使用ResNet101作为预训练模型训练Faster-RCNN-TensorFlow-Python3-master

使用VGG16作为预训练模型训练Faster-RCNN-TensorFlow-Python3-master的详细步骤→Windows10+Faster-RCNN-TensorFlow-Python3-master+VOC2007数据集。

如果使用ResNet101作为预训练模型训练Faster-RCNN-TensorFlow-Python3-master，在之前使用VGG16作为预训练模型的训练步骤基础上需要修改几个地方。

第一个，在之前的第6步时，改为下载预训练模型ResNet101，在./data文件夹下新建文件夹imagenet_weights，将下载好的resnet_v1_101_2016_08_28.tar.gz解压到./data/imagenet_weights路径下，并将resnet_v1_101.ckpt重命名为resnet101.ckpt。
第二个，在之前的第7步时，除了修改最大迭代次数max_iters参数和迭代多少次保存一次模型snap_iterations参数之外，还需要修改以下几个参数。
① 将network参数由vgg16改为resnet101

② 将pretrained_model参数由./data/imagenet_weights/vgg16.ckpt改为./data/imagenet_weights/resnet101.ckpt

③ 增加pooling_mode、FIXED_BLOCKS、POOLING_SIZE、MAX_POOL四个参数

tf.app.flags.DEFINE_string('network', "resnet101", "The network to be used as backbone")

tf.app.flags.DEFINE_string('pretrained_model', "./data/imagenet_weights/resnet101.ckpt", "Pretrained network weights")

# ResNet options
tf.app.flags.DEFINE_string('pooling_mode', "crop", "Default pooling mode")
tf.app.flags.DEFINE_integer('FIXED_BLOCKS', 1, "Number of fixed blocks during training")
tf.app.flags.DEFINE_integer('POOLING_SIZE', 7, "Size of the pooled region after RoI pooling")
tf.app.flags.DEFINE_boolean('MAX_POOL', False, "Whether to append max-pooling after crop_and_resize")

第三个，对resnet_v1.py文件进行修改，用下面的代码替换原文件中的代码。

# --------------------------------------------------------
# Tensorflow Faster R-CNN
# Licensed under The MIT License [see LICENSE for details]
# Written by Zheqi He and Xinlei Chen
# --------------------------------------------------------
from __future__ import absolute_import
from __future__ import division
from __future__ import print_functionimport tensorflow as tf
import tensorflow.contrib.slim as slim
from tensorflow.contrib.slim import losses
from tensorflow.contrib.slim import arg_scope
from tensorflow.contrib.slim.python.slim.nets import resnet_utils
from tensorflow.contrib.slim.python.slim.nets import resnet_v1
import numpy as npfrom lib.nets.network import Network
from tensorflow.python.framework import ops
from tensorflow.contrib.layers.python.layers import regularizers
from tensorflow.python.ops import nn_ops
from tensorflow.contrib.layers.python.layers import initializers
from tensorflow.contrib.layers.python.layers import layers
from lib.config import config as cfgdef resnet_arg_scope(is_training=True,weight_decay=cfg.FLAGS.weight_decay,# weight_decay=cfg.TRAIN.WEIGHT_DECAY,batch_norm_decay=0.997,batch_norm_epsilon=1e-5,batch_norm_scale=True):batch_norm_params = {# NOTE 'is_training' here does not work because inside resnet it gets reset:# https://github.com/tensorflow/models/blob/master/slim/nets/resnet_v1.py#L187'is_training': False,'decay': batch_norm_decay,'epsilon': batch_norm_epsilon,'scale': batch_norm_scale,'trainable': False,'updates_collections': ops.GraphKeys.UPDATE_OPS}with arg_scope([slim.conv2d],weights_regularizer=regularizers.l2_regularizer(weight_decay),weights_initializer=initializers.variance_scaling_initializer(),trainable=is_training,activation_fn=nn_ops.relu,normalizer_fn=layers.batch_norm,normalizer_params=batch_norm_params):with arg_scope([layers.batch_norm], **batch_norm_params) as arg_sc:return arg_scclass resnetv1(Network):def __init__(self, batch_size=1, num_layers=101):Network.__init__(self, batch_size=batch_size)self._num_layers = num_layersself._resnet_scope = 'resnet_v1_%d' % num_layersdef _crop_pool_layer(self, bottom, rois, name):with tf.variable_scope(name) as scope:batch_ids = tf.squeeze(tf.slice(rois, [0, 0], [-1, 1], name="batch_id"), [1])# Get the normalized coordinates of bboxesbottom_shape = tf.shape(bottom)height = (tf.to_float(bottom_shape[1]) - 1.) * np.float32(self._feat_stride[0])width = (tf.to_float(bottom_shape[2]) - 1.) * np.float32(self._feat_stride[0])x1 = tf.slice(rois, [0, 1], [-1, 1], name="x1") / widthy1 = tf.slice(rois, [0, 2], [-1, 1], name="y1") / heightx2 = tf.slice(rois, [0, 3], [-1, 1], name="x2") / widthy2 = tf.slice(rois, [0, 4], [-1, 1], name="y2") / height# Won't be backpropagated to rois anyway, but to save timebboxes = tf.stop_gradient(tf.concat([y1, x1, y2, x2], 1))if cfg.FLAGS.MAX_POOL:pre_pool_size = cfg.FLAGS.POOLING_SIZE * 2crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids), [pre_pool_size, pre_pool_size],name="crops")crops = slim.max_pool2d(crops, [2, 2], padding='SAME')else:crops = tf.image.crop_and_resize(bottom, bboxes, tf.to_int32(batch_ids),[cfg.FLAGS.POOLING_SIZE, cfg.FLAGS.POOLING_SIZE],name="crops")return crops# Do the first few layers manually, because 'SAME' padding can behave inconsistently# for images of different sizes: sometimes 0, sometimes 1def build_base(self):with tf.variable_scope(self._resnet_scope, self._resnet_scope):net = resnet_utils.conv2d_same(self._image, 64, 7, stride=2, scope='conv1')net = tf.pad(net, [[0, 0], [1, 1], [1, 1], [0, 0]])net = slim.max_pool2d(net, [3, 3], stride=2, padding='VALID', scope='pool1')return netdef build_network(self, sess, is_training=True):# select initializers# if cfg.TRAIN.TRUNCATED:if cfg.FLAGS.initializer == "truncated":initializer = tf.truncated_normal_initializer(mean=0.0, stddev=0.01)initializer_bbox = tf.truncated_normal_initializer(mean=0.0, stddev=0.001)else:initializer = tf.random_normal_initializer(mean=0.0, stddev=0.01)initializer_bbox = tf.random_normal_initializer(mean=0.0, stddev=0.001)bottleneck = resnet_v1.bottleneck# choose different blocks for different number of layersif self._num_layers == 50:blocks = [resnet_utils.Block('block1', bottleneck,[(256, 64, 1)] * 2 + [(256, 64, 2)]),resnet_utils.Block('block2', bottleneck,[(512, 128, 1)] * 3 + [(512, 128, 2)]),# Use stride-1 for the last conv4 layerresnet_utils.Block('block3', bottleneck,[(1024, 256, 1)] * 5 + [(1024, 256, 1)]),resnet_utils.Block('block4', bottleneck, [(2048, 512, 1)] * 3)]elif self._num_layers == 101:# blocks = [#     resnet_utils.Block('block1', bottleneck,#                        [(256, 64, 1)] * 2 + [(256, 64, 2)]),#     resnet_utils.Block('block2', bottleneck,#                        [(512, 128, 1)] * 3 + [(512, 128, 2)]),#     # Use stride-1 for the last conv4 layer#     resnet_utils.Block('block3', bottleneck,#                        [(1024, 256, 1)] * 22 + [(1024, 256, 1)]),#     resnet_utils.Block('block4', bottleneck, [(2048, 512, 1)] * 3)# ]blocks = [resnet_v1.resnet_v1_block('block1', base_depth=64, num_units=3, stride=2),resnet_v1.resnet_v1_block('block2', base_depth=128, num_units=4, stride=2),resnet_v1.resnet_v1_block('block3', base_depth=256, num_units=23, stride=1),resnet_v1.resnet_v1_block('block4', base_depth=512, num_units=3, stride=1),]elif self._num_layers == 152:blocks = [resnet_utils.Block('block1', bottleneck,[(256, 64, 1)] * 2 + [(256, 64, 2)]),resnet_utils.Block('block2', bottleneck,[(512, 128, 1)] * 7 + [(512, 128, 2)]),# Use stride-1 for the last conv4 layerresnet_utils.Block('block3', bottleneck,[(1024, 256, 1)] * 35 + [(1024, 256, 1)]),resnet_utils.Block('block4', bottleneck, [(2048, 512, 1)] * 3)]else:# other numbers are not supportedraise NotImplementedError# assert (0 <= cfg.RESNET.FIXED_BLOCKS < 4)assert (0 <= cfg.FLAGS.FIXED_BLOCKS < 4)if cfg.FLAGS.FIXED_BLOCKS == 3:with slim.arg_scope(resnet_arg_scope(is_training=False)):net = self.build_base()net_conv4, _ = resnet_v1.resnet_v1(net,blocks[0:cfg.FLAGS.FIXED_BLOCKS],global_pool=False,include_root_block=False,scope=self._resnet_scope)elif cfg.FLAGS.FIXED_BLOCKS > 0:with slim.arg_scope(resnet_arg_scope(is_training=False)):net = self.build_base()net, _ = resnet_v1.resnet_v1(net,blocks[0:cfg.FLAGS.FIXED_BLOCKS],global_pool=False,include_root_block=False,scope=self._resnet_scope)with slim.arg_scope(resnet_arg_scope(is_training=is_training)):net_conv4, _ = resnet_v1.resnet_v1(net,blocks[cfg.FLAGS.FIXED_BLOCKS:-1],global_pool=False,include_root_block=False,scope=self._resnet_scope)else:  # cfg.RESNET.FIXED_BLOCKS == 0with slim.arg_scope(resnet_arg_scope(is_training=is_training)):net = self.build_base()net_conv4, _ = resnet_v1.resnet_v1(net,blocks[0:-1],global_pool=False,include_root_block=False,scope=self._resnet_scope)self._act_summaries.append(net_conv4)self._layers['head'] = net_conv4with tf.variable_scope(self._resnet_scope, self._resnet_scope):# build the anchors for the imageself._anchor_component()# rpnrpn = slim.conv2d(net_conv4, 512, [3, 3], trainable=is_training, weights_initializer=initializer,scope="rpn_conv/3x3")self._act_summaries.append(rpn)rpn_cls_score = slim.conv2d(rpn, self._num_anchors * 2, [1, 1], trainable=is_training,weights_initializer=initializer,padding='VALID', activation_fn=None, scope='rpn_cls_score')# change it so that the score has 2 as its channel sizerpn_cls_score_reshape = self._reshape_layer(rpn_cls_score, 2, 'rpn_cls_score_reshape')rpn_cls_prob_reshape = self._softmax_layer(rpn_cls_score_reshape, "rpn_cls_prob_reshape")rpn_cls_prob = self._reshape_layer(rpn_cls_prob_reshape, self._num_anchors * 2, "rpn_cls_prob")rpn_bbox_pred = slim.conv2d(rpn, self._num_anchors * 4, [1, 1], trainable=is_training,weights_initializer=initializer,padding='VALID', activation_fn=None, scope='rpn_bbox_pred')if is_training:rois, roi_scores = self._proposal_layer(rpn_cls_prob, rpn_bbox_pred, "rois")rpn_labels = self._anchor_target_layer(rpn_cls_score, "anchor")# Try to have a determinestic order for the computing graph, for reproducibilitywith tf.control_dependencies([rpn_labels]):rois, _ = self._proposal_target_layer(rois, roi_scores, "rpn_rois")else:# if cfg.TEST.MODE == 'nms':if cfg.FLAGS.test_mode == "nms":rois, _ = self._proposal_layer(rpn_cls_prob, rpn_bbox_pred, "rois")# elif cfg.TEST.MODE == 'top':elif cfg.FLAGS.test_mode == "top":rois, _ = self._proposal_top_layer(rpn_cls_prob, rpn_bbox_pred, "rois")else:raise NotImplementedError# rcnnif cfg.FLAGS.pooling_mode == 'crop':pool5 = self._crop_pool_layer(net_conv4, rois, "pool5")else:raise NotImplementedErrorwith slim.arg_scope(resnet_arg_scope(is_training=is_training)):fc7, _ = resnet_v1.resnet_v1(pool5,blocks[-1:],global_pool=False,include_root_block=False,scope=self._resnet_scope)with tf.variable_scope(self._resnet_scope, self._resnet_scope):# Average pooling done by reduce_meanfc7 = tf.reduce_mean(fc7, axis=[1, 2])cls_score = slim.fully_connected(fc7, self._num_classes, weights_initializer=initializer,trainable=is_training, activation_fn=None, scope='cls_score')cls_prob = self._softmax_layer(cls_score, "cls_prob")bbox_pred = slim.fully_connected(fc7, self._num_classes * 4, weights_initializer=initializer_bbox,trainable=is_training,activation_fn=None, scope='bbox_pred')self._predictions["rpn_cls_score"] = rpn_cls_scoreself._predictions["rpn_cls_score_reshape"] = rpn_cls_score_reshapeself._predictions["rpn_cls_prob"] = rpn_cls_probself._predictions["rpn_bbox_pred"] = rpn_bbox_predself._predictions["cls_score"] = cls_scoreself._predictions["cls_prob"] = cls_probself._predictions["bbox_pred"] = bbox_predself._predictions["rois"] = roisself._score_summaries.update(self._predictions)return rois, cls_prob, bbox_preddef get_variables_to_restore(self, variables, var_keep_dic):variables_to_restore = []for v in variables:# exclude the first conv layer to swap RGB to BGRif v.name == (self._resnet_scope + '/conv1/weights:0'):self._variables_to_fix[v.name] = vcontinueif v.name.split(':')[0] in var_keep_dic:print('Varibles restored: %s' % v.name)variables_to_restore.append(v)return variables_to_restoredef fix_variables(self, sess, pretrained_model):print('Fix Resnet V1 layers..')with tf.variable_scope('Fix_Resnet_V1') as scope:with tf.device("/cpu:0"):# fix RGB to BGRconv1_rgb = tf.get_variable("conv1_rgb", [7, 7, 3, 64], trainable=False)restorer_fc = tf.train.Saver({self._resnet_scope + "/conv1/weights": conv1_rgb})restorer_fc.restore(sess, pretrained_model)sess.run(tf.assign(self._variables_to_fix[self._resnet_scope + '/conv1/weights:0'],tf.reverse(conv1_rgb, [2])))

第四个，在之前的第9步时，点击Run 'train'开始训练之前先修改train.py代码的如下几个地方。

# 添加的代码（使用resnet101作为预训练模型）
from lib.nets.resnet_v1 import resnetv1
# 添加结束

        # 添加的代码（使用resnet101）if cfg.FLAGS.network == 'resnet101':self.net = resnetv1(batch_size=cfg.FLAGS.ims_per_batch)# 添加结束

        # Store the model snapshotfilename = 'resnet101_faster_rcnn_iter_{:d}'.format(iter) + '.ckpt'filename = os.path.join(self.output_dir, filename)self.saver.save(sess, filename)print('Wrote snapshot to: {:s}'.format(filename))# Also store some meta information, random state, etc.nfilename = 'resnet101_faster_rcnn_iter_{:d}'.format(iter) + '.pkl'nfilename = os.path.join(self.output_dir, nfilename)

经过上面的几步修改后，就可以运行train.py开始训练模型了。
训练时，模型保存的路径是./default/voc_2007_trainval/default，每次保存模型都是保存4个文件，如下图所示。

在这里插入图片描述

相应地，测试时也需要修改几个地方。

第一个，在之前的第12步时，改为新建./output/resnet101/voc_2007_trainval/default文件夹，从./default/voc_2007_trainval/default路径下复制一组模型数据到新建的文件夹下，并将所有文件名改为resnet101.后缀。
第二个，在之前的第13步时，对demo.py再进行如下的修改。

经过上面的几步修改后，就可以运行demo.py开始测试模型了。
在输出PR曲线并计算AP值时，同样也需要修改test_net.py文件中的几个地方，如下图所示。

在这里插入图片描述

# 添加的代码（使用resnet101）
from lib.nets.resnet_v1 import resnetv1
# 添加结束

# NETS = {'vgg16': ('vgg16.ckpt',)}  # 自己需要修改：训练输出模型
NETS = {'resnet101': ('resnet101.ckpt',)}  # 自己需要修改：训练输出模型

经过上面的几步修改后，就可以运行test_net.py来输出PR曲线并计算AP值了。

使用ResNet101作为预训练模型训练Faster-RCNN-TensorFlow-Python3-master

相关文章

TensorRT学习笔记--基于FCN-ResNet101推理引擎实现语义分割

迁移学习之ResNet50和ResNet101（图像识别）

Mask-RCNN(2)Resnet101

Pytorch-预训练网络

基于ResNet-101深度学习网络的图像目标识别算法matlab仿真

【深度学习】ResNet网络详解

【使用Pytorch实现ResNet网络模型：ResNet50、ResNet101和ResNet152】

使用PyTorch搭建ResNet101、ResNet152网络

Java中的数组

java输出数组(java输出数组)

java怎么输出数组(Java怎么给数组赋值)

数组的输入与输出

Java二维数组的输出

Java中数组的输入输出

Java 数组的输入输出

Java中字符串数组的输入与输出

java中打印输出数组内容的三种方式

NTP协议之旅

ntrip协议

Ntrip协议简介