Tensorflow线性回归模型中的断言失败误差

Question

# IMPORTS
import os
import numpy as np
import tensorflow as tf
import pandas as pd

# IMPORT CSV FILES AS PANDASDB
dfTrain = pd.read_csv('carPriceTrain.csv')
dfEval = pd.read_csv('carPriceEval.csv')

# RENAME COLUMN NAMES
dfTrain = dfTrain.rename(columns={"Gear box type": "gearBoxType"})
dfEval = dfTrain.rename(columns={"Gear box type": "gearBoxType"})
dfTrain = dfTrain.rename(columns={"Leather interior": "leatherInterior"})
dfEval = dfTrain.rename(columns={"Leather interior": "leatherInterior"})

# REMOVE EXTRANEOUS CAR INFORMATION
dfTrain.pop('ID')
dfTrain.pop('Levy')
dfTrain.pop('Category')
dfTrain.pop('Fuel type')
dfTrain.pop('Drive wheels')
dfTrain.pop('leatherInterior')
dfTrain.pop('gearBoxType')
dfTrain.pop('Doors')
dfTrain.pop('Wheel')
dfTrain.pop('Color')
dfTrain.pop('Airbags')

dfEval.pop('ID')
dfEval.pop('Levy')
dfEval.pop('Category')
dfEval.pop('Fuel type')
dfEval.pop('Drive wheels')
dfEval.pop('leatherInterior')
dfEval.pop('gearBoxType')
dfEval.pop('Doors')
dfEval.pop('Wheel')
dfEval.pop('Color')
dfEval.pop('Airbags')

# POP PRICE (PREDICTING VAL)
yTrain = dfTrain.pop('Price')
yEval = dfEval.pop('Price')

# CREATE COLUMNS NAMES
CATEGORICAL_COLUMNS = ['Manufacturer', 'Model']
NUMERIC_COLUMNS = ['Prod. year', 'Mileage', 'Cylinders', 'Engine volume']

# FEATURE COLUMNS FOR CATERGORICAL
featureColumns = []
for featureName in CATEGORICAL_COLUMNS:
  vocabulary = dfTrain[featureName].unique()
  featureColumns.append(tf.feature_column.categorical_column_with_vocabulary_list(featureName, vocabulary))

# FEATURE COLUMNS FOR NUMERIC
for featureName in NUMERIC_COLUMNS:
    featureColumns.append(tf.feature_column.numeric_column(featureName, dtype=tf.float32))

# CREATING INPUT FN
def makeInputFN(dfData, dfLabel, nEpochs=10, shuffle=True, batchSize=32):
  def inputFN():
    ds = tf.data.Dataset.from_tensor_slices((dict(dfData), dfLabel))
    if shuffle:
      ds = ds.shuffle(1000)
    ds = ds.batch(batchSize).repeat(nEpochs)
    return ds
  return inputFN

trainInputFN = makeInputFN(dfTrain, yTrain)
evalInputFN = makeInputFN(dfEval, yEval, nEpochs=1, shuffle=False)

linearEst = tf.estimator.LinearClassifier(feature_columns=featureColumns)

linearEst.train(trainInputFN)
result = linearEst.evaluate(evalInputFN)

我使用TensorFlow 2.0创建了一个线性回归模型。我导入了一个CSV文件，其中包含ID、Price、Levy、Prod、Model和Prod的数据。采购产品年份，类别，皮革内部，燃料类型，发动机体积，里程，气缸，变速箱型，驱动轮，门，车轮，颜色，安全气囊。我弹出了我不会从这些行中使用的行，然后继续这个过程。我遇到了这个错误：

WARNING:tensorflow:Using temporary folder as model directory: /var/folders/kq/823s5gqs0ds7wqckr9sxfcnm0000gn/T/tmp22bryhkx
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow/python/training/training_util.py:396: Variable.initialized_value (from tensorflow.python.ops.variables) is deprecated and will be removed in a future version.
Instructions for updating:
Use Variable.read_value. Variables in 2.X are initialized automatically both in eager and graph (inside tf.defun) contexts.
WARNING:tensorflow:From /Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/keras/optimizers/optimizer_v2/ftrl.py:153: calling Constant.__init__ (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
2022-07-30 15:22:47.534048: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2022-07-30 15:22:47.549419: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:354] MLIR V1 optimization pass is not enabled
Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow/python/client/session.py", line 1377, in _do_call
    return fn(*args)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow/python/client/session.py", line 1360, in _run_fn
    return self._call_tf_sessionrun(options, feed_dict, fetch_list,
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow/python/client/session.py", line 1453, in _call_tf_sessionrun
    return tf_session.TF_SessionRun_wrapper(self._session, options, feed_dict,
tensorflow.python.framework.errors_impl.InvalidArgumentError: assertion failed: [Labels must be <= n_classes - 1] [Condition x <= y did not hold element-wise:] [x (head/losses/Cast:0) = ] [[19444][56509][8781]...] [y (head/losses/check_label_range/Const:0) = ] [1]
         [[{{function_node head_losses_check_label_range_assert_less_equal_Assert_AssertGuard_false_667}}{{node Assert}}]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/Users/anirud/CarPricePredictor/main.py", line 75, in <module>
    linearEst.train(trainInputFN)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow_estimator/python/estimator/estimator.py", line 360, in train
    loss = self._train_model(input_fn, hooks, saving_listeners)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow_estimator/python/estimator/estimator.py", line 1186, in _train_model
    return self._train_model_default(input_fn, hooks, saving_listeners)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow_estimator/python/estimator/estimator.py", line 1217, in _train_model_default
    return self._train_with_estimator_spec(estimator_spec, worker_hooks,
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow_estimator/python/estimator/estimator.py", line 1533, in _train_with_estimator_spec
    _, loss = mon_sess.run([estimator_spec.train_op, estimator_spec.loss])
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow/python/training/monitored_session.py", line 782, in run
    return self._sess.run(
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow/python/training/monitored_session.py", line 1311, in run
    return self._sess.run(
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow/python/training/monitored_session.py", line 1416, in run
    raise six.reraise(*original_exc_info)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/six.py", line 719, in reraise
    raise value
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow/python/training/monitored_session.py", line 1401, in run
    return self._sess.run(*args, **kwargs)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow/python/training/monitored_session.py", line 1469, in run
    outputs = _WrappedSession.run(
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow/python/training/monitored_session.py", line 1232, in run
    return self._sess.run(*args, **kwargs)
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow/python/client/session.py", line 967, in run
    result = self._run(None, fetches, feed_dict, options_ptr,
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow/python/client/session.py", line 1190, in _run
    results = self._do_run(handle, final_targets, final_fetches,
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow/python/client/session.py", line 1370, in _do_run
    return self._do_call(_run_fn, feeds, fetches, targets, options,
  File "/Library/Frameworks/Python.framework/Versions/3.9/lib/python3.9/site-packages/tensorflow/python/client/session.py", line 1396, in _do_call
    raise type(e)(node_def, op, message)  # pylint: disable=no-value-for-parameter
tensorflow.python.framework.errors_impl.InvalidArgumentError: Graph execution error:

assertion failed: [Labels must be <= n_classes - 1] [Condition x <= y did not hold element-wise:] [x (head/losses/Cast:0) = ] [[19444][56509][8781]...] [y (head/losses/check_label_range/Const:0) = ] [1]
         [[{{node Assert}}]]

我不知道为什么会发生这个错误，也不知道该从哪里着手。

Answer 1

我想问题就在这条线上：

linearEst = tf.estimator.LinearClassifier(feature_columns=featureColumns)

您应该根据n_classes的Tensorflow文档设置参数LinearClassifier。参见n_classes的论点：

标签类的数量。默认是二进制分类。注意，类标签是表示类索引的整数(即从0到n_class-1的值)。对于任意的标签值(例如字符串标签)，首先转换为类索引。

因为默认的是二进制分类，所以应该设置类的数量。如果我正确理解你有六个类，那么你应该有：

linearEst = tf.estimator.LinearClassifier(feature_columns=featureColumns, n_classes=6)