如何在 tf.keras 中创建具有多个输出的回归模型？

Question

我正在尝试训练回归模型来预测 BPM 等音乐属性。该模型采用 256x128 像素 png 文件的音频片段的频谱图，并输出几个连续值。到目前为止，我有以下代码是我在 tensorflow 网站上基于 this guide 开发的：

import tensorflow as tf
import os
import random
import pathlib

AUTOTUNE = tf.data.experimental.AUTOTUNE
TRAINING_DATA_DIR = r'specgrams'

def gen_model():
    model = tf.keras.models.Sequential([
      tf.keras.layers.Flatten(input_shape=(256, 128, 3)),
      tf.keras.layers.Dense(256, activation='relu'),
      tf.keras.layers.Dense(2)
    ])

    model.compile(optimizer=tf.keras.optimizers.RMSprop(0.001),
                  loss='mse',
                  metrics=['mse', 'mae'])

    return model


def fetch_batch(batch_size=1000):
    all_image_paths = []
    all_image_labels = []

    data_root = pathlib.Path(TRAINING_DATA_DIR)
    files = data_root.iterdir()

    for file in files:
        file = str(file)
        all_image_paths.append(os.path.abspath(file))
        label = file[:-4].split('-')[2:]
        label = float(label[0]) / 200, int(label[1]) / 1000.0
        all_image_labels.append(label)

    def preprocess_image(path):
        img_raw = tf.io.read_file(path)
        image = tf.image.decode_png(img_raw, channels=3)
        image = tf.image.resize(image, [256, 128])
        image /= 255.0
        return image

    def preprocess(path, label):
        return preprocess_image(path), label

    path_ds = tf.data.Dataset.from_tensor_slices(all_image_paths)
    image_ds = path_ds.map(preprocess_image, num_parallel_calls=AUTOTUNE)
    label_ds = tf.data.Dataset.from_tensor_slices(all_image_labels)
    ds = tf.data.Dataset.zip((image_ds, label_ds))
    ds = ds.shuffle(buffer_size=len(os.listdir(TRAINING_DATA_DIR)))
    ds = ds.repeat()
    ds = ds.batch(batch_size)
    ds = ds.prefetch(buffer_size=AUTOTUNE)

    return ds

ds = fetch_batch()
model = gen_model()
model.fit(ds, epochs=1, steps_per_epoch=10)

但是我认为我的模型结构或我对训练数据的预处理方式有误，因为我收到有关不正确维度的错误，但我正在努力缩小问题的确切范围。我知道我遵循的指南是针对分类问题而不是回归问题的，我的 "labels" 是一个包含 2 个值的数组，这是导致问题的原因，但我不确定如何解决这个问题。

对于上下文，文件名采用 xxx-xxx-A-B.png 格式，其中 A 和 B 是模型的两个所需输出值。 A 是介于 70 和 180 之间的浮点值，B 是介于 0-1000 之间的整数值。因此，每个图像的 label 变量看起来像这样：(0.64, 0.319).

这是我在尝试执行上述脚本时看到的错误：

Traceback (most recent call last):
  File "C:\Users\cainy\Desktop\BeatNet\training.py", line 60, in <module>
    model.fit(ds, epochs=1, steps_per_epoch=3)
  File "C:\Users\cainy\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py", line 791, in fit
    initial_epoch=initial_epoch)
  File "C:\Users\cainy\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1515, in fit_generator
    steps_name='steps_per_epoch')
  File "C:\Users\cainy\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\keras\engine\training_generator.py", line 257, in model_iteration
    batch_outs = batch_function(*batch_data)
  File "C:\Users\cainy\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1259, in train_on_batch
    outputs = self._fit_function(ins)  # pylint: disable=not-callable
  File "C:\Users\cainy\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\keras\backend.py", line 3217, in __call__
    outputs = self._graph_fn(*converted_inputs)
  File "C:\Users\cainy\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\function.py", line 558, in __call__
    return self._call_flat(args)
  File "C:\Users\cainy\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\function.py", line 627, in _call_flat
    outputs = self._inference_function.call(ctx, args)
  File "C:\Users\cainy\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\function.py", line 415, in call
    ctx=ctx)
  File "C:\Users\cainy\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\eager\execute.py", line 66, in quick_execute
    six.raise_from(core._status_to_exception(e.code, message), None)
  File "<string>", line 3, in raise_from
tensorflow.python.framework.errors_impl.InvalidArgumentError: Can not squeeze dim[1], expected a dimension of 1, got 2
     [[{{node metrics/accuracy/Squeeze}}]] [Op:__inference_keras_scratch_graph_734]

编辑：我已经将源代码上传到 GitHub here.

Answer 1

您目前只有 1 个输出 - 一个长度为 2 的张量（每个批次元素）。如果你想 use/monitor 分离损失，你需要在模型输出和标签中 unstack 它。

我不确定 models.Sequential 是否合适，但你绝对可以使用功能 API:

def gen_model():
    inputs = tf.keras.layers.Input(shape=(256, 128, 3), dtype=tf.float32)
    x = inputs
    x = tf.keras.layers.Dense(256, activation='relu')
    x = tf.keras.layers.Dense(2)
    a, b = tf.keras.layers.Lambda(tf.unstack, arguments=dict(axis=-1))(x)
    model = tf.keras.models.Model(inputs=inputs, outputs=[a, b])
    model.compile(optimizer=tf.keras.optimizers.RMSprop(0.001),
                  loss=['mse', 'mae'],
                  metrics=[['mse'], ['mae']])
    return model

在你的预处理中：

def preprocess(path, label):
    return preprocess_image(path), tf.unstack(label, axis=-1)

如何在 tf.keras 中创建具有多个输出的回归模型？

How do I create a regression model with multiple outputs in tf.keras?

python

tensorflow

keras

tensorflow2.0

tf.keras