我正在使用TensorFlow Data和keras构建一个管道来训练我的模型，直到现在，一切都很好，只使用一个输入图像。事实证明，我需要包括2个具有单独CNN架构的新图像，以合并到单个神经网络中，总共3个输入。让我展示一下代码：
def read_tfrecord(example_proto):
image_feature_description = {
'label': tf.io.FixedLenFeature([], tf.int64),
'full_image': tf.io.FixedLenFeature([], tf.string),
'hand_0': tf.io.FixedLenFeature([], tf.string),
'hand_1': tf.io.FixedLenFeature([], tf.string)
}
example = tf.io.parse_single_example(example_proto, image_feature_description)
return read_full_image_and_label(example)
def load_dataset(tf_record_path):
raw_dataset = tf.data.TFRecordDataset(tf_record_path, num_parallel_reads=AUTOTUNE)
parsed_dataset = raw_dataset.map(read_tfrecord, num_parallel_calls=tf.data.experimental.AUTOTUNE)
return parsed_dataset
def load_data_tfrecord(tfrecord_path, augmentation):
dataset = load_dataset(tfrecord_path)
dataset = prepare_for_training(dataset, augmentation)
return dataset
data_generator['train'] = load_data_tfrecord(train_fns, True)
我按照这个顺序阅读我的TF记录，直到这一点，代码几乎与之前的工作内容相同，添加了"hand_0"one_answers"hand_1"(我的新图像(。为了获得图像，我采用了这种方法：
def decode_and_resize_img(tf_btstring, img_width, img_height):
image = tf.image.decode_jpeg(tf_btstring, channels=3)
image = tf.image.resize(image, [img_width, img_height])
return image
def read_full_image_and_label(tf_bytestring):
image = decode_and_resize_img(tf_bytestring['full_image'], 224, 224)
hand_0 = decode_and_resize_img(tf_bytestring['hand_0'], 224, 224)
hand_1 = decode_and_resize_img(tf_bytestring['hand_1'], 224, 224)
label = tf.cast(tf_bytestring['label'], tf.int32)
return {'image_data': image, 'hnd_0': hand_0, 'hnd_1': hand_1}, label
我没有只返回一个图像和一个标签，而是创建了一个对象来放置我所有的图像。在最后一步中，我准备了数据集以提供模型：
def prepare_for_training(ds, augmentation=True, shuffle_buffer_size=1000):
ds.cache()
ds = ds.repeat()
ds = ds.batch(batch_size)
ds = ds.unbatch()
ds = ds.shuffle(buffer_size=shuffle_buffer_size)
ds = ds.batch(batch_size)
ds = ds.prefetch(AUTOTUNE)
return ds
在整个体系结构中，我只是通过对象和TFRecord描述更改了图像的返回。我还更改了CNN/NN拓扑结构，如下所示：
full_body_model = EfficientNetB4(input_shape=(img_width, img_height, 3), weights='imagenet', include_top=False)
hand_1_model = EfficientNetB0(input_shape=(224, 224, 3), weights='imagenet', include_top=False)
hand_2_model = EfficientNetB0(input_shape=(224, 224, 3), weights='imagenet', include_top=False)
full_body_model.trainable = False
hand_1_model.trainable = False
hand_2_model.trainable = False
for layer in hand_1_model.layers:
layer._name = 'hand_1' + str(layer._name)
for layer in hand_2_model.layers:
layer._name = 'hand_2' + str(layer._name)
fbm = full_body_model.output
fbm = GlobalAveragePooling2D()(fbm)
h1m = hand_1_model.output
h1m = GlobalAveragePooling2D()(h1m)
h2m = hand_2_model.output
h2m = GlobalAveragePooling2D()(h2m)
x = Concatenate()([fbm, h1m, h2m])
x = Dense(512, activation='elu', name='fc1')(x)
x = Dropout(0.4)(x)
x = Dense(256, activation='elu', name='fc2')(x)
x = Dropout(0.4)(x)
x = Dense(128, activation='elu', name='fc3')(x)
x = Dropout(0.4)(x)
x = Dense(64, activation='elu', name='fc4')(x)
x = Dropout(0.4)(x)
predictions = Dense(nb_classes, activation='softmax', name='predictions')(x)
model = Model([full_body_model.input, hand_1_model.input, hand_2_model.input], predictions)
现在，我面临这个错误：
ValueError: in user code:
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:811 train_function *
for _ in math_ops.range(self._steps_per_execution):
/usr/local/lib/python3.6/dist-packages/tensorflow/python/autograph/operators/control_flow.py:414 for_stmt
symbol_names, opts)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/autograph/operators/control_flow.py:629 _tf_range_for_stmt
opts)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/autograph/operators/control_flow.py:1059 _tf_while_stmt
body, get_state, set_state, init_vars, nulls, symbol_names)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/autograph/operators/control_flow.py:1032 _try_handling_undefineds
_verify_loop_init_vars(init_vars, symbol_names, first_iter_vars)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/autograph/operators/control_flow.py:193 _verify_loop_init_vars
raise ValueError(error_msg)
ValueError: 'outputs' must be defined before the loop.
我尝试过其他方法，比如这里：https://github.com/tensorflow/tensorflow/issues/20698，但我总是犯同样的错误。我希望得到一些帮助来解决这个问题！
我使用的是谷歌Colab的当前版本，带有TF 2.4.0
为了解决这个问题，我更改了模型接收输入数据的方式。我使用自定义生成器将多输入图像堆叠在一起，并将此列表传递给fit方法。这是我的代码：
def train_gen():
for (stacked, label) in train_ds:
label = label
img1 = stacked[:,0,:,:]
img2 = stacked[:,1,:,:]
img3 = stacked[:,2,:,:]
img1, img2, img3 = transform_batch(img1, img2, img3) #data augmentation
yield [img1, img2, img3], label