Я пытаюсь загрузить файл model.h5 в коде java с использованием deeplearning4j. Я следую этому уроку https://deeplearning4j.konduit.ai/keras-import/model-functional
Java код
public static void jk()
throws IOException, InvalidKerasConfigurationException, UnsupportedKerasConfigurationException {
String path = "randomjk.h5";
String fullModel = new ClassPathResource(path).getFile().getPath();
ComputationGraph computationGraph = KerasModelImport.importKerasModelAndWeights(fullModel);
}
Ошибка:
Exception in thread "main" org.deeplearning4j.nn.modelimport.keras.exceptions.UnsupportedKerasConfigurationException: No SameDiff Lambda layer found for Lambda layer lambda_1. You can register a SameDiff Lambda layer using KerasLayer.registerLambdaLayer(lambdaLayerName, sameDiffLambdaLayer);. Please file an issue at https://github.com/eclipse/deeplearning4j/issues.
как я тренировался в python
зависимость:
<dependency>
<groupId>org.nd4j</groupId>
<artifactId>nd4j-native-platform</artifactId>
<version>1.0.0-beta6</version>
</dependency>
<dependency>
<groupId>org.deeplearning4j</groupId>
<artifactId>deeplearning4j-modelimport</artifactId>
<version>1.0.0-beta6</version>
</dependency>
<dependency>
<groupId>org.deeplearning4j</groupId>
<artifactId>deeplearning4j-core</artifactId>
<version>0.9.1</version>
</dependency>
Мой python -3,6 импорта:
import datetime
import keras.backend as K
import matplotlib.pyplot as plt
import numpy as np
import os
import pandas as pd
import statistics
import sys
import tensorflow as tf
import uuid
from IPython.display import display, FileLink
from keras.layers import Activation, BatchNormalization, Conv2D, Dense, Dropout, Flatten, Input, Lambda, MaxPooling2D
from keras.models import Model, Sequential, load_model
from keras.optimizers import Adam, SGD
Как я сохранил в python:
model_name_jk = "model_name_jk"
hyper['uuid'] = model_name_jk
stamp('%.1f%% (%.1f%% training) %s' % (test_accuracy, train_accuracy, hyper))
model.save('saved_models/%s.h5' % hyper['uuid'])
Как я создал модель в python:
hyper['dropout'] = 0.5
model_size = 'L'
hyper['conv_filters'] = [32, 64, 128, 256, 512]
hyper['pool_size'] = (2, 2)
hyper['batch_normalization'] = True
hyper['dense_units'] = [6144]
hyper['share_per_character_weights'] = False
hyper['batch_normalization'] = True
def create_per_character_model(activation):
inputs = Input(shape=(hyper['charset_len'],))
x = Dense(hyper['charset_len'], activation='softmax')(inputs)
return Model(inputs, x, name='char_model')
def create_model():
x = Input(shape=(hyper['image_height'], hyper['image_width'], 1), name='input')
image_input = x
# Shared convolutional layers
for layer, filters in enumerate(hyper['conv_filters']):
if hyper['batch_normalization']:
x = BatchNormalization()(x)
x = Conv2D(filters, (3, 3), strides=(1, 1), padding='same', name=f'conv_{layer}', activation='relu')(x)
x = MaxPooling2D(pool_size=hyper['pool_size'], padding='same', name=f'maxpool_{layer}')(x)
x = Dropout(hyper['dropout'], name=f'conv_dropout_{layer}')(x)
# Shared dense layers
x = Flatten()(x)
for layer, units in enumerate(hyper['dense_units']):
x = Dense(units, activation='relu', name=f'dense_{layer}')(x)
x = Dropout(hyper['dropout'], name=f'dense_dropout_{layer}')(x)
x = Dense(hyper['max_len'] * hyper['charset_len'], name='wide_output', activation='linear')(x)
# Per-character output layers
split = Lambda(lambda whole: tf.split(whole, num_or_size_splits=hyper['max_len'], axis=1))(x)
if hyper['share_per_character_weights']:
per_character_model = create_per_character_model(activation='relu' if hyper['post_shared_dense'] else 'softmax')
if hyper['post_shared_dense']:
outputs = [Dense(hyper['charset_len'], name='output_char_%d' % ii, activation='softmax')(per_character_model(split[ii])) for ii in range(hyper['max_len'])]
else:
outputs = [per_character_model(split[ii]) for ii in range(hyper['max_len'])]
else:
outputs = [Dense(hyper['charset_len'], name='output_char_%d' % ii, activation='softmax')(split[ii]) for ii in range(hyper['max_len'])]
model = Model(inputs=[image_input], outputs=outputs)
model.summary()
return model
model = create_model()
Что я пробовал до сих пор:
https://github.com/eclipse/deeplearning4j/blob/master/deeplearning4j/deeplearning4j-modelimport/src/test/java/org/deeplearning4j/nn/modelimport/keras/e2e/KerasLambdaTest.java
Этот пример реализует SameDiffLambdaLayer, но не уверен, как сопоставить это с моей моделью
В python Я предоставил только гиперпараметры при загрузке модели. В deeplearning4j он отличается?