10 examples of 'load model keras' in Python

80
def load_model():
81
	"""
82
	"""
83
84
	json_file = open('multilabel_model.json', 'r')
85
	loaded_model_json = json_file.read()
86
	json_file.close()
87
	model = model_from_json(loaded_model_json)
88
89
	model.load_weights('multilabel_model.h5')
90
	print("Loaded model from disk")
91
92
	model.summary()
93
94
	model.compile(loss='binary_crossentropy',
95
		optimizer='adam',
96
		metrics=[f1_score])
97
98
99
	return model

43
def loaded_model():
44
45
    json_file = open('/Users/yang/ChemTS/RNN-model/model.json', 'r')
46
    #json_file = open('/Users/yang/LSTM-chemical-project/protein-ligand/model.json', 'r')
47
    loaded_model_json = json_file.read()
48
    json_file.close()
49
    loaded_model = model_from_json(loaded_model_json)
50
51
    # load weights into new model
52
    #loaded_model.load_weights('/Users/yang/LSTM-chemical-project/protein-ligand/model.h5')
53
    loaded_model.load_weights('/Users/yang/ChemTS/RNN-model/model.h5')
54
    print("Loaded model from disk")
55
56
57
    return loaded_model

140
def load(self, model_folder='./model/'):
141
    # load json and create model
142
    json_file = open(model_folder + 'model.json', 'r')
143
    loaded_model_json = json_file.read()
144
    json_file.close()
145
    loaded_model = model_from_json(loaded_model_json)
146
    # load weights into new model
147
    loaded_model.load_weights(model_folder + 'model.h5')
148
    print('Loaded model from disk')
149
    
150
    self.model = loaded_model
151
    # loaded model should be compiled
152
    self.__compile()
153
    self.load_activation_model()

58
def load(self, save_path):
59
    self.classifier = keras.models.load_model(save_path)

120
def load_pretrained_model():
121
    weathernet = keras.models.load_model(model_filepath)
122
    return weathernet

111
def load_best_model(self):
112
    print('Logging Info - Loading model checkpoint: %s.hdf5\n' % self.config.exp_name)
113
    self.load_model(os.path.join(self.config.checkpoint_dir, '{}.hdf5'.format(self.config.exp_name)))
114
    print('Logging Info - Model loaded')

103
def _load_model(self):
104
    '''
105
    Loads the model weights from disk. Prepares the model to be able to
106
    make predictions.
107
    '''
108
    self.logger.info(
109
        'Loading model weights from {}'.format(self.model_filepath))
110
    self.model = load_model(self.model_filepath)
111
    self.graph = tf.get_default_graph()

4
def ModelLoader(model_file):
5
    print("Loading pre-trained model")
6
    custom_objects = {'weighted_dice_coefficient_loss': weighted_dice_coefficient_loss}
7
    try:
8
        from keras_contrib.layers import InstanceNormalization
9
        custom_objects["InstanceNormalization"] = InstanceNormalization
10
    except ImportError:
11
        pass
12
    try:
13
        return load_model(model_file, custom_objects=custom_objects)
14
    except ValueError as error:
15
        if 'InstanceNormalization' in str(error):
16
            raise ValueError(str(error) + "\n\nPlease install keras-contrib to use InstanceNormalization:\n"
17
                                          "'pip install git+https://www.github.com/keras-team/keras-contrib.git'")
18
        else:
19
            raise error

175
def load_model(self):
176
    print("BertBiLstmModel load_model start!")
177
    # logger.info("BertBiLstmModel load_model start!")
178
    self.model.load_weights(args.path_save_model)
179
    # logger.info("BertBiLstmModel load_model end+!")
180
    print("BertBiLstmModel load_model end+!")

282
def load(model_name, img_dim, nb_patch, bn_mode, use_mbd, batch_size):
283
284
    if model_name == "generator_unet_upsampling":
285
        model = generator_unet_upsampling(img_dim, bn_mode, model_name=model_name)
286
        model.summary()
287
        return model
288
289
    if model_name == "generator_unet_deconv":
290
        model = generator_unet_deconv(img_dim, bn_mode, batch_size, model_name=model_name)
291
        model.summary()
292
        return model
293
294
    if model_name == "DCGAN_discriminator":
295
        model = DCGAN_discriminator(img_dim, nb_patch, bn_mode, model_name=model_name, use_mbd=use_mbd)
296
        model.summary()
297
        return model