Data shape error when executing usb_camera_demo.py

[nabedev]

I tried to run usb_camera_demo.py in Jetson TX2 with python3 it raises following data shape error.

ubuntu@ubuntu:~/gpu/python$ python3 usb_camera_demo.py -c ../models/meta.yaml -m ../models/minimal_graph_with_shape.pb
2019-05-08 19:00:36.089683: W tensorflow/core/platform/profile_utils/cpu_utils.cc:98] Failed to find bogomips in /proc/cpuinfo; cannot determine CPU frequency
2019-05-08 19:00:36.090686: I tensorflow/compiler/xla/service/service.cc:161] XLA service 0x439b2de0 executing computations on platform Host. Devices:
2019-05-08 19:00:36.090814: I tensorflow/compiler/xla/service/service.cc:168]   StreamExecutor device (0): <undefined>, <undefined>
2019-05-08 19:00:36.161812: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:965] ARM64 does not support NUMA - returning NUMA node zero
2019-05-08 19:00:36.162111: I tensorflow/compiler/xla/service/service.cc:161] XLA service 0x3eca5f60 executing computations on platform CUDA. Devices:
2019-05-08 19:00:36.162165: I tensorflow/compiler/xla/service/service.cc:168]   StreamExecutor device (0): NVIDIA Tegra X2, Compute Capability 6.2
2019-05-08 19:00:36.162452: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1433] Found device 0 with properties: 
name: NVIDIA Tegra X2 major: 6 minor: 2 memoryClockRate(GHz): 1.02
pciBusID: 0000:00:00.0
totalMemory: 7.68GiB freeMemory: 3.12GiB
2019-05-08 19:00:36.162502: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1512] Adding visible gpu devices: 0
2019-05-08 19:00:37.254041: I tensorflow/core/common_runtime/gpu/gpu_device.cc:984] Device interconnect StreamExecutor with strength 1 edge matrix:
2019-05-08 19:00:37.254265: I tensorflow/core/common_runtime/gpu/gpu_device.cc:990]      0 
2019-05-08 19:00:37.254410: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1003] 0:   N 
2019-05-08 19:00:37.255722: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 2693 MB memory) -> physical GPU (device: 0, name: NVIDIA Tegra X2, pci bus id: 0000:00:00.0, compute capability: 6.2)
Gtk-Message: 19:00:37.490: Failed to load module "canberra-gtk-module"
multiprocessing.pool.RemoteTraceback: 
"""
Traceback (most recent call last):
  File "/usr/lib/python3.6/multiprocessing/pool.py", line 119, in worker
    result = (True, func(*args, **kwds))
  File "usb_camera_demo.py", line 93, in _run_inference
    result, fps, _ = run_inference(img, nn, pre_process, post_process)
  File "/home/ubuntu/gpu/python/lmnet/utils/demo.py", line 154, in run_inference
    result = nn.run(data)
  File "/home/ubuntu/gpu/python/lmnet/tensorflow_graph_runner.py", line 62, in run
    return self.sess.run(self.output_op, feed_dict={self.images_placeholder: data})
  File "/home/ubuntu/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 929, in run
    run_metadata_ptr)
  File "/home/ubuntu/.local/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1128, in _run
    str(subfeed_t.get_shape())))
ValueError: Cannot feed value of shape (160, 160, 3) for Tensor 'images_placeholder:0', which has shape '(1, 160, 160, 3)'
"""

@ruimashita told me should add the following line in demo.py.

data = np.expand_dims(data, axis=0)

But I'm not sure where it is correct to add this line.