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

Posted 大彤小忆

tags:

篇首语:本文由小常识网(cha138.com)小编为大家整理,主要介绍了使用ResNet101作为预训练模型训练Faster-RCNN-TensorFlow-Python3-master相关的知识,希望对你有一定的参考价值。

  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_modeFIXED_BLOCKSPOOLING_SIZEMAX_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_function

import 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 np

from 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 cfg


def 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_sc


class resnetv1(Network):
    def __init__(self, batch_size=1, num_layers=101):
        Network.__init__(self, batch_size=batch_size)
        self._num_layers = num_layers
        self._resnet_scope = 'resnet_v1_%d' % num_layers

    def _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 bboxes
            bottom_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") / width
            y1 = tf.slice(rois, [0, 2], [-1, 1], name="y1") / height
            x2 = tf.slice(rois, [0, 3], [-1, 1], name="x2") / width
            y2 = tf.slice(rois, [0, 4], [-1, 1], name="y2") / height
            # Won't be backpropagated to rois anyway, but to save time
            bboxes = tf.stop_gradient(tf.concat([y1, x1, y2, x2], 1))
            if cfg.FLAGS.MAX_POOL:
                pre_pool_size = cfg.FLAGS.POOLING_SIZE * 2
                crops = 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 1
    def 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 net

    def 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 layers
        if 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 layer
                resnet_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 layer
                resnet_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 supported
            raise 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 == 0
            with 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_conv4
        with tf.variable_scope(self._resnet_scope, self._resnet_scope):
            # build the anchors for the image
            self._anchor_component()

            # rpn
            rpn = 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 size
            rpn_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 reproducibility
                with 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

            # rcnn
            if cfg.FLAGS.pooling_mode == 'crop':
                pool5 = self._crop_pool_layer(net_conv4, rois, "pool5")
            else:
                raise NotImplementedError

        with slim使用 tf slim 重新训练预训练的 ResNet-50 模型以进行分类

如何测量预训练模型(例如 vgg、resnet...)提取的图像特征之间的语义相似度?

Google 对象检测 API - 使用 faster_rcnn_resnet101_coco 模型进行训练

手把手写深度学习(13):如何利用官方预训练模型做微调/迁移学习?(以Resnet50提取图像特征为例)

手把手写深度学习(14):如何利用官方预训练模型做微调/迁移学习?(以Resnet50提取图像特征为例)

在 torchvision.models.resnet34 中训练 resnet 预训练模型时,Pytorch 如何在 ImageNet 中处理图像?