为了加深理解，我对SSD项目进行了复现，基于原版，有按照自己理解的修改，
项目见github：SSD_Realization_TensorFlow、SSD_Realization_MXNet
构建思路按照训练主函数的步骤顺序，文末贴了出来，下面我们按照这个顺序简要介绍一下各个流程的重点，想要详细了解的建议看一看之前的解读源码的对应篇章（tf），或者看看李沐博士的ssd介绍视频（虽然不太详细，不过结合讲义思路很清晰，参见：『MXNet』第十弹_物体检测SSD）。
重点说明
SSD架构主要有四个部分，网络设计、搜索框设计、学习目标处理、损失函数实现。
网络设计
重点在于正常前向网络中挑选出的特征层分别添加两个卷积出口：分类和回归出口，用于对应后面的每个搜索框的各个类别得分、以及4个坐标值。
搜索框设计
对应网络的特征层：每个层有若干搜索框，我们需要搜索框位置形状信息。对于tf版本我们保存了每个框的中心点以及HW信息，而mx版本我们保存的是左上右下两个的4个坐标数值，mx更为直观，但是tf版本节省空间：一组框对应同一个中心点，不过搜索框信息量不大，b无伤大雅。
学习目标处理
个人感觉最为繁琐，我们需要的的信息包含（此时已经获得了）：一组搜索框（实际上指的是全部搜索框的n4个坐标值），图片的label、图片的真实框坐标(对应label数目4)，我们需要的就是找到搜索框和真是图片的标签联系，
获取：
每个搜索框对应的分类（和哪个真实框的IOU最大就选真实框的类别标注给该搜索，也就是说会出现大量的0 class搜索框）
每个搜索框的坐标的回归目标（同上的寻找方法，空位也为0）
负类掩码，虽然每张图片里面通常只有几个标注的边框，但SSD会生成大量的锚框。可以想象很多锚框都不会框住感兴趣的物体，就是说跟任何对应感兴趣物体的表框的IoU都小于某个阈值。这样就会产生大量的负类锚框，或者说对应标号为0的锚框。对于这类锚框有两点要考虑的：
1、边框预测的损失函数不应该包括负类锚框，因为它们并没有对应的真实边框
2、因为负类锚框数目可能远多于其他，我们可以只保留其中的一些。而且是保留那些目前预测最不确信它是负类的，就是对类0预测值排序，选取数值最小的哪一些困难的负类锚框
所以需要使用掩码，抑制一部分计算出来的loss。
损失函数
可讲的不多，按照公式实现即可，重点也在上一步计算出来的掩码处理损失函数值一步。
MXNet训练主函数
if __name__ == ‘__main__‘: ???batch_size = 4 ???ctx = mx.cpu(0) ???# ctx = mx.gpu(0) ???# box_metric = mx.MAE() ???cls_metric = mx.metric.Accuracy() ???ssd = ssd_mx.SSDNet() ???ssd.initialize(ctx=ctx) ?# mx.init.Xavier(magnitude=2) ???cls_loss = util_mx.FocalLoss() ???box_loss = util_mx.SmoothL1Loss() ???trainer = mx.gluon.Trainer(ssd.collect_params(), ??????????????????????????????‘sgd‘, {‘learning_rate‘: 0.01, ‘wd‘: 5e-4}) ???data = get_iterators(data_shape=304, batch_size=batch_size) ???for epoch in range(30): ???????# reset data iterators and metrics ???????data.reset() ???????cls_metric.reset() ???????# box_metric.reset() ???????tic = time.time() ???????for i, batch in enumerate(data): ???????????start_time = time.time() ???????????x = batch.data[0].as_in_context(ctx) ???????????y = batch.label[0].as_in_context(ctx) ???????????# 将-1占位符改为背景标签0，对应坐标框记录为[0,0,0,0] ???????????y = nd.where(y < 0, nd.zeros_like(y), y) ???????????with mx.autograd.record(): ???????????????# anchors, 检测框坐标，[1，n，4] ???????????????# class_preds, 各图片各检测框分类情况，[bs，n，num_cls + 1] ???????????????# box_preds, 各图片检测框坐标预测情况，[bs, n * 4] ???????????????anchors, class_preds, box_preds = ssd(x, True) ???????????????# box_target, 检测框的收敛目标，[bs, n * 4] ???????????????# box_mask, 隐藏不需要的背景类，[bs, n * 4] ???????????????# cls_target, 记录全检测框的真实类别，[bs，n] ???????????????box_target, box_mask, cls_target = ssd_mx.training_targets(anchors, class_preds, y) ???????????????loss1 = cls_loss(class_preds, cls_target) ???????????????loss2 = box_loss(box_preds, box_target, box_mask) ???????????????loss = loss1 + loss2 ???????????loss.backward() ???????????trainer.step(batch_size) ???????????if i % 1 == 0: ???????????????duration = time.time() - start_time ???????????????examples_per_sec = batch_size / duration ???????????????sec_per_batch = float(duration) ???????????????format_str = "[*] step %d, ?loss=%.2f (%.1f examples/sec; %.3f sec/batch)" ???????????????print(format_str % (i, nd.sum(loss).asscalar(), examples_per_sec, sec_per_batch)) ???????????if i % 500 == 0:ssd.model.save_parameters(‘model_mx_{}.params‘.format(epoch))TensorFlow训练主函数
def main(): ???max_steps = 1500 ???batch_size = 32 ???adam_beta1 = 0.9 ???adam_beta2 = 0.999 ???opt_epsilon = 1.0 ???num_epochs_per_decay = 2.0 ???num_samples_per_epoch = 17125 ???moving_average_decay = None ???tf.logging.set_verbosity(tf.logging.DEBUG) ???with tf.Graph().as_default(): ???????# Create global_step. ???????with tf.device("/device:CPU:0"): ???????????global_step = tf.train.create_global_step() ???????ssd = SSDNet() ???????ssd_anchors = ssd.anchors ???????# tfr解析操作放在GPU下有加速，效果不稳定 ???????dataset = ????????????tfr_data_process.get_split(‘./TFR_Data‘, ??????????????????????????????????????‘voc2012_*.tfrecord‘, ??????????????????????????????????????num_classes=21, ??????????????????????????????????????num_samples=num_samples_per_epoch) ???????with tf.device("/device:CPU:0"): ?# 仅CPU支持队列操作 ???????????image, glabels, gbboxes = ????????????????tfr_data_process.tfr_read(dataset) ???????????image, glabels, gbboxes = ????????????????preprocess_img_tf.preprocess_image(image, glabels, gbboxes, out_shape=(300, 300)) ???????????gclasses, glocalisations, gscores = ????????????????ssd.bboxes_encode(glabels, gbboxes, ssd_anchors) ???????????batch_shape = [1] + [len(ssd_anchors)] * 3 ?# (1,f层,f层,f层) ???????????# Training batches and queue. ???????????r = tf.train.batch( ?# 图片，中心点类别，真实框坐标，得分 ???????????????util_tf.reshape_list([image, gclasses, glocalisations, gscores]), ???????????????batch_size=batch_size, ???????????????num_threads=4, ???????????????capacity=5 * batch_size) ???????????batch_queue = slim.prefetch_queue.prefetch_queue( ???????????????r, ?# <-----输入格式实际上并不需要调整 ???????????????capacity=2 * 1) ???????# Dequeue batch. ???????b_image, b_gclasses, b_glocalisations, b_gscores = ????????????util_tf.reshape_list(batch_queue.dequeue(), batch_shape) ?# 重整list ???????predictions, localisations, logits, end_points = ????????????ssd.net(b_image, is_training=True, weight_decay=0.00004) ???????ssd.losses(logits, localisations, ??????????????????b_gclasses, b_glocalisations, b_gscores, ??????????????????match_threshold=.5, ??????????????????negative_ratio=3, ??????????????????alpha=1, ??????????????????label_smoothing=.0) ???????update_ops = tf.get_collection(tf.GraphKeys.UPDATE_OPS) ???????# =================================================================== # ???????# Configure the moving averages. ???????# =================================================================== # ???????if moving_average_decay: ???????????moving_average_variables = slim.get_model_variables() ???????????variable_averages = tf.train.ExponentialMovingAverage( ???????????????moving_average_decay, global_step) ???????else: ???????????moving_average_variables, variable_averages = None, None ???????# =================================================================== # ???????# Configure the optimization procedure. ???????# =================================================================== # ???????with tf.device("/device:CPU:0"): ?# learning_rate节点使用CPU（不明） ???????????decay_steps = int(num_samples_per_epoch / batch_size * num_epochs_per_decay) ???????????learning_rate = tf.train.exponential_decay(0.01, ??????????????????????????????????????????????????????global_step, ??????????????????????????????????????????????????????decay_steps, ??????????????????????????????????????????????????????0.94, ?# learning_rate_decay_factor, ??????????????????????????????????????????????????????staircase=True, ??????????????????????????????????????????????????????name=‘exponential_decay_learning_rate‘) ???????????optimizer = tf.train.AdamOptimizer( ???????????????learning_rate, ???????????????beta1=adam_beta1, ???????????????beta2=adam_beta2, ???????????????epsilon=opt_epsilon) ???????????tf.summary.scalar(‘learning_rate‘, learning_rate) ???????if moving_average_decay: ???????????# Update ops executed locally by trainer. ???????????update_ops.append(variable_averages.apply(moving_average_variables)) ???????# Variables to train. ???????trainable_scopes = None ???????if trainable_scopes is None: ???????????variables_to_train = tf.trainable_variables() ???????else: ???????????scopes = [scope.strip() for scope in trainable_scopes.split(‘,‘)] ???????????variables_to_train = [] ???????????for scope in scopes: ???????????????variables = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope) ???????????????variables_to_train.extend(variables) ???????losses = tf.get_collection(tf.GraphKeys.LOSSES) ???????regularization_losses = tf.get_collection( ???????????tf.GraphKeys.REGULARIZATION_LOSSES) ???????regularization_loss = tf.add_n(regularization_losses) ???????loss = tf.add_n(losses) ???????tf.summary.scalar("loss", loss) ???????tf.summary.scalar("regularization_loss", regularization_loss) ???????grad = optimizer.compute_gradients(loss, var_list=variables_to_train) ???????grad_updates = optimizer.apply_gradients(grad, ????????????????????????????????????????????????global_step=global_step) ???????update_ops.append(grad_updates) ???????# update_op = tf.group(*update_ops) ???????with tf.control_dependencies(update_ops): ???????????total_loss = tf.add_n([loss, regularization_loss]) ???????tf.summary.scalar("total_loss", total_loss) ???????# =================================================================== # ???????# Kicks off the training. ???????# =================================================================== # ???????gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.8) ???????config = tf.ConfigProto(log_device_placement=False, ???????????????????????????????gpu_options=gpu_options) ???????saver = tf.train.Saver(max_to_keep=5, ??????????????????????????????keep_checkpoint_every_n_hours=1.0, ??????????????????????????????write_version=2, ??????????????????????????????pad_step_number=False) ???????if True: ???????????import os ???????????import time ???????????print(‘start......‘) ???????????model_path = ‘./logs‘ ???????????batch_size = batch_size ???????????with tf.Session(config=config) as sess: ???????????????summary = tf.summary.merge_all() ???????????????coord = tf.train.Coordinator() ???????????????threads = tf.train.start_queue_runners(sess=sess, coord=coord) ???????????????writer = tf.summary.FileWriter(model_path, sess.graph) ???????????????init_op = tf.group(tf.global_variables_initializer(), ??????????????????????????????????tf.local_variables_initializer()) ???????????????init_op.run() ???????????????for step in range(max_steps): ???????????????????start_time = time.time() ???????????????????loss_value = sess.run(total_loss) ???????????????????# loss_value, summary_str = sess.run([train_tensor, summary_op]) ???????????????????# writer.add_summary(summary_str, step) ???????????????????duration = time.time() - start_time ???????????????????if step % 10 == 0: ???????????????????????summary_str = sess.run(summary) ???????????????????????writer.add_summary(summary_str, step) ???????????????????????examples_per_sec = batch_size / duration ???????????????????????sec_per_batch = float(duration) ???????????????????????format_str = "[*] step %d, ?loss=%.2f (%.1f examples/sec; %.3f sec/batch)" ???????????????????????print(format_str % (step, loss_value, examples_per_sec, sec_per_batch)) ???????????????????# if step % 100 == 0: ???????????????????# ????accuracy_step = test_cifar10(sess, training=False) ???????????????????# ????acc.append(‘{:.3f}‘.format(accuracy_step)) ???????????????????# ????print(acc) ???????????????????if step % 500 == 0 and step != 0: ???????????????????????saver.save(sess, os.path.join(model_path, "ssd_tf.model"), global_step=step) ???????????????coord.request_stop()coord.join(threads)『TensorFlow × MXNet』SSD项目复现经验
原文地址：https://www.cnblogs.com/hellcat/p/9540591.html