The instructions are based on the x86 host PC. Not jetson side.
hi sir, can you tell me how to install tensorflow on jetson nano?
Nevermind sir, I installed Tensorflow 2.3.1+nv20.12 on my jetson nano. But, do you know anything about this error when i’m trying to load my model.
Traceback (most recent call last):
File "PREDICT_CODE.py", line 17, in <module>
model = tf.keras.models.load_model(MODEL_PATH)
File "/home/baekchua_thesis/.local/lib/python3.6/site-packages/tensorflow/python/keras/saving/save.py", line 182, in load_model
return hdf5_format.load_model_from_hdf5(filepath, custom_objects, compile)
File "/home/baekchua_thesis/.local/lib/python3.6/site-packages/tensorflow/python/keras/saving/hdf5_format.py", line 194, in load_model_from_hdf5
training_config, custom_objects))
File "/home/baekchua_thesis/.local/lib/python3.6/site-packages/tensorflow/python/keras/saving/saving_utils.py", line 217, in compile_args_from_training_config
loss = _deserialize_nested_config(losses.deserialize, loss_config)
File "/home/baekchua_thesis/.local/lib/python3.6/site-packages/tensorflow/python/keras/saving/saving_utils.py", line 258, in _deserialize_nested_config
return deserialize_fn(config)
File "/home/baekchua_thesis/.local/lib/python3.6/site-packages/tensorflow/python/keras/losses.py", line 1854, in deserialize
printable_module_name='loss function')
File "/home/baekchua_thesis/.local/lib/python3.6/site-packages/tensorflow/python/keras/utils/generic_utils.py", line 360, in deserialize_keras_object
return cls.from_config(cls_config)
File "/home/baekchua_thesis/.local/lib/python3.6/site-packages/tensorflow/python/keras/losses.py", line 163, in from_config
return cls(**config)
TypeError: __init__() got an unexpected keyword argument 'axis'
I think it’s because I trained and compiled it in a much latest version of tensorflow. But maybe you can tell me something different and fixes that I can do to this.
please file a new topic if what you want to ask is not relevant to original topic.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.