Open glitzflitz opened 5 years ago
Ok so just copied model directory from facenet and this error seemss to be gone. But now I'm getting different error
Traceback (most recent call last):
File "Top.py", line 186, in <module>
FR.build()
File "/home/direwolf/stuff/Face-recognition-with-User-interface/FaceRecognizer.py", line 168, in build
saver.restore(self._sess, os.path.join(self._facenet_model_dir, ckpt_file))
File "/usr/lib/python3.7/site-packages/tensorflow/python/training/saver.py", line 1302, in restore
err, "a Variable name or other graph key that is missing")
tensorflow.python.framework.errors_impl.NotFoundError: Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:
2 root error(s) found.
(0) Not found: Tensor name "InceptionResnetV1/Bottleneck/BatchNorm/beta" not found in checkpoint files /home/direwolf/stuff/Face-recognition-with-User-interface/pretrained_models/FaceNet/model-20161116-234200.ckpt-80000
[[node save/RestoreV2 (defined at /home/direwolf/stuff/Face-recognition-with-User-interface/FaceRecognizer.py:167) ]]
[[save/RestoreV2/_301]]
(1) Not found: Tensor name "InceptionResnetV1/Bottleneck/BatchNorm/beta" not found in checkpoint files /home/direwolf/stuff/Face-recognition-with-User-interface/pretrained_models/FaceNet/model-20161116-234200.ckpt-80000
[[node save/RestoreV2 (defined at /home/direwolf/stuff/Face-recognition-with-User-interface/FaceRecognizer.py:167) ]]
0 successful operations.
0 derived errors ignored.
What was the model directory of facenet and where did you copy it?
I was copying the code here https://github.com/davidsandberg/facenet/tree/master/src/models. And I have a new error
2019-07-26 11:35:18.910564: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2
2019-07-26 11:35:18.916341: I tensorflow/core/common_runtime/process_util.cc:71] Creating new thread pool with default inter op setting: 8. Tune using inter_op_parallelism_threads for best performance.
Load FaceDatabase from C:\Users\alema\OneDrive\Documents\tesis\Face-recognition-with-User-interface-master\data\database\database.pkl
Top.py:185: DeprecationWarning: time.clock has been deprecated in Python 3.3 and will be removed from Python 3.8: use time.perf_counter or time.processtime instead
tic = time.clock()
Load FaceNet model checkpoint from model-20161116-234200.ckpt-80000
Traceback (most recent call last):
File "Top.py", line 186, in
@alejomarcano Yes, the code is not correct. It is not your problem. I recommend making your own network.inference function. You can study tensorflow docs for that
Where can we get the inception model?