python - 任务未能取消序列化

Question

当我尝试运行一些聚类算法时，我不断收到以下错误：

sklearn.externals.joblib.externals.loky.process_executor.BrokenProcessPool：任务无法反序列化。请确保函数的参数都是可挑选的。

我尝试了以下方法：

• 将 scikit-learn 更新到 0.20.2

• 更改 n_jobs = 1 和 -1

  grid = {'km__n_clusters': self._clusters, 'NN__alpha': self._nn_reg, 'NN__hidden_layer_sizes': self._nn_arch}
  mlp = MLPClassifier(activation='relu', max_iter=2000, early_stopping=True, random_state=self._details.seed)
  km = kmeans(random_state=self._details.seed, n_jobs=self._details.threads) #tried n_jobs=self._details.threads
  pipe = Pipeline([('km', km), ('NN', mlp)], memory=experiments.pipeline_memory)
  gs, _ = self.gs_with_best_estimator(pipe, grid, type='kmeans')
  self.log("KMmeans Grid search complete")
  

标签： pythonscikit-learn