Closed jacklu2016 closed 4 years ago
This issue is fixed in autokeras 1.0.0b0. If not, please reopen the issue. Thanks.
I am facing the same issue when I am trying to compile the following code:
import tensorflow as tf
config = tf.compat.v1.ConfigProto()
config.gpu_options.allow_growth = True
tf.compat.v1.keras.backend.set_session(tf.compat.v1.Session(config=config))
from tensorflow.keras.datasets import mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
print(x_train.shape) # (60000, 28, 28)
print(y_train.shape) # (60000,)
print(y_train[:3]) # array([7, 2, 1], dtype=uint8)
import autokeras as ak
clf = ak.ImageClassifier(max_trials=10) # It tries 10 different models.
clf.fit(x_train, y_train)
predicted_y = clf.predict(x_test)
print(clf.evaluate(x_test, y_test))
The trace is as follows:
Traceback (most recent call last):
File "demo.py", line 17, in <module>
clf.fit(x_train, y_train)
File "/home/abhinit/anaconda3/envs/keras/lib/python3.7/site-packages/autokeras/task.py", line 116, in fit
**kwargs)
File "/home/abhinit/anaconda3/envs/keras/lib/python3.7/site-packages/autokeras/auto_model.py", line 199, in fit
**kwargs)
File "/home/abhinit/anaconda3/envs/keras/lib/python3.7/site-packages/autokeras/tuner.py", line 138, in search
super().search(callbacks=new_callbacks, **fit_kwargs)
File "/home/abhinit/anaconda3/envs/keras/lib/python3.7/site-packages/kerastuner/engine/base_tuner.py", line 122, in search
self.run_trial(trial, *fit_args, **fit_kwargs)
File "/home/abhinit/anaconda3/envs/keras/lib/python3.7/site-packages/autokeras/tuner.py", line 53, in run_trial
trial.hyperparameters)
File "/home/abhinit/anaconda3/envs/keras/lib/python3.7/site-packages/autokeras/hypermodel/graph.py", line 460, in build_graphs
plain_graph = self.hyper_build(hp)
File "/home/abhinit/anaconda3/envs/keras/lib/python3.7/site-packages/autokeras/hypermodel/graph.py", line 480, in hyper_build
outputs = old_block.build(hp, inputs=inputs)
File "/home/abhinit/anaconda3/envs/keras/lib/python3.7/site-packages/autokeras/hypermodel/base.py", line 117, in _build_wrapper
return self._build(hp, *args, **kwargs)
File "/home/abhinit/anaconda3/envs/keras/lib/python3.7/site-packages/autokeras/hypermodel/hyperblock.py", line 62, in build
seed=self.seed)(output_node)
File "/home/abhinit/anaconda3/envs/keras/lib/python3.7/site-packages/autokeras/hypermodel/preprocessor.py", line 577, in __init__
super().__init__(**kwargs)
File "/home/abhinit/anaconda3/envs/keras/lib/python3.7/site-packages/autokeras/hypermodel/base.py", line 100, in __init__
super().__init__(**kwargs)
TypeError: __init__() got an unexpected keyword argument 'seed'
My setup is as follows:
same issue, is it fixed in 1.0.0b.0?
same issue, is it fixed in 1.0.0b.0?
It is merged in the current version in the repo
Bug Description
i have installed autokeras1.0 from git at 12/20/2019, when i running the code bellow, i got errors
this is the code:
erros
Setup Details
Include the details about the versions of: