我正在尝试在一些数据上学习一个简单的线性Softmax模型。scikit-learn中的LogisticRegression似乎工作得很好，现在我试图将代码移植到TensorFlow中，但我没有得到同样的表现，而是差了很多。我理解结果不会完全相同（scikit-learn有正则化参数等），但差距太大了。
total = pd.read_feather('testfile.feather')labels = total['labels']features = total[['f1', 'f2']]print(labels.shape)print(features.shape)classifier = linear_model.LogisticRegression(C=1e5, solver='newton-cg', multi_class='multinomial')classifier.fit(features, labels)pred_labels = classifier.predict(features)print("SCI-KITLEARN RESULTS: ")print('\tAccuracy:', classifier.score(features, labels)) print('\tPrecision:', precision_score(labels, pred_labels, average='macro'))print('\tRecall:', recall_score(labels, pred_labels, average='macro'))print('\tF1:', f1_score(labels, pred_labels, average='macro'))# now try softmax regression with tensorflow print("\n\nTENSORFLOW RESULTS: ")## By default, the OneHotEncoder class will return a more efficient sparse encoding. ## This may not be suitable for some applications, such as use with the Keras deep learning library. ## In this case, we disabled the sparse return type by setting the sparse=False argument.enc = OneHotEncoder(sparse=False)enc.fit(labels.values.reshape(len(labels), 1)) # Reshape is required as Encoder expect 2D data as inputlabels_one_hot = enc.transform(labels.values.reshape(len(labels), 1))# tf Graph Inputx = tf.placeholder(tf.float32, [None, 2]) # 2 input featuresy = tf.placeholder(tf.float32, [None, 5]) # 5 output classes# Set model weightsW = tf.Variable(tf.zeros([2, 5]))b = tf.Variable(tf.zeros([5]))# Construct modelpred = tf.nn.softmax(tf.matmul(x, W) + b) # Softmaxclas = tf.argmax(pred, axis=1)# Minimize error using cross entropycost = tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred), reduction_indices=1))# Gradient Descentoptimizer = tf.train.GradientDescentOptimizer(0.01).minimize(cost)# Initialize the variables (i.e. assign their default value)init = tf.global_variables_initializer()# Start trainingwith tf.Session() as sess: # Run the initializer sess.run(init) # Training cycle for epoch in range(1000): # Run optimization op (backprop) and cost op (to get loss value) _, c = sess.run([optimizer, cost], feed_dict={x: features, y: labels_one_hot}) # Test model correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1)) class_out = clas.eval({x: features}) # Calculate accuracy accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) print("\tAccuracy:", accuracy.eval({x: features, y: labels_one_hot})) print('\tPrecision:', precision_score(labels, class_out, average='macro')) print('\tRecall:', recall_score(labels, class_out, average='macro')) print('\tF1:', f1_score(labels, class_out, average='macro'))这段代码的输出是
(1681,)(1681, 2)SCI-KITLEARN RESULTS: Accuracy: 0.822129684711 Precision: 0.837883361162 Recall: 0.784522522208 F1: 0.806251963817TENSORFLOW RESULTS: Accuracy: 0.694825 Precision: 0.735883666192 Recall: 0.649145125846 F1: 0.678045562185我检查了一热编码的结果和数据，但我不知道为什么TF中的结果差很多。
任何建议都会非常感激..
回答：
问题最终证明是愚蠢的，我只需要更多的训练周期，一个更小的学习率（为了效率，我转而使用AdamOptimizer，现在结果相同，尽管TF实现要慢得多。
(1681,)(1681, 2)SCI-KITLEARN RESULTS: Accuracy: 0.822129684711 Precision: 0.837883361162 Recall: 0.784522522208 F1: 0.806251963817TENSORFLOW RESULTS: Accuracy: 0.82213 Precision: 0.837883361162 Recall: 0.784522522208 F1: 0.806251963817