Closed GangLiCN closed 5 years ago
The issue had been fixed.
Reason: model file is corrupt, I used "aria2c" to dowload the model file but it looks like the download had been not finished yet, reexecuted "aria2c" and finished downloading.
BTW: md5 of "yolo.h5": bb28869448aeac2b53ce6f0f43c34d42
sha256 of "yolo.h5": bcfda0f438f0a3db74a5e99ad9c6cd62e4773efdd6beee5ef13b5ad7cfb994f0
Hello,
I'm hitting below error when running "video analyzer" examples:
D:\Dev\Install\Python\packages\AI_learn\imageai\examples>python video_analysis_per_frame.py Using TensorFlow backend. 2018-12-28 08:52:46.075376: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 Traceback (most recent call last): File "video_analysis_per_frame.py", line 52, in
video_detector.loadModel()
File "D:\py36\lib\site-packages\imageai\Detection__init.py", line 1024, in loadModel
model.load_weights(self.modelPath)
File "D:\py36\lib\site-packages\keras\engine\network.py", line 1166, in load_weights
f, self.layers, reshape=reshape)
File "D:\py36\lib\site-packages\keras\engine\saving.py", line 1021, in load_weights_from_hdf5_group
g = f[name]
File "h5py_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "D:\py36\lib\site-packages\h5py_hl\group.py", line 262, in getitem__
oid = h5o.open(self.id, self._e(name), lapl=self._lapl)
File "h5py_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
File "h5py_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
File "h5py\h5o.pyx", line 190, in h5py.h5o.open
KeyError: 'Unable to open object (bad symbol table node signature)'
Same error throws when running another example "video_analyzer_per_second.py".
Does this error mean the model file 'yolo.h5' is corrupt and need to download again ? If this is the case, I suggest that you can provide checksum values(sha256,sha128,md5,,,etc) on the web page for these model files so that users can compare it.
Thanks !