can use modAl with keras multi_gpu_model?how should i do?

[awalker0215]

when I use modAl with keras multi_gpu_model,training occurred error like following:

Query no. 1 Traceback (most recent call last): File "/home/es712/Documents/MingHan/pycode/test/ALtest.py", line 77, in query_idx, query_instance = learner.query(X_pool, n_instances=100, verbose=0) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/modAL/models/base.py", line 203, in query query_result = self.query_strategy(self, *query_args, **query_kwargs) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/modAL/uncertainty.py", line 152, in uncertainty_sampling uncertainty = classifier_uncertainty(classifier, X, **uncertainty_measure_kwargs) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/modAL/uncertainty.py", line 77, in classifier_uncertainty classwise_uncertainty = classifier.predict_proba(X, **predict_proba_kwargs) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/modAL/models/base.py", line 186, in predict_proba return self.estimator.predict_proba(X, **predict_proba_kwargs) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/tensorflow/python/keras/wrappers/scikit_learn.py", line 265, in predict_proba probs = self.model.predict_proba(x, **kwargs) AttributeError: 'Model' object has no attribute 'predict_proba'

[cosmic-cortex]

Hi!

As far as I understand the scikit-learn wrapper for Keras, it constructs the model using the build function you provide during the .fit() method, which is stored in the model attribute. From the error log you posted, I suspect the problem is that the model has not been constructed yet when you call learner.query(). Let me know if it helps!

[awalker0215]

Thank you for your answer. I change keras library from tensorflow to origin,use example code from github and it can work. finally code as following: model = Sequential() model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(28, 28, 1))) model.add(Conv2D(64, (3, 3), activation='relu')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Dropout(0.25)) model.add(Flatten()) model.add(Dense(128, activation='relu')) model.add(Dropout(0.5)) model.add(Dense(10, activation='softmax')) try: _model = keras.utils.multi_gpu_model(model,gpus=2) print("Training using multiple GPUs..") except ValueError: _model = model print("Training using single GPU or CPU..") _model.compile(loss='categorical_crossentropy', optimizer='adadelta', metrics=['accuracy']) However,I used resnet50 in keras as my learner,another error occurred with tensorflow.device('/cpu:0'): model = Sequential() model.add(resnet50.ResNet50(include_top = False, pooling = 'avg', weights = None,input_tensor=Input(shape=(28, 28, 1)))) model.add(Dense(10, activation = 'softmax')) adam = optimizers.Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0.0, amsgrad=False)

and error is :

Training using multiple GPUs.. WARNING:tensorflow:From /home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use tf.cast instead. Traceback (most recent call last): File "/home/es712/Documents/MingHan/pycode/test/ALtest.py", line 92, in verbose=1 File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/modAL/models/learners.py", line 79, in init X_training, y_training, bootstrap_init, **fit_kwargs) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/modAL/models/base.py", line 63, in init self._fit_to_known(bootstrap=bootstrap_init, **fit_kwargs) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/modAL/models/base.py", line 106, in _fit_to_known self.estimator.fit(self.X_training, self.y_training, **fit_kwargs) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/keras/wrappers/scikit_learn.py", line 209, in fit return super(KerasClassifier, self).fit(x, y, **kwargs) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/keras/wrappers/scikit_learn.py", line 151, in fit history = self.model.fit(x, y, **fit_args) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/keras/engine/training.py", line 1213, in fit self._make_train_function() File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/keras/engine/training.py", line 316, in _make_train_function loss=self.total_loss) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 91, in wrapper return func(*args, **kwargs) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/keras/optimizers.py", line 543, in get_updates p_t = p - lr_t * m_t / (K.sqrt(v_t) + self.epsilon) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 815, in binary_op_wrapper y = ops.convert_to_tensor(y, dtype=x.dtype.base_dtype, name="y") File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1039, in convert_to_tensor return convert_to_tensor_v2(value, dtype, preferred_dtype, name) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1097, in convert_to_tensor_v2 as_ref=False) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1175, in internal_convert_to_tensor ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 304, in _constant_tensor_conversion_function return constant(v, dtype=dtype, name=name) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 245, in constant allow_broadcast=True) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py", line 283, in _constant_impl allow_broadcast=allow_broadcast)) File "/home/es712/pythonenvs/tensorflow1.13.1/tensorflow1.13.1/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py", line 454, in make_tensor_proto raise ValueError("None values not supported.") ValueError: None values not supported.