网站做微信支付宝支付接口,网站建设 软件企业,做资源网站需要什么,有的网站显示正在建设中毕设做深度学习的课题#xff0c;使用到了TensorFlow#xff0c;但训练时出现了问题#xff1a;跑脚本开启训练之后#xff0c;跑完不到100次就会卡死#xff0c;然后显示python已停止工作这是我的训练的代码# 导入数据集import load_record# 导入TensorFlow并创建Session…毕设做深度学习的课题使用到了TensorFlow但训练时出现了问题跑脚本开启训练之后跑完不到100次就会卡死然后显示python已停止工作这是我的训练的代码# 导入数据集import load_record# 导入TensorFlow并创建Sessionimport tensorflow as tfsess tf.InteractiveSession()# # 构建计算图x tf.placeholder(float, shape [None, 224, 224, 1])y_ tf.placeholder(float, shape [None, 2])def weight_variable(shape):initial tf.truncated_normal(shape, stddev 0.1)return tf.Variable(initial)def bias_variable(shape):initial tf.constant(0.1, shape shape)return tf.Variable(initial)def conv2d(x, W):return tf.nn.conv2d(x, W, strides [1, 1, 1, 1], padding SAME)def max_pool_2x2(x):return tf.nn.max_pool(x, ksize [1, 2, 2, 1], strides [1, 2, 2, 1], padding SAME)x_image tf.reshape(x, [-1, 224, 224, 1])# 第一层卷积W_conv1 weight_variable([5, 5, 1, 32])b_conv1 bias_variable([32])h_conv1 tf.nn.relu(conv2d(x_image, W_conv1) b_conv1)h_pool1 max_pool_2x2(h_conv1)# 第二层卷积W_conv2 weight_variable([5, 5, 32, 64])b_conv2 bias_variable([64])h_conv2 tf.nn.relu(conv2d(h_pool1, W_conv2) b_conv2)h_pool2 max_pool_2x2(h_conv2)# 第一层全连接层W_fc1 weight_variable([56 * 56 * 64, 1024])b_fc1 bias_variable([1024])h_pool2_flat tf.reshape(h_pool2, [-1, 56*56*64])h_fc1 tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) b_fc1)# Dropout层防止过拟合keep_prob tf.placeholder(tf.float32)h_fc1_drop tf.nn.dropout(h_fc1, keep_prob)# 第二层全连接层输出W_fc2 weight_variable([1024, 2])b_fc2 bias_variable([2])y_conv tf.matmul(h_fc1_drop, W_fc2) b_fc2# 训练模型cross_entropy tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labelsy_, logitsy_conv))train_step tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)correct_prediction tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))accuracy tf.reduce_mean(tf.cast(correct_prediction, tf.float32))sess.run(tf.global_variables_initializer())print(ready...)for i in range(500):images, labels load_record.inputs(data_set train, batch_size 50, num_epochs None)tf.train.start_queue_runners(sess sess)_images, _labels sess.run([images, labels])if i % 100 0:train_accuracy accuracy.eval(feed_dict{x:_images, y_: _labels, keep_prob: 1.0})print(step %d, training accuracy %g%(i, train_accuracy))train_step.run(feed_dict{x: _images, y_: _labels, keep_prob: 0.5})数据集我是用tfrecord读进去的def inputs(data_set,batch_size,num_epochs):if not num_epochs:num_epochs Noneif data_set train:file TRAIN_FILEelse:file VALIDATION_FILEwith tf.name_scope(input) as scope:filename_queue tf.train.string_input_producer([file], num_epochsnum_epochs)image,label read_and_decode(filename_queue)#随机获得batch_size大小的图像和labelimages,labels tf.train.shuffle_batch([image, label],batch_sizebatch_size,num_threads64,capacity1000 3 * batch_size,min_after_dequeue1000)return images,labels求教如需补充描述请只迭代了第一次 第二次就不行了
