Keras人体姿态分类模型本地报错：无法将'51'转换为形状

问题描述 #

我正在构建一个人体姿态分类的Keras模型，代码参考TensorFlow姿态分类相关教程。代码在Colab环境中运行正常，但本地执行时抛出错误：Cannot convert '51' to a shape.

相关代码 #

def landmarks_to_embedding(landmarks_and_scores):
  """Converts the input landmarks into a pose embedding."""
  # Reshape the flat input into a matrix with shape=(17, 3)
  reshaped_inputs = keras.layers.Reshape((17, 3))(landmarks_and_scores)

  # Normalize landmarks 2D
  landmarks = normalize_pose_landmarks(reshaped_inputs[:, :, :2])

  # Flatten the normalized landmark coordinates into a vector
  embedding = keras.layers.Flatten()(landmarks)

  return embedding

inputs = tf.keras.Input(shape=(51))
embedding = landmarks_to_embedding(inputs)

layer = keras.layers.Dense(128, activation=tf.nn.relu6)(embedding)
layer = keras.layers.Dropout(0.5)(layer)
layer = keras.layers.Dense(64, activation=tf.nn.relu6)(layer)
layer = keras.layers.Dropout(0.5)(layer)
outputs = keras.layers.Dense(len(class_names), activation="softmax")(layer)

model = keras.Model(inputs, outputs)
model.summary()

问题原因与修复方案 #

错误根源在于tf.keras.Input(shape=(51))这一行：在Python中，(51)是整数类型，而非元组。TensorFlow要求输入shape参数必须是元组格式，本地版本对类型检查更严格，而Colab环境可能做了兼容处理。

只需将输入shape改为单元素元组形式即可修复：

inputs = tf.keras.Input(shape=(51,))  # 末尾添加逗号，明确为元组

修改后的完整代码：

def landmarks_to_embedding(landmarks_and_scores):
  """Converts the input landmarks into a pose embedding."""
  # Reshape the flat input into a matrix with shape=(17, 3)
  reshaped_inputs = keras.layers.Reshape((17, 3))(landmarks_and_scores)

  # Normalize landmarks 2D
  landmarks = normalize_pose_landmarks(reshaped_inputs[:, :, :2])

  # Flatten the normalized landmark coordinates into a vector
  embedding = keras.layers.Flatten()(landmarks)

  return embedding

inputs = tf.keras.Input(shape=(51,))  # 修复此处
embedding = landmarks_to_embedding(inputs)

layer = keras.layers.Dense(128, activation=tf.nn.relu6)(embedding)
layer = keras.layers.Dropout(0.5)(layer)
layer = keras.layers.Dense(64, activation=tf.nn.relu6)(layer)
layer = keras.layers.Dropout(0.5)(layer)
outputs = keras.layers.Dense(len(class_names), activation="softmax")(layer)

model = keras.Model(inputs, outputs)
model.summary()

内容的提问来源于stack exchange，提问作者B L Praveen