我不明白为什么 tf.estimator.predict 会根据 test_data 的大小预测不同的类别。
test_data = list()for i in range(8, 10): test_data.append(mpimg.imread(FLAGS.input + 'test-' + str(i) + '.png'))test_data = np.asarray(test_data)test_data = test_data[:, :, :, :3].astype(np.float32)...classifier = tf.estimator.Estimator(model_fn=custom_model_fn, model_dir=FLAGS.modelPath)pred_input = tf.estimator.inputs.numpy_input_fn(x = { 'x': test_data }, shuffle = False, num_epochs = 1)根据上面的代码，test_data 包含 test-8.png 和 test-9.png，它们分别对应标签 8 和 9。
通过模型的预测，test_data 推断出的标签分别为 3 和 9。
但是当我使用大小为3的 test_data 时，
for i in range(7, 10): test_data.append(mpimg.imread(FLAGS.input + 'test-' + str(i) + '.png'))test_data 的大小扩展到3，并且包含 test-7.png、test-8.png 和 test-9.png，它们分别对应标签 7、8 和 9。
但是 test_data 推断出的标签分别为 7、8 和 9。
我想知道为什么在第一个和第二个代码中，test-8.png 的预期类别不同。此外，我不明白为什么 test_data 的大小会影响实际的预测结果。
可能代码中存在错误，如果您能告诉我是什么错误，我将不胜感激。
if __name__ == '__main__': import argparse import scipy.io import matplotlib.image as mpimg tf.estimator.RunConfig( ... ) if FLAGS.isTrain: mat_data = scipy.io.loadmat(FLAGS.inputMat) data = mat_data['X'] labels = mat_data['y'] data = data.reshape(data.shape[0] * data.shape[1] * data.shape[2], data.shape[3]).T data = data/np.float32(255) labels = labels.reshape(labels.shape[0]) % 10 train_data = data[:500000] train_labels = make_onehot_vector(labels[:500000].astype(np.float32)) ... classifier = tf.estimator.Estimator(custom_model_fn, model_dir = FLAGS.modelPath) tensors_to_log = {"probabilities" : "softmax_tensor"} logging_hook = tf.train.LoggingTensorHook(tensors=tensors_to_log, every_n_iter=2000) train_input = tf.estimator.inputs.numpy_input_fn( x = {"x":train_data}, y = train_labels, batch_size = FLAGS.batch_size, num_epochs=FLAGS.num_epoch, shuffle = True) train_spec = tf.estimator.TrainSepc(input_fn=train_input, max_stpes=FLAGS.num_stpes) ... tf.estimator.train_and_evaluate(classifier, train_spec, eval_spec) classifier.export_savedmodel(FLAGS.modelPath, serving_input_receiver_fn=serving_input_receiver_fn) else: test_data = list() for i in range(8, 10): test_data.append(mpimg.imread(FLAGS.input + 'test-' + str(i) + '.png')) test_data = np.asarray(test_data) test_data = test_data[:, :, :, :3].astype(np.float32) test_data = test_data.reshape(-1, 32*32*3) classifier = tf.estimator.Estimator(model_fn = custom_model_fn, model_dir = FLAGS.modelPath) pred_input = tf.estimator.inputs.numpy_input_fn(x = {"x": test_Data}, y = None, shuffle=False, num_epochs = 1) pred_result = classifier.predict(input_fn = pred_input) pred_list = list(pred_result) print(pred_list)def custom_model_fn(features, labels, mode): input_layer = tf.reshape(features['x'], [-1, 32, 32, 3]) isTrain = (mode == tf.estimator.ModeKeys.TRAIN) L1 = cnn(input_layer, 32, [5,5], [2,2], 2, phase=isTrain) ... L5 = cnn(L4, 196, [5,5], [2,2], 2, phase=isTrain) L5_flat = tf.reshape(L5, [-1, 196 * 3 * 3]) L6 = dense_batch_relu(L5_flat, isTrain, 1024, 'L6') logits = tf.layers.dense(inputs=L6, units = 10, activation=None) predictions = {"classes": tf.argmax(input=logits, axis=1), "probabilities": tf.nn.softmax(logits, name="softmax_tensor")} if mode == tf.estimator.ModeKeys.PREDICT: export_outputs = {"predict_output": tf.estimator.export.PredictOutput(predictions)} return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions, export_outputs=export_outputs) loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=labels)) + tf.losses.get_regularization_loss() if mode == tf.estimator ModeKeys.TRAIN: optimizer = tf.train.AdamOptimizer(5e-4) train_op = optimizer.minimize(loss=loss, global_step = tf.train.get_global_step()) return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op) Y = tf.argmax(labels, 1) eval_metric_ops = {"acc" : tf.metrics.accuracy(labels=Y, predictions=predictions['classes'])} return tf.estimator.EstimatorSpec(mode=mode, loss=loss, eval_metric_ops=eval_metric_ops)def serving_input_receiver_fn(): inputs = { 'x':tf.placeholder(tf.float32, [None, 32*32*3]), } return tf.estimator.export.ServingInputReceiver(inputs, inputs)在这个代码中，为什么测试数据越小，预测值越不准确，而数据量越大，预测值越准确？
回答：
我在 dense_batch_relu 中使用了 tf.layers.batch_normalization
def dense_batch_relu(x, phase, unit, scope, dropout_rate=0.3): with tf.variable_scope(scope): reg = tf.contrib.layers.l2_regularizer(scale = 5e-3) l1 = tf.layers.dense(x, unit, activation = None, kernel_regularizer=reg) l2 = tf.layers.batch_normalization(inputs=l1, training=phase) l3 = tf.layers.dropout(l2, dropout_rate, training=phase) return tf.nn.relu(l3, 'relu')但是，我没有在 tf.estimator.ModeKeys.TRAIN 中添加 tf.conrol_dependencies
所以，我将代码修改如下：
if mode == tf.estimator ModeKeys.TRAIN: update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS) with tf.control_dependencies(update_ops): optimizer = tf.train.AdamOptimizer(5e-4) train_op = optimizer.minimize(loss=loss, global_step = tf.train.get_global_step()) return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op)然后，它运行得很好。
