cv2.error: OpenCV(3.4.8) /io/opencv/modules/imgproc/src/resize.cpp:3720: error: (-215:Assertion failed) !ssize.empty() in function 'resize' about arcface-multiplex-recognition HOT 4 OPEN

This may be because the face border is too small.
Remember to determine the size of the face before entering the network
记得在输入网络之前判断人脸的大小

from arcface-multiplex-recognition.

python usb_camera.py -c 0
[0]
Exception in thread Thread-3:
Traceback (most recent call last):
File "/home1/houjr/anaconda3/lib/python3.7/threading.py", line 926, in _bootstrap_inner
self.run()
File "/home1/houjr/anaconda3/lib/python3.7/threading.py", line 870, in run
self._target(*self._args, **self._kwargs)
File "usb_camera.py", line 140, in
Process(target=lambda: asyncio.run(upload_loop())).start()
File "/home1/houjr/anaconda3/lib/python3.7/asyncio/runners.py", line 43, in run
return loop.run_until_complete(main)
File "/home1/houjr/anaconda3/lib/python3.7/asyncio/base_events.py", line 579, in run_until_complete
return future.result()
File "usb_camera.py", line 51, in upload_loop
await sio.connect(url)
File "/home1/houjr/anaconda3/lib/python3.7/site-packages/socketio/asyncio_client.py", line 110, in connect
six.raise_from(exceptions.ConnectionError(exc.args[0]), None)
File "", line 3, in raise_from
socketio.exceptions.ConnectionError: Connection refused by the server

[17:59:05] src/nnvm/legacy_json_util.cc:209: Loading symbol saved by previous version v1.4.1. Attempting to upgrade...
[17:59:05] src/nnvm/legacy_json_util.cc:217: Symbol successfully upgraded!
Exception in thread Thread-2:
Traceback (most recent call last):
File "/home1/houjr/anaconda3/lib/python3.7/threading.py", line 926, in _bootstrap_inner
self.run()
File "/home1/houjr/anaconda3/lib/python3.7/threading.py", line 870, in run
self._target(self._args, *self._kwargs)
File "usb_camera.py", line 139, in
Process(target=lambda: asyncio.run(detection_loop(preload))).start()
File "/home1/houjr/anaconda3/lib/python3.7/asyncio/runners.py", line 43, in run
return loop.run_until_complete(main)
File "/home1/houjr/anaconda3/lib/python3.7/asyncio/base_events.py", line 579, in run_until_complete
return future.result()
File "usb_camera.py", line 67, in detection_loop
detector = face_detector.DetectorModel(preload)
File "/home1/houjr/project/ArcFace-Multiplex-Recognition-master/face_detector.py", line 14, in init
self.detector = RetinaFace(args.retina_model, 0, args.gpu, 'net3')
File "/home1/houjr/project/ArcFace-Multiplex-Recognition-master/retinaface.py", line 84, in init
sym, arg_params, aux_params = mx.model.load_checkpoint(prefix, epoch)
File "/home1/houjr/anaconda3/lib/python3.7/site-packages/mxnet/model.py", line 451, in load_checkpoint
save_dict = nd.load('%s-%04d.params' % (prefix, epoch))
File "/home1/houjr/anaconda3/lib/python3.7/site-packages/mxnet/ndarray/utils.py", line 175, in load
ctypes.byref(names)))
File "/home1/houjr/anaconda3/lib/python3.7/site-packages/mxnet/base.py", line 253, in check_call
raise MXNetError(py_str(_LIB.MXGetLastError()))
mxnet.base.MXNetError: [17:59:05] src/ndarray/ndarray.cc:1839: Check failed: header == kMXAPINDArrayListMagic: Invalid NDArray file format
Stack trace:
[bt] (0) /home1/houjr/anaconda3/lib/python3.7/site-packages/mxnet/libmxnet.so(+0x4958fb) [0x7fc5f4a698fb]
[bt] (1) /home1/houjr/anaconda3/lib/python3.7/site-packages/mxnet/libmxnet.so(mxnet::NDArray::Load(dmlc::Stream, std::vector<mxnet::NDArray, std::allocatormxnet::NDArray >, std::vector<std::string, std::allocatorstd::string >*)+0x161) [0x7fc5f6d8f381]
[bt] (2) /home1/houjr/anaconda3/lib/python3.7/site-packages/mxnet/libmxnet.so(MXNDArrayLoad+0x263) [0x7fc5f6ae6a53]
[bt] (3) /home1/houjr/anaconda3/lib/python3.7/lib-dynload/../../libffi.so.6(ffi_call_unix64+0x4c) [0x7fc625aa4ec0]
[bt] (4) /home1/houjr/anaconda3/lib/python3.7/lib-dynload/../../libffi.so.6(ffi_call+0x22d) [0x7fc625aa487d]
[bt] (5) /home1/houjr/anaconda3/lib/python3.7/lib-dynload/_ctypes.cpython-37m-x86_64-linux-gnu.so(_ctypes_callproc+0x2ce) [0x7fc625cb9ede]
[bt] (6) /home1/houjr/anaconda3/lib/python3.7/lib-dynload/_ctypes.cpython-37m-x86_64-linux-gnu.so(+0x12914) [0x7fc625cba914]
[bt] (7) python(_PyObject_FastCallKeywords+0x49b) [0x556dac4708fb]
[bt] (8) python(_PyEval_EvalFrameDefault+0x52f8) [0x556dac4d46e8]

[17:59:05] src/nnvm/legacy_json_util.cc:209: Loading symbol saved by previous version v1.4.1. Attempting to upgrade...
[17:59:05] src/nnvm/legacy_json_util.cc:217: Symbol successfully upgraded!
Exception in thread Thread-1:
Traceback (most recent call last):
File "/home1/houjr/anaconda3/lib/python3.7/threading.py", line 926, in _bootstrap_inner
self.run()
File "/home1/houjr/anaconda3/lib/python3.7/threading.py", line 870, in run
self._target(self._args, *self._kwargs)
File "usb_camera.py", line 138, in
Process(target=lambda: asyncio.run(embedding_loop(preload))).start()
File "/home1/houjr/anaconda3/lib/python3.7/asyncio/runners.py", line 43, in run
return loop.run_until_complete(main)
File "/home1/houjr/anaconda3/lib/python3.7/asyncio/base_events.py", line 579, in run_until_complete
return future.result()
File "usb_camera.py", line 57, in embedding_loop
embedding = face_embedding.EmbeddingModel(preload)
File "/home1/houjr/project/ArcFace-Multiplex-Recognition-master/face_embedding.py", line 39, in init
self.model = get_model(ctx, image_size, args.arcface_model, 'fc1')
File "/home1/houjr/project/ArcFace-Multiplex-Recognition-master/face_embedding.py", line 23, in get_model
sym, arg_params, aux_params = mx.model.load_checkpoint(prefix, epoch)
File "/home1/houjr/anaconda3/lib/python3.7/site-packages/mxnet/model.py", line 451, in load_checkpoint
save_dict = nd.load('%s-%04d.params' % (prefix, epoch))
File "/home1/houjr/anaconda3/lib/python3.7/site-packages/mxnet/ndarray/utils.py", line 175, in load
ctypes.byref(names)))
File "/home1/houjr/anaconda3/lib/python3.7/site-packages/mxnet/base.py", line 253, in check_call
raise MXNetError(py_str(_LIB.MXGetLastError()))
mxnet.base.MXNetError: [17:59:05] src/ndarray/ndarray.cc:1839: Check failed: header == kMXAPINDArrayListMagic: Invalid NDArray file format
Stack trace:
[bt] (0) /home1/houjr/anaconda3/lib/python3.7/site-packages/mxnet/libmxnet.so(+0x4958fb) [0x7fc5f4a698fb]
[bt] (1) /home1/houjr/anaconda3/lib/python3.7/site-packages/mxnet/libmxnet.so(mxnet::NDArray::Load(dmlc::Stream, std::vector<mxnet::NDArray, std::allocatormxnet::NDArray >, std::vector<std::string, std::allocatorstd::string >*)+0x161) [0x7fc5f6d8f381]
[bt] (2) /home1/houjr/anaconda3/lib/python3.7/site-packages/mxnet/libmxnet.so(MXNDArrayLoad+0x263) [0x7fc5f6ae6a53]
[bt] (3) /home1/houjr/anaconda3/lib/python3.7/lib-dynload/../../libffi.so.6(ffi_call_unix64+0x4c) [0x7fc625aa4ec0]
[bt] (4) /home1/houjr/anaconda3/lib/python3.7/lib-dynload/../../libffi.so.6(ffi_call+0x22d) [0x7fc625aa487d]
[bt] (5) /home1/houjr/anaconda3/lib/python3.7/lib-dynload/_ctypes.cpython-37m-x86_64-linux-gnu.so(_ctypes_callproc+0x2ce) [0x7fc625cb9ede]
[bt] (6) /home1/houjr/anaconda3/lib/python3.7/lib-dynload/_ctypes.cpython-37m-x86_64-linux-gnu.so(+0x12914) [0x7fc625cba914]
[bt] (7) python(_PyObject_FastCallKeywords+0x49b) [0x556dac4708fb]
[bt] (8) python(_PyEval_EvalFrameDefault+0x52f8) [0x556dac4d46e8]

from arcface-multiplex-recognition.

还是这个NDArray的问题

mxnet.base.MXNetError: [18:16:46] src/ndarray/ndarray.cc:1839: Check failed: header == kMXAPINDArrayListMagic: Invalid NDArray file format

from arcface-multiplex-recognition.

我的MXNET版本是1.14.X和1.15.X，cuda 9 10 10.1都测试过
要不你试试通过这个链接重新下载对应的模型
如果还有问题可以等我更新更稳定的版本（月底之前）

from arcface-multiplex-recognition.