_per_batch:.3f} sec (per Batch); {examples_per_sec:.1f} imgs/sec'.
2017-02-02 16:57:58,428 INFO f: <open file 'hypes/kittiBox.json', mode 'r' at 0x7f8d28f74930>
2017-02-02 16:57:58,428 INFO Initialize training folder
2017-02-02 16:57:58,432 INFO Start training
npy file loaded
Traceback (most recent call last):
File "train.py", line 83, in
tf.app.run()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 44, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "train.py", line 79, in main
train.do_training(hypes)
File "incl/tensorvision/train.py", line 376, in do_training
tv_graph = core.build_training_graph(hypes, queue, modules)
File "incl/tensorvision/core.py", line 79, in build_training_graph
logits = encoder.inference(hypes, image, train=True)
File "/home/fc/2TB/FC/src/KittiBox/hypes/../encoder/vgg.py", line 28, in inference
random_init_fc8=True)
File "incl/tensorflow_fcn/fcn8_vgg.py", line 62, in build
bgr = tf.concat_v2([
AttributeError: 'module' object has no attribute 'concat_v2'

When I am running train.py，I get some errors.
ERROR: Couldn't read: 007000.txt of ground truth. Please write me an email!
An error occured while processing your results.
Please make sure that the data in your zip archive has the right format!

Why?
Thanks!

`Traceback (most recent call last):
File "/home/dlwork/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1323, in _do_call
return fn(*args)
File "/home/dlwork/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1302, in _run_fn
status, run_metadata)
File "/home/dlwork/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/errors_impl.py", line 473, in exit
c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: 0-th value returned by pyfunc_0 is uint8, but expects float
[[Node: Evaluation/PyFunc = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_FLOAT], token="pyfunc_0", _device="/job:localhost/replica:0/task:0/device:CPU:0"](Inputs/Maximum/_147, Evaluation/strided_slice/_365, Evaluation/strided_slice_1/_367, Optimizer/Variable/read, Evaluation/PyFunc/input_4)]]
[[Node: Evaluation/PyFunc/_369 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_1186_Evaluation/PyFunc", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "train.py", line 82, in
tf.app.run()
File "/home/dlwork/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "train.py", line 78, in main
train.do_training(hypes)
File "incl/tensorvision/train.py", line 395, in do_training
run_training(hypes, modules, tv_graph, tv_sess)
File "incl/tensorvision/train.py", line 264, in run_training
feed_dict=feed_dict)
File "/home/dlwork/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 889, in run
run_metadata_ptr)
File "/home/dlwork/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1120, in _run
feed_dict_tensor, options, run_metadata)
File "/home/dlwork/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1317, in _do_run
options, run_metadata)
File "/home/dlwork/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1336, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: 0-th value returned by pyfunc_0 is uint8, but expects float
[[Node: Evaluation/PyFunc = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_FLOAT], token="pyfunc_0", _device="/job:localhost/replica:0/task:0/device:CPU:0"](Inputs/Maximum/_147, Evaluation/strided_slice/_365, Evaluation/strided_slice_1/_367, Optimizer/Variable/read, Evaluation/PyFunc/input_4)]]
[[Node: Evaluation/PyFunc/_369 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_1186_Evaluation/PyFunc", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]]

Caused by op 'Evaluation/PyFunc', defined at:
File "train.py", line 82, in
tf.app.run()
File "/home/dlwork/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "train.py", line 78, in main
train.do_training(hypes)
File "incl/tensorvision/train.py", line 376, in do_training
tv_graph = core.build_training_graph(hypes, queue, modules)
File "incl/tensorvision/core.py", line 105, in build_training_graph
hypes, image, labels, decoded_logits, losses, global_step)
File "/mnt/fpan/HBL_data/data_set/KITTI/KittiBox/hypes/../decoder/fastBox.py", line 476, in evaluation
[tf.float32])
File "/home/dlwork/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/ops/script_ops.py", line 212, in py_func
input=inp, token=token, Tout=Tout, name=name)
File "/home/dlwork/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/ops/gen_script_ops.py", line 50, in _py_func
"PyFunc", input=input, token=token, Tout=Tout, name=name)
File "/home/dlwork/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
op_def=op_def)
File "/home/dlwork/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 2956, in create_op
op_def=op_def)
File "/home/dlwork/anaconda3/envs/tensorflow/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1470, in init
self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

InvalidArgumentError (see above for traceback): 0-th value returned by pyfunc_0 is uint8, but expects float
[[Node: Evaluation/PyFunc = PyFunc[Tin=[DT_FLOAT, DT_FLOAT, DT_FLOAT, DT_INT32, DT_STRING], Tout=[DT_FLOAT], token="pyfunc_0", _device="/job:localhost/replica:0/task:0/device:CPU:0"](Inputs/Maximum/_147, Evaluation/strided_slice/_365, Evaluation/strided_slice_1/_367, Optimizer/Variable/read, Evaluation/PyFunc/input_4)]]
[[Node: Evaluation/PyFunc/_369 = _Recvclient_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device_incarnation=1, tensor_name="edge_1186_Evaluation/PyFunc", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"]]
`

I have one problem in running the demo.py in my own pc. It goes smooth with the demo pictures in the data dir. But when it goes to the other pictures in kiiti, all of them report one same bug. I am so confused with this bug. By the way, I use the tensorflow 1.0.1 without gpu and I don't think this version does matter.

I had following warnings when calling "cd submodules/KittiObjective2/ && make"

g++ -O3 -DNDEBUG -o evaluate_object2 evaluate_object.cpp
evaluate_object.cpp: In function ‘void saveAndPlotPlots(std::__cxx11::string, std::__cxx11::string, std::__cxx11::string, std::vector, bool)’:
evaluate_object.cpp:625:20: warning: ignoring return value of ‘int system(const char)’, declared with attribute warn_unused_result [-Wunused-result]
system(command);
^
evaluate_object.cpp:630:18: warning: ignoring return value of ‘int system(const char*)’, declared with attribute warn_unused_result [-Wunused-result]
system(command);
^
evaluate_object.cpp:632:18: warning: ignoring return value of ‘int system(const char*)’, declared with attribute warn_unused_result [-Wunused-result]
system(command);
^
evaluate_object.cpp:634:18: warning: ignoring return value of ‘int system(const char*)’, declared with attribute warn_unused_result [-Wunused-result]
system(command);
^
evaluate_object.cpp: In function ‘bool eval(std::__cxx11::string, std::__cxx11::string, Mail*)’:
evaluate_object.cpp:652:40: warning: ignoring return value of ‘int system(const char*)’, declared with attribute warn_unused_result [-Wunused-result]
system(("mkdir " + plot_dir).c_str());
^
There is still a "evaluate_object2" generated.
Also when I try to test it, it produce errors as shown below:
2 val_pred val_gt
Thank you for participating in our evaluation!
Starting to evaluate Results found in: val_pred
mkdir: cannot create directory ‘val_pred/plot’: File exists
Loading detections...
done.
sh: 1: gnuplot: not found
sh: 1: gnuplot: not found
Error: /undefinedfilename in (car_detection.eps)
Operand stack:

Execution stack:
%interp_exit .runexec2 --nostringval-- --nostringval-- --nostringval-- 2 %stopped_push --nostringval-- --nostringval-- --nostringval-- false 1 %stopped_push
Dictionary stack:
--dict:1198/1684(ro)(G)-- --dict:0/20(G)-- --dict:78/200(L)--
Current allocation mode is local
Last OS error: No such file or directory
GPL Ghostscript 9.18: Unrecoverable error, exit code 1
sh: 1: pdfcrop: not found
Evaluation Succesfull. Results can be found:
val_pred /results

And during training, program terminates whenever evaluation script is called.

dear MarvinTeichmann,
I have run your code normally and gotten correct results.
However, I found the running time is too long (as your paper declared, the release time is about 30+ms).
My GPU is K40, and the results are as follows:

2017-03-10 13:43:10,864 INFO /home/mifs/mttt2/local_disk/RUNS/TensorDetect2/paper_bench/tau5_zoom_0_kitti_2016_11_09_05.57/model.ckpt-179999
2017-03-10 13:43:17,416 INFO Weights loaded successfully.
2017-03-10 13:43:17,416 INFO Starting inference using data/demo2.png as input
time_h: 2.3411090374
2017-03-10 13:43:19,819 INFO 7 Cars detected
2017-03-10 13:43:19,819 INFO
2017-03-10 13:43:19,819 INFO Coordinates of Box 0
2017-03-10 13:43:19,819 INFO x1: 425.5

Could you help me? Thank you very much!

hey,i was training the kittibox,but my result of evaluation were all zero, i was followed the steps in readme,what steps i missed? other results was right

Hello,
I'am a new to python and tensorflow.

I am trying to run the KittiBox.

However, below logs are printed when I run 'train.py''

===================================================================
Layer shape: (3, 3, 512, 512)
Layer name: conv5_3
Layer shape: (3, 3, 512, 512)
Layer name: fc6
Layer shape: [7, 7, 512, 4096]
Layer name: fc7
Layer shape: [1, 1, 4096, 4096]
Traceback (most recent call last):
File "/home/kimna/TensorflowWorkspace/KittiBox/train.py", line 82, in
tf.app.run()
File "/home/kimna/anaconda3/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 48, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "/home/kimna/TensorflowWorkspace/KittiBox/train.py", line 78, in main
train.do_training(hypes)
File "incl/tensorvision/train.py", line 393, in do_training
modules['input'].start_enqueuing_threads(hypes, queue, 'train', sess)
File "/home/kimna/TensorflowWorkspace/KittiBox/hypes/../inputs/kitti_input.py", line 240, in start_enqueuing_threads
data = gen.next()
AttributeError: 'generator' object has no attribute 'next'

Process finished with exit code 1

I think the 'generator' is written in 'kitti_input.py' -> '_load_kitti_txt' function. However I can't debug the function with Pycharm debuging tool.

What is the my problem?

Thank you

$ make
pip install runcython
Requirement already satisfied: runcython in d:\programfiles\conda\lib\site-pacges
Requirement already satisfied: Cython>=0.10 in d:\programfiles\conda\lib\site-ckages (from runcython)
makecython++ stitch_wrapper.pyx "" "stitch_rects.cpp ./hungarian/hungarian.cpp
Package python was not found in the pkg-config search path.
Perhaps you should add the directory containing `python.pc'
to the PKG_CONFIG_PATH environment variable
No package 'python' found
stitch_wrapper.cpp:4:20: fatal error: Python.h: No such file or directory
 #include "Python.h"
                    ^
compilation terminated.
make: *** [all-python2] Error 1

I have python 3.6.1, what could be a problem?

Hi, I have the problem of running out of memory, as I am testing it on a laptop (GPU memory 2G).
Does it run with CPU only tensorflow?
Or how can I reduce the computing load?

(tensorflow) shawn@governor-ThinkPad-P50:~/Programs/KittiBox$ python demo.py --input_image data/demo.png
2018-02-08 20:01:29,354 INFO No environment variable 'TV_PLUGIN_DIR' found. Set to '/home/nwx8/tv-plugins'.
2018-02-08 20:01:29,354 INFO No environment variable 'TV_STEP_SHOW' found. Set to '50'.
2018-02-08 20:01:29,355 INFO No environment variable 'TV_STEP_EVAL' found. Set to '250'.
2018-02-08 20:01:29,355 INFO No environment variable 'TV_STEP_WRITE' found. Set to '1000'.
2018-02-08 20:01:29,355 INFO No environment variable 'TV_MAX_KEEP' found. Set to '10'.
2018-02-08 20:01:29,355 INFO No environment variable 'TV_STEP_STR' found. Set to 'Step {step}/{total_steps}: loss = {loss_value:.2f}; lr = {lr_value:.2e}; {sec_per_batch:.3f} sec (per Batch); {examples_per_sec:.1f} imgs/sec'.
2018-02-08 20:01:29,355 INFO f: <_io.TextIOWrapper name='RUNS/KittiBox_pretrained/model_files/hypes.json' mode='r' encoding='UTF-8'>
2018-02-08 20:01:29,356 INFO Hypes loaded successfully.
2018-02-08 20:01:29,357 INFO Modules loaded successfully. Starting to build tf graph.
npy file loaded
Layer name: conv1_1
Layer shape: (3, 3, 3, 64)
2018-02-08 20:01:31,717 INFO Creating Summary for: conv1_1/filter
2018-02-08 20:01:31,732 INFO Creating Summary for: conv1_1/biases
Layer name: conv1_2
Layer shape: (3, 3, 64, 64)
2018-02-08 20:01:31,753 INFO Creating Summary for: conv1_2/filter
2018-02-08 20:01:31,765 INFO Creating Summary for: conv1_2/biases
Layer name: conv2_1
Layer shape: (3, 3, 64, 128)
2018-02-08 20:01:31,785 INFO Creating Summary for: conv2_1/filter
2018-02-08 20:01:31,798 INFO Creating Summary for: conv2_1/biases
Layer name: conv2_2
Layer shape: (3, 3, 128, 128)
2018-02-08 20:01:31,821 INFO Creating Summary for: conv2_2/filter
2018-02-08 20:01:31,833 INFO Creating Summary for: conv2_2/biases
Layer name: conv3_1
Layer shape: (3, 3, 128, 256)
2018-02-08 20:01:31,868 INFO Creating Summary for: conv3_1/filter
2018-02-08 20:01:31,881 INFO Creating Summary for: conv3_1/biases
Layer name: conv3_2
Layer shape: (3, 3, 256, 256)
2018-02-08 20:01:31,937 INFO Creating Summary for: conv3_2/filter
2018-02-08 20:01:31,951 INFO Creating Summary for: conv3_2/biases
Layer name: conv3_3
Layer shape: (3, 3, 256, 256)
2018-02-08 20:01:31,991 INFO Creating Summary for: conv3_3/filter
2018-02-08 20:01:32,004 INFO Creating Summary for: conv3_3/biases
Layer name: conv4_1
Layer shape: (3, 3, 256, 512)
2018-02-08 20:01:32,107 INFO Creating Summary for: conv4_1/filter
2018-02-08 20:01:32,122 INFO Creating Summary for: conv4_1/biases
Layer name: conv4_2
Layer shape: (3, 3, 512, 512)
2018-02-08 20:01:32,401 INFO Creating Summary for: conv4_2/filter
2018-02-08 20:01:32,417 INFO Creating Summary for: conv4_2/biases
Layer name: conv4_3
Layer shape: (3, 3, 512, 512)
2018-02-08 20:01:32,720 INFO Creating Summary for: conv4_3/filter
2018-02-08 20:01:32,737 INFO Creating Summary for: conv4_3/biases
Layer name: conv5_1
Layer shape: (3, 3, 512, 512)
2018-02-08 20:01:32,970 INFO Creating Summary for: conv5_1/filter
2018-02-08 20:01:32,985 INFO Creating Summary for: conv5_1/biases
Layer name: conv5_2
Layer shape: (3, 3, 512, 512)
2018-02-08 20:01:33,148 INFO Creating Summary for: conv5_2/filter
2018-02-08 20:01:33,163 INFO Creating Summary for: conv5_2/biases
Layer name: conv5_3
Layer shape: (3, 3, 512, 512)
2018-02-08 20:01:33,363 INFO Creating Summary for: conv5_3/filter
2018-02-08 20:01:33,379 INFO Creating Summary for: conv5_3/biases
Layer name: fc6
Layer shape: [7, 7, 512, 4096]
2018-02-08 20:01:51,219 INFO Creating Summary for: fc6/weights
2018-02-08 20:01:51,233 INFO Creating Summary for: fc6/biases
Layer name: fc7
Layer shape: [1, 1, 4096, 4096]
2018-02-08 20:01:53,957 INFO Creating Summary for: fc7/weights
2018-02-08 20:01:53,973 INFO Creating Summary for: fc7/biases
2018-02-08 20:01:53,994 INFO Creating Summary for: score_fr/weights
2018-02-08 20:01:54,006 INFO Creating Summary for: score_fr/biases
2018-02-08 20:01:54,077 WARNING From /home/nwx8/Programs/KittiBox/incl/tensorflow_fcn/fcn8_vgg.py:114: calling argmax (from tensorflow.python.ops.math_ops) with dimension is deprecated and will be removed in a future version.
Instructions for updating:
Use the axis argument instead
2018-02-08 20:01:54,086 INFO Creating Summary for: upscore2/up_filter
2018-02-08 20:01:54,105 INFO Creating Summary for: score_pool4/weights
2018-02-08 20:01:54,117 INFO Creating Summary for: score_pool4/biases
2018-02-08 20:01:54,140 INFO Creating Summary for: upscore4/up_filter
2018-02-08 20:01:54,160 INFO Creating Summary for: score_pool3/weights
2018-02-08 20:01:54,173 INFO Creating Summary for: score_pool3/biases
2018-02-08 20:01:54,194 INFO Creating Summary for: upscore32/up_filter
2018-02-08 20:01:54,541 INFO Graph build successfully.
2018-02-08 20:01:54.541597: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2018-02-08 20:01:54.619046: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:895] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-02-08 20:01:54.619518: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1105] Found device 0 with properties:
name: Quadro M1000M major: 5 minor: 0 memoryClockRate(GHz): 1.0715
pciBusID: 0000:01:00.0
totalMemory: 1.96GiB freeMemory: 1.59GiB
2018-02-08 20:01:54.619534: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1195] Creating TensorFlow device (/device:GPU:0) -> (device: 0, name: Quadro M1000M, pci bus id: 0000:01:00.0, compute capability: 5.0)
2018-02-08 20:01:55,209 INFO /home/mifs/mttt2/local_disk/RUNS/TensorDetect2/paper_bench/tau5_zoom_0_kitti_2016_11_09_05.57/model.ckpt-179999
2018-02-08 20:01:55,209 INFO Restoring parameters from RUNS/KittiBox_pretrained/model.ckpt-179999
2018-02-08 20:01:59,947 INFO Weights loaded successfully.
2018-02-08 20:01:59,947 INFO Starting inference using data/demo.png as input
2018-02-08 20:02:00.910205: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.03GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
2018-02-08 20:02:01.099306: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 3.09GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
2018-02-08 20:02:01.221222: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 526.50MiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
2018-02-08 20:02:01.377088: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.55GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
2018-02-08 20:02:01.573297: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.07GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
2018-02-08 20:02:01.731673: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 807.75MiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
2018-02-08 20:02:01.920731: W tensorflow/core/common_runtime/bfc_allocator.cc:217] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.06GiB. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory is available.
Traceback (most recent call last):
File "demo.py", line 219, in
tf.app.run()
File "/home/shawn/Programs/tensorflow/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 124, in run
_sys.exit(main(argv))
File "demo.py", line 175, in main
min_conf=0.50, tau=hypes['tau'], color_acc=(0, 255, 0))
File "incl/utils/train_utils.py", line 103, in add_rectangles
from utils.stitch_wrapper import stitch_rects
ImportError: incl/utils/stitch_wrapper.so: undefined symbol: _Py_ZeroStruct

Thank you.
Shawn

I am basically wondering if there's a way to use the existing kittibox weights as the starting point of a new training or if I have to start from scratch without any existing weights?

Hi Marvin

MultiNet is a very amazing job, will you have some plans to release the codes?
Or could I do some contribution based on your codes?

Looking forward to your replay!

I know that how the bounding box realized but this demo just recognize cars in a picture. How to run this model in a video?

I've got

INFO:tensorflow:Summary name /delta_hist0_x is illegal; using delta_hist0_x instead.
2017-03-17 13:42:53,521 INFO Summary name /delta_hist0_x is illegal; using delta_hist0_x instead.
INFO:tensorflow:Summary name /delta_hist0_y is illegal; using delta_hist0_y instead.
2017-03-17 13:42:53,523 INFO Summary name /delta_hist0_y is illegal; using delta_hist0_y instead.
INFO:tensorflow:Summary name /delta_hist0_w is illegal; using delta_hist0_w instead.
2017-03-17 13:42:53,525 INFO Summary name /delta_hist0_w is illegal; using delta_hist0_w instead.
INFO:tensorflow:Summary name /delta_hist0_h is illegal; using delta_hist0_h instead.
2017-03-17 13:42:53,527 INFO Summary name /delta_hist0_h is illegal; using delta_hist0_h instead.
INFO:tensorflow:Summary name /pred_boxes is illegal; using pred_boxes instead.
2017-03-17 13:42:54,742 INFO Summary name /pred_boxes is illegal; using pred_boxes instead.
INFO:tensorflow:Summary name /true_boxes is illegal; using true_boxes instead.
2017-03-17 13:42:54,743 INFO Summary name /true_boxes is illegal; using true_boxes instead.

Your 1. example in Tutorial -> Getting started does not work in my environment but gives:

2018-02-08 20:43:57,633 INFO Starting inference using data/demo.png as input
Traceback (most recent call last):
File "demo.py", line 219, in
tf.app.run()
File "/Users/erkki/tensorflow/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 124, in run
_sys.exit(main(argv))
File "demo.py", line 175, in main
min_conf=0.50, tau=hypes['tau'], color_acc=(0, 255, 0))
File "incl/utils/train_utils.py", line 103, in add_rectangles
from utils.stitch_wrapper import stitch_rects
ImportError: dynamic module does not define module export function (PyInit_stitch_wrapper)

I'm running your code on macOS High Sierra version 10.13.3 and installed tensorflow and all SW you mentioned according your instructions and instructions by tensorflow. How could this situation be fixed ?

I was training KittiBox with my resize Kitti images data. Such that I modified data in label files. And in the evaluation process, it need KittiObject2 to support evaluation. But how does val_gt and val_pred produce? Since README.md in KittiObject2 does not tell me about val_gt and val_pred.

It's a wonderful project and it works with pretrained model. Now problem occured when I start to train my own dataset, how can I generate label file just like data_object_label_2.zip? Thanks.

Hello :)

This is a really cool idea and implementation!

I bumped into what appears to be a small bug with python 3.6 on Ubuntu 16.04.

While running python evaluate.py this error is returned:
ModuleNotFoundError: No module named 'stitch_wrapper'

The fix below works for me. Not sure if it's a general issue or not. Figured I would post here in case others run into it:

1. run cd submodules/utils && make as directed in readme, if you haven't already
2. rename stitch_wrapper.pyx to stitch_wrapper
3. change the import statement on line 67 in train_utils to add utils.
   ie -> from utils.stitch_wrapper import stitch_rects

Traceback (most recent call last):
File "demo.py", line 206, in
tf.app.run()
File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 44, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "demo.py", line 135, in main
image=image)
File "incl/tensorvision/core.py", line 137, in build_inference_graph
logits = modules['arch'].inference(hypes, image, train=False)
File "RUNS/KittiBox_pretrained/model_files/architecture.py", line 22, in inference
vgg_fcn = fcn8_vgg.FCN8VGG(vgg16_npy_path=vgg16_npy_path)
File "/home/zjj/KittiBox/incl/tensorflow_fcn/fcn8_vgg.py", line 33, in init
self.data_dict = np.load(vgg16_npy_path, encoding='latin1').item()
File "/home/zjj/.local/lib/python2.7/site-packages/numpy/lib/npyio.py", line 406, in load
pickle_kwargs=pickle_kwargs)
File "/home/zjj/.local/lib/python2.7/site-packages/numpy/lib/format.py", line 637, in read_array
array = pickle.load(fp, **pickle_kwargs)
EOFError

I need your help

Hi, great work so far! I've been experimenting with fastbox and have been able to get the demo to work. However, when I try to retrain my own model with the same Kitti dataset I'm getting the following error message when I run: python train.py

terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
Aborted (core dumped)

How to import new encoders like MobileNet , Inception , Xception ... Instead of VGG or GoogleNet ?

There is a import error when I run demo.py .

I am wondering what is the licensing of the pre-trained weights ? I am wondering because I would like to use the weights as a baseline for further training and I want to make sure I know what the licensing is.

Awesome library, btw !

Is there any way to add or remove summary for certain fields?

when I run the demo.py, I got the following errors. Looks like the ./submodules/utils is not built properly, missing some add'l lib in linkage, maybe. Would you please give me some directions? thanks.

2017-03-18 10:50:40,035 INFO Weights loaded successfully.
2017-03-18 10:50:40,035 INFO Starting inference using data/demo.png as input
Traceback (most recent call last):
File "demo.py", line 206, in
tf.app.run()
File "/home/jin/anaconda2/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 44, in run
_sys.exit(main(_sys.argv[:1] + flags_passthrough))
File "demo.py", line 172, in main
min_conf=0.50, tau=hypes['tau'], color_acc=(0, 255, 0))
File "incl/utils/train_utils.py", line 103, in add_rectangles
from stitch_wrapper import stitch_rects
ImportError: incl/utils/stitch_wrapper.so: undefined symbol: _ZTINSt8ios_base7failureB5cxx11E

i use python 3.5 on windows and built 'stitch_wrapper.pyx' with visual C++ 2015 build tool.
The tensorflow version is 1.0
when i run demo.py, i get this error:
ImportError: dynamic module does not define module export function (PyInit_stitch_wrapper)
I wonder that if this code can only run on python 2.7? do any one success run this on python 3.5

ERROR File 'DATA/vgg16.npy' not found. Download it from ftp://mi.eng.cam.ac.uk/pub/mttt2/models/vgg16.npy

I use image in KITTI and regard pred_up in modules['arch'].inference as segmentaion result, but I find this segmentaion result is worse than that in paper "MultiNet Real-time Joint Semantic Reasoning for Autonomous Driving", is it because pred_up not be the segmentation result ?

Hi, suppose i wanna use kittiBox to detect road-sign, billboard, monitor screen and totally 7 types of object, i seem like i have to modify AnnotationLib.py to make it parse annotation rect with class number.

thanks!

https://github.com/Khaos/DD2017/tree/kittiEdit/Code/KittiBox

Hello :)

When I ran this repo with python 3.5 on MacOS 10.12.5.
While running cd submodules/utils && make to build cython code, and this error is returned:

$ make
pip install runcython
Requirement already satisfied: runcython in /Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages
Requirement already satisfied: Cython>=0.10 in /Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages (from runcython)
makecython++ stitch_wrapper.pyx "" "stitch_rects.cpp ./hungarian/hungarian.cpp"
Package python was not found in the pkg-config search path.
Perhaps you should add the directory containing `python.pc'
to the PKG_CONFIG_PATH environment variable
No package 'python' found
In file included from stitch_wrapper.cpp:453:

It seems that the python.pc is not found. I've found phthon3.pc in usr/local/lib/pkgconfig.
So what should I do to fixed this problem? Can you please help me to achieve this.
Thanks so much in advance.

@MarvinTeichmann How reproduce results in your Multinet paper? I tried to add resnet decoders and compare them with the VGG decoder but when I submit results onto http://www.cvlibs.net/datasets/kitti/, it turns out that VGG can only reach 50% on moderate. I used min_conf=0.50, tau=0.35 and exactly same setting as in provided pretrained VGG.

Hey MarvinTeichmann,

I was reviewing https://github.com/MarvinTeichmann/KittiBox/blob/master/demo.py and there is a line

Line:
from utils import train_utils as kittibox_utils

and I'm getting an import error ...

Error:
ImportError: No module named 'utils'

Do you recall where this "kittibox_utils" lives?

Firstly,thanks for your code.It is very useful for my learning.Then,I want to change the "car"detecting to multi-classes detect,about pedestrian ,cyclist and so on.But ,unfortunately,there is many questiones to change the code.So,can you help me? I need you help very much. Thanks a lot!

Could you help explaining what the result values got from "evaluate_object.cpp" is? It's said to be 41 recall discretization steps but I what I got (example in pedestrian_orientation.txt) is a 40 x 4 matrix :

0.000000 1.000000 1.000000 1.000000
0.025000 0.000000 0.000000 0.000000
0.050000 0.000000 0.000000 0.000000
0.075000 0.000000 0.000000 0.000000
0.100000 0.000000 0.000000 0.000000
0.125000 0.000000 0.000000 0.000000
0.150000 0.000000 0.000000 0.000000
0.175000 0.000000 0.000000 0.000000
0.200000 0.000000 0.000000 0.000000
0.225000 0.000000 0.000000 0.000000
0.250000 0.000000 0.000000 0.000000
0.275000 0.000000 0.000000 0.000000
0.300000 0.000000 0.000000 0.000000
0.325000 0.000000 0.000000 0.000000
0.350000 0.000000 0.000000 0.000000
0.375000 0.000000 0.000000 0.000000
0.400000 0.000000 0.000000 0.000000
0.425000 0.000000 0.000000 0.000000
0.450000 0.000000 0.000000 0.000000
0.475000 0.000000 0.000000 0.000000
0.500000 0.000000 0.000000 0.000000
0.525000 0.000000 0.000000 0.000000
0.550000 0.000000 0.000000 0.000000
0.575000 0.000000 0.000000 0.000000
0.600000 0.000000 0.000000 0.000000
0.625000 0.000000 0.000000 0.000000
0.650000 0.000000 0.000000 0.000000
0.675000 0.000000 0.000000 0.000000
0.700000 0.000000 0.000000 0.000000
0.725000 0.000000 0.000000 0.000000
0.750000 0.000000 0.000000 0.000000
0.775000 0.000000 0.000000 0.000000
0.800000 0.000000 0.000000 0.000000
0.825000 0.000000 0.000000 0.000000
0.850000 0.000000 0.000000 0.000000
0.875000 0.000000 0.000000 0.000000
0.900000 0.000000 0.000000 0.000000
0.925000 0.000000 0.000000 0.000000
0.950000 0.000000 0.000000 0.000000
0.975000 0.000000 0.000000 0.000000
1.000000 0.000000 0.000000 0.000000

I don't understand this result at all.
And to calculate the avg precision, it's mentioned to do the following :

sum = 0;
for (i=0; i<=40; i+=4)
  sum += vals[i];
average = sum/11.0;

I don't know what value I should sum.
Please help enlightening me.

Thanks
This is a really cool work!

While running #cd submodules/utils && make # to build cython code, this error is returned:

Thanks！