ml2cpp step 12 : Keras
Closed this issue · 5 comments
antoinecarme commented
Keras
Follow the six steps described in #1
antoinecarme commented
antoinecarme commented
antoinecarme commented
Keras models fail to pickle (keras.version == '2.4.3')
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-7-59b94fe31a3c> in <module>
14
15
---> 16 lCPPCode = generate_cpp_for_model(clf);
<ipython-input-7-59b94fe31a3c> in generate_cpp_for_model(model)
1 def generate_cpp_for_model(model):
2 import pickle, json, requests, base64
----> 3 b64_data = base64.b64encode(pickle.dumps(model)).decode('utf-8')
4 # send the model th the web service
5 json_data={"Name":"model_cpp_sample",
TypeError: cannot pickle '_thread.RLock' object
antoinecarme commented
There is already a keras issue filed for this same problem :
antoinecarme commented
Same issue filed d by sklearn2sql_heroku two years ago !!!
mllite/sklearn2sql_heroku#3 (comment)
Anyway, as long as pytorch C++ code generation is working, we can get rid of keras.
Closing.