Keras ValueError: Unknown layer:name, when trying to load model to another platform

python tensorflow keras keras-layer nvidia-jetson
Yannis picture Yannis · Nov 6, 2018 · Viewed 11k times · Source

I have trained a convolutional neural network using Keras 2.2.4 on Nvidia Quadro board. I have saved the trained model in tow separate files: one file (model.json) that describes the architecture and another file (model.h5) that has all the weights.

I want to load the saved model on the Nvidia Jetson TX2 board that runs Keras 2.2.2 and I'm trying to do it as follows:

# load json and create model
    json_file = open(prefix+'final_model.json', 'r')
    loaded_model_json = json_file.read()
    json_file.close()
    loaded_model = model_from_json(loaded_model_json)
# load weights into new model
    loaded_model.load_weights(prefix+"model.h5")
    model = loaded_model

However, when I tried to load I got the following error:

loaded_model = model_from_json(loaded_model_json)

File "/home/nvidia/.local/lib/python3.5/site-packages/keras/engine/saving.py", line 368, in model_from_json return deserialize(config, custom_objects=custom_objects) File "/home/nvidia/.local/lib/python3.5/site-packages/keras/layers/init.py", line 55, in deserialize printable_module_name='layer') File "/home/nvidia/.local/lib/python3.5/site-packages/keras/utils/generic_utils.py", line 145, in deserialize_keras_object list(custom_objects.items()))) File "/home/nvidia/.local/lib/python3.5/site-packages/keras/engine/sequential.py", line 292, in from_config custom_objects=custom_objects) File "/home/nvidia/.local/lib/python3.5/site-packages/keras/layers/init.py", line 55, in deserialize printable_module_name='layer') File "/home/nvidia/.local/lib/python3.5/site-packages/keras/utils/generic_utils.py", line 165, in deserialize_keras_object ':' + function_name) ValueError: Unknown layer:name

I've also tried to save the whole model in one file, but got the same error.

I have tried the solution from here but wasn't able to solve it.

Has anyone seen this error before? Any suggestions?

Answer

user3646527 picture user3646527 · Nov 10, 2018

I had the same problem yesterday, I just updated keras through conda and everything worked perfectly.

Related questions

How do I get the weights of a layer in Keras?

I am using Windows 10, Python 3.5, and tensorflow 1.1.0. I have the following script: import tensorflow as tf import tensorflow.contrib.keras.api.keras.backend as K from tensorflow.contrib.keras.api.keras.layers import Dense tf.reset_default_graph() init = tf.…

Read More
How to fix "AttributeError: module 'tensorflow' has no attribute 'get_default_graph'"?

I am trying to run some code to create an LSTM model but i get an error: AttributeError: module 'tensorflow' has no attribute 'get_default_graph' My code is as follows: from keras.models import Sequential model = Sequential() model.add(…

Read More
Negative dimension size caused by subtracting 3 from 1 for 'conv2d_2/convolution'

I got this error message when declaring the input layer in Keras. ValueError: Negative dimension size caused by subtracting 3 from 1 for 'conv2d_2/convolution' (op: 'Conv2D') with input shapes: [?,1,28,28], [3,3,28,32]. My code is like this model.add(Convolution2D(32, 3, 3, activation=…

Read More