hi,I've just met a new porblem when I run the testDetector.py. Hope you can help me check it out.
Traceback (most recent call last):
File "testDetector.py", line 54, in
model = models.load_model(model_path, backbone_name='resnet50')
File "/home/ps/.local/lib/python3.6/site-packages/keras_retinanet/models/init.py", line 87, in load_model
return keras.models.load_model(filepath, custom_objects=backbone(backbone_name).custom_objects)
File "/home/ps/anaconda3/lib/python3.6/site-packages/keras/engine/saving.py", line 492, in load_wrapper
return load_function(*args, **kwargs)
File "/home/ps/anaconda3/lib/python3.6/site-packages/keras/engine/saving.py", line 584, in load_model
model = _deserialize_model(h5dict, custom_objects, compile)
File "/home/ps/anaconda3/lib/python3.6/site-packages/keras/engine/saving.py", line 274, in _deserialize_model
model = model_from_config(model_config, custom_objects=custom_objects)
File "/home/ps/anaconda3/lib/python3.6/site-packages/keras/engine/saving.py", line 627, in model_from_config
return deserialize(config, custom_objects=custom_objects)
File "/home/ps/anaconda3/lib/python3.6/site-packages/keras/layers/init.py", line 168, in deserialize
printable_module_name='layer')
File "/home/ps/anaconda3/lib/python3.6/site-packages/keras/utils/generic_utils.py", line 140, in deserialize_keras_object
': ' + class_name)
ValueError: Unknown layer: Functional
might be a tf version issue, are you using tensorflow 1.11?
pip install tensorflow-gpu==1.11
ok I‘ll try it！
------------------ Original ------------------
From: Jasper Brown <[email protected]>
Date: Mon,Sep 14,2020 1:04 PM
To: jaspereb/Retinanet-Tutorial <[email protected]>
Cc: 林超 <[email protected]>, Author <[email protected]>
Subject: Re: [jaspereb/Retinanet-Tutorial] the problem with testDetector.py (#6)
might be a tf version issue, are you using tensorflow 1.11?
pip install tensorflow-gpu==1.11
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub, or unsubscribe.
jaspereb
