我按照MNIST 教程进行了学习，并尝试将其调整为使用我自己的数据集。我使用了 Inception 模型，通过 build_image_data.py 将我的图像转换为张量并加载。然后我尝试将它们作为模型的输入，但执行在 model.fit() 函数处就停止了。此后没有任何 CPU 使用率和输出。
以下是相关的代码：
from __future__ import absolute_importfrom __future__ import divisionfrom __future__ import print_functionimport numpy as npimport tensorflow as tffrom tensorflow.contrib import learnfrom tensorflow.contrib.learn.python.learn.estimators import model_fn as model_fn_libimport image_processingimport datasettf.logging.set_verbosity(tf.logging.INFO)height = 200width = 200def cnn_model_fn(features, labels, mode): input_layer = tf.reshape(features, [-1, width, height, 1]) con v1 = tf.layers.conv2d(inputs=input_layer, filters=32, kernel_size=[5, 5], padding="same", activation=tf.nn.relu) pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2) conv2 = tf.layers.conv2d(inputs=pool1, filters=64, kernel_size=[5, 5], padding="same", activation=tf.nn.relu) pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2) pool2_flat = tf.reshape(pool2, [-1, (width/4) * (width/4) * 64]) dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu) dropout = tf.layers.dropout(inputs=dense, rate=0.4, training=mode == learn.ModeKeys.TRAIN) logits = tf.layers.dense(inputs=dropout, units=2) loss = None train_op = None if mode != learn.ModeKeys.INFER: onehot_labels = tf.one_hot(indices=tf.cast(labels, tf.int32), depth=2) loss = tf.losses.softmax_cross_entropy(onehot_labels=onehot_labels, logits=logits) if mode == learn.ModeKeys.TRAIN: train_op = tf.contrib.layers.optimize_loss(loss=loss, global_step=tf.contrib.framework.get_global_step(), learning_rate=0.001, optimizer="SGD") predictions = { "classes": tf.argmax(input=logits, axis=1), "probabilities": tf.nn.softmax(logits, name="softmax_tensor") } return model_fn_lib.ModelFnOps(mode=mode, predictions=predictions, loss=loss, train_op=train_op)def main(unused_argv): training_data = dataset.Dataset("train-00000-of-00001", "train") validation_data = dataset.Dataset("validation-00000-of-00001", "validation") images, labels = image_processing.inputs(training_data) vimages, vlabels = image_processing.inputs(validation_data) sess = tf.InteractiveSession() feature_classifier = learn.SKCompat(learn.Estimator(model_fn=cnn_model_fn, model_dir="/tmp/feature_model")) tensors_to_log = {"probabilities": "softmax_tensor"} logging_hook = tf.train.LoggingTensorHook(tensors=tensors_to_log, every_n_iter=10) feature_classifier.fit(x=images.eval(), y=labels.eval(), batch_size=100, steps=200000, monitors=[logging_hook]) metrics = { "accuracy": learn.MetricSpec(metric_fn=tf.metrics.accuracy, prediction_key="classes"), } # 评估模型并打印结果 eval_results = feature_classifier.evaluate(x=vimages.eval(), y=vlabels.eval(), metrics=metrics) print(eval_results)if __name__ == "__main__": tf.app.run()它在最开始时唯一的输出是：
INFO:tensorflow:使用默认配置。 INFO:tensorflow:使用配置: {‘_save_checkpoints_steps’: None, ‘_tf_config’: gpu_options { per_process_gpu_memory_fraction: 1 } , ‘_tf_random_seed’: None, ‘_keep_checkpoint_max’: 5, ‘_num_ps_replicas’: 0, ‘_master’: ”, ‘_is_chief’: True, ‘_keep_checkpoint_every_n_hours’: 10000, ‘_task_id’: 0, ‘_save_summary_steps’: 100, ‘_task_type’: None, ‘_num_worker_replicas’: 0, ‘_save_checkpoints_secs’: 600, ‘_evaluation_master’: ”, ‘_cluster_spec’: , ‘_environment’: ‘local’, ‘_model_dir’: None}
我的数据集大约有 31 MB + 6 MB 用于输入和验证集。
回答：
你需要启动队列运行器。以下代码更改应该有效：
sess = tf.InteractiveSession()sess.run(tf.global_variables_initializer())coordinator = tf.train.Coordinator()threads = tf.train.start_queue_runners(sess=sess,coord=coordinator)feature_classifier = learn.SKCompat(learn.Estimator(model_fn=cnn_model_fn, model_dir="/tmp/feature_model")) ...print(eval_results)coordinator.request_stop()coordinator.join(threads)另一种推荐的方法是使用更新后的 Estimator ‘input_fn’ 方法，进行以下更改：
sess = tf.InteractiveSession()feature_classifier = learn.Estimator(model_fn=cnn_model_fn, model_dir="/tmp/feature_model")tensors_to_log = {"probabilities": "softmax_tensor"}logging_hook = tf.train.LoggingTensorHook(tensors=tensors_to_log, every_n_iter=10)feature_classifier.fit( input_fn=lambda:image_processing.inputs(training_data), train=True), steps=200000, monitors=[logging_hook])metrics = { "accuracy": learn.MetricSpec(metric_fn=tf.metrics.accuracy, prediction_key="classes"),}