hampty score 16
2018/12/25 18:40 投稿
| kerasで学習させたh5モデルからmlmodelへの変換 |
| kerasで学習させたh5モデルからmlmodelへの変換しようとするとエラーがでる |
| ### 前提・実現したいこと |
| kerasで学習させたh5モデルからcoremltoolsを使ったmlmodelへの変換 |
| ### 発生している問題・エラーメッセージ |
| ``` |
| Traceback (most recent call last): |
| File "converter.py", line 8, in <module> |
| class_labels='labels.txt') |
| File "/anaconda3/envs/tf-200/lib/python3.6/site-packages/coremltools/converters/keras/_keras_converter.py", line 745, in convert |
| custom_conversion_functions=custom_conversion_functions) |
| File "/anaconda3/envs/tf-200/lib/python3.6/site-packages/coremltools/converters/keras/_keras_converter.py", line 543, in convertToSpec |
| custom_objects=custom_objects) |
| File "/anaconda3/envs/tf-200/lib/python3.6/site-packages/coremltools/converters/keras/_keras2_converter.py", line 182, in _convert |
| model = _keras.models.load_model(model, custom_objects = custom_objects) |
| File "/anaconda3/envs/tf-200/lib/python3.6/site-packages/keras/models.py", line 233, in load_model |
| model = model_from_config(model_config, custom_objects=custom_objects) |
| File "/anaconda3/envs/tf-200/lib/python3.6/site-packages/keras/models.py", line 307, in model_from_config |
| return layer_module.deserialize(config, custom_objects=custom_objects) |
| File "/anaconda3/envs/tf-200/lib/python3.6/site-packages/keras/layers/__init__.py", line 54, in deserialize |
| printable_module_name='layer') |
| File "/anaconda3/envs/tf-200/lib/python3.6/site-packages/keras/utils/generic_utils.py", line 139, in deserialize_keras_object |
| list(custom_objects.items()))) |
| File "/anaconda3/envs/tf-200/lib/python3.6/site-packages/keras/models.py", line 1204, in from_config |
| if 'class_name' not in config[0] or config[0]['class_name'] == 'Merge': |
| KeyError: 0 |
| ``` |
| ```python |
| path = './keras_cnn.h5' |
| import coremltools |
| coreml_model = coremltools.converters.keras.convert( |
| path, |
| input_names='image', |
| image_input_names='image', |
| class_labels='labels.txt') |
| coreml_model.save('predict.mlmodel') |
| ``` |
| ``` |
| from keras.models import Sequential |
| from keras.layers import Conv2D, MaxPooling2D |
| from keras.layers import Activation, Dropout, Flatten, Dense |
| from keras.utils import np_utils |
| import keras |
| import numpy as np |
| classes = ["perfect", "normal", "bad"] |
| num_classes = len(classes) |
| image_size = 75 |
| def main(): |
| X_train, X_test, y_train, y_test = np.load("./Judgment.npy") |
| X_train = X_train.astype("float") / 256 |
| X_test = X_test.astype("float") / 256 |
| y_train = np_utils.to_categorical(y_train, num_classes) |
| y_test = np_utils.to_categorical(y_test, num_classes) |
| model = model_train(X_train, y_train) |
| model_eval(model, X_test, y_test) |
| def model_train(X, y): |
| model = Sequential() |
| model.add(Conv2D(32, (3, 3), padding='same', input_shape=X.shape[1:])) |
| model.add(Activation('relu')) |
| model.add(Conv2D(32, (3, 3))) |
| model.add(Activation('relu')) |
| model.add(MaxPooling2D(pool_size=(2, 2))) |
| model.add(Dropout(0.25)) |
| model.add(Conv2D(64, (3, 3), padding='same')) |
| model.add(Activation('relu')) |
| model.add(Conv2D(64, (3, 3))) |
| model.add(Activation('relu')) |
| model.add(MaxPooling2D(pool_size=(2, 2))) |
| model.add(Dropout(0.25)) |
| model.add(Flatten()) |
| model.add(Dense(512)) |
| model.add(Activation('relu')) |
| model.add(Dropout(0.5)) |
| model.add(Dense(3)) |
| model.add(Activation('softmax')) |
| opt = keras.optimizers.rmsprop(lr=0.0001, decay=1e-6) |
| model.compile( |
| loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy']) |
| model.fit(X, y, batch_size=32, epochs=100) |
| model.save('./keras_cnn.h5') |
| return model |
| def model_eval(model, X, y): |
| scores = model.evaluate(X, y, verbose=1) |
| print('Test Loss: ', scores[0]) |
| print('Test Accuracy: ', scores[1]) |
| if __name__ == "__main__": |
| main() |
| ``` |
| ### 試したこと |
| python2.7で同様の条件での実行 |
| ### 補足情報（FW/ツールのバージョンなど） |
| python 3.6 |
| Keras 2.0.6 |
| h5py 2.7.1 |
| tensorflow 1.1.0 |
