关键词：
【说明】：欢迎加入：faster-rcnn 交流群 238138700，本文分析faster-rcnn 训练的python脚本；
【debug】：我是把__main__修改了下，放在一个自己定义的函数里面，然后调用debug一步步看执行效果的，读者不妨也这样做，可以清晰看到程序是如何运行的；
#!/usr/bin/env python
# --------------------------------------------------------
# Faster R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------
"""Train a Faster R-CNN network using alternating optimization.
This tool implements the alternating optimization algorithm described in our
NIPS 2015 paper ("Faster R-CNN: Towards Real-time Object Detection with Region
Proposal Networks." Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun.)
"""
import _init_paths
from fast_rcnn.train import get_training_roidb, train_net
from fast_rcnn.config import cfg, cfg_from_file, cfg_from_list, get_output_dir
from datasets.factory import get_imdb
from rpn.generate import imdb_proposals
import argparse
import pprint
import numpy as np
import sys, os
import multiprocessing as mp
import cPickle
import shutil
def parse_args():
"""
Parse input arguments
"""
parser = argparse.ArgumentParser(description='Train a Faster R-CNN network')
parser.add_argument('--gpu', dest='gpu_id',
help='GPU device id to use [0]',
default=0, type=int)
parser.add_argument('--net_name', dest='net_name',
help='network name (e.g., "ZF")',
default='ZF', type=str) #qyy
parser.add_argument('--weights', dest='pretrained_model',
help='initialize with pretrained model weights',
default='./data/imagenet_models/ZF.v2.caffemodel', type=str) #qyy
parser.add_argument('--cfg', dest='cfg_file',
help='optional config file',
default='./experiments/cfgs/faster_rcnn_alt_opt.yml', type=str)# qyy
parser.add_argument('--imdb', dest='imdb_name',
help='dataset to train on',
default='voc_2007_trainval', type=str)
parser.add_argument('--set', dest='set_cfgs',
help='set config keys', default=None,
nargs=argparse.REMAINDER)
if len(sys.argv) == 1:
parser.print_help()
sys.exit(1)
args = parser.parse_args()
return args
def get_roidb(imdb_name, rpn_file=None):
imdb = get_imdb(imdb_name)
print 'Loaded dataset `:s` for training'.format(imdb.name)
imdb.set_proposal_method(cfg.TRAIN.PROPOSAL_METHOD)
print 'Set proposal method: :s'.format(cfg.TRAIN.PROPOSAL_METHOD)
if rpn_file is not None:
imdb.config['rpn_file'] = rpn_file
roidb = get_training_roidb(imdb)
return roidb, imdb
def get_solvers(net_name):
# Faster R-CNN Alternating Optimization
n = 'faster_rcnn_alt_opt'
# Solver for each training stage
solvers = [[net_name, n, 'stage1_rpn_solver60k80k.pt'],
[net_name, n, 'stage1_fast_rcnn_solver30k40k.pt'],
[net_name, n, 'stage2_rpn_solver60k80k.pt'],
[net_name, n, 'stage2_fast_rcnn_solver30k40k.pt']]
solvers = [os.path.join(cfg.MODELS_DIR, *s) for s in solvers]
# Iterations for each training stage
max_iters = [80000, 40000, 80000, 40000]
# max_iters = [100, 100, 100, 100]
# Test prototxt for the RPN
rpn_test_prototxt = os.path.join(
cfg.MODELS_DIR, net_name, n, 'rpn_test.pt')
return solvers, max_iters, rpn_test_prototxt
# ------------------------------------------------------------------------------
# Pycaffe doesn't reliably free GPU memory when instantiated nets are discarded
# (e.g. "del net" in Python code). To work around this issue, each training
# stage is executed in a separate process using multiprocessing.Process.
# ------------------------------------------------------------------------------
def _init_caffe(cfg):
"""Initialize pycaffe in a training process.
"""
import caffe
# fix the random seeds (numpy and caffe) for reproducibility
np.random.seed(cfg.RNG_SEED)
caffe.set_random_seed(cfg.RNG_SEED)
# set up caffe
caffe.set_mode_gpu()
caffe.set_device(cfg.GPU_ID)
def train_rpn(queue=None, imdb_name=None, init_model=None, solver=None,
max_iters=None, cfg=None):
"""Train a Region Proposal Network in a separate training process.
"""
#首先进来后继续配置了一些cfg这个对象的一些参数
# Not using any proposals, just ground-truth boxes
cfg.TRAIN.HAS_RPN = True
cfg.TRAIN.BBOX_REG = False # applies only to Fast R-CNN bbox regression
cfg.TRAIN.PROPOSAL_METHOD = 'gt'
cfg.TRAIN.IMS_PER_BATCH = 1
print 'Init model: '.format(init_model) #格式化输出字符串
print('Using config:')
pprint.pprint(cfg)
import caffe
_init_caffe(cfg)
#这里是关键，准备数据集，我们在debug的时候可以发现，imdb是一个类，而roidb是该类的一个成员
roidb, imdb = get_roidb(imdb_name)#我们进入这个数据准备的函数看看
print 'roidb len: '.format(len(roidb))
output_dir = get_output_dir(imdb)
print 'Output will be saved to `:s`'.format(output_dir)
#这个solver传入的是./models/pascal_voc/ZF/faster_rcnn_alt_opt/stage1_rpn_solver60k80k.pt
model_paths = train_net(solver, roidb, output_dir,
pretrained_model=init_model,
max_iters=max_iters) #进入train_net函数，看训练如何实现的
# Cleanup all but the final model
for i in model_paths[:-1]: #把训练过程中保存的中间结果的模型删掉，只返回最终模型的结果
os.remove(i)
rpn_model_path = model_paths[-1]
# Send final model path through the multiprocessing queue
queue.put('model_path': rpn_model_path) #通过队列将该进程运行的模型结果的路径返回
#这个函数利用rpn网络来生成proposals的
def rpn_generate(queue=None, imdb_name=None, rpn_model_path=None, cfg=None,
rpn_test_prototxt=None):
"""Use a trained RPN to generate proposals.
"""
cfg.TEST.RPN_PRE_NMS_TOP_N = -1 # no pre NMS filtering
cfg.TEST.RPN_POST_NMS_TOP_N = 2000 # limit top boxes after NMS
print 'RPN model: '.format(rpn_model_path)
print('Using config:')
pprint.pprint(cfg)
import caffe
_init_caffe(cfg)
# NOTE: the matlab implementation computes proposals on flipped images, too.
# We compute them on the image once and then flip the already computed
# proposals. This might cause a minor loss in mAP (less proposal jittering).
imdb = get_imdb(imdb_name)
print 'Loaded dataset `:s` for proposal generation'.format(imdb.name)
# Load RPN and configure output directory
rpn_net = caffe.Net(rpn_test_prototxt, rpn_model_path, caffe.TEST)
output_dir = get_output_dir(imdb)
print 'Output will be saved to `:s`'.format(output_dir)
# Generate proposals on the imdb
rpn_proposals = imdb_proposals(rpn_net, imdb)
# Write proposals to disk and send the proposal file path through the
# multiprocessing queue
rpn_net_name = os.path.splitext(os.path.basename(rpn_model_path))[0]
rpn_proposals_path = os.path.join(
output_dir, rpn_net_name + '_proposals.pkl')
with open(rpn_proposals_path, 'wb') as f:
cPickle.dump(rpn_proposals, f, cPickle.HIGHEST_PROTOCOL)
print 'Wrote RPN proposals to '.format(rpn_proposals_path)
queue.put('proposal_path': rpn_proposals_path)
#这个函数是用来训练检测网络的
def train_fast_rcnn(queue=None, imdb_name=None, init_model=None, solver=None,
max_iters=None, cfg=None, rpn_file=None):
"""Train a Fast R-CNN using proposals generated by an RPN.
"""
cfg.TRAIN.HAS_RPN = False # not generating prosals on-the-fly
cfg.TRAIN.PROPOSAL_METHOD = 'rpn' # use pre-computed RPN proposals instead
cfg.TRAIN.IMS_PER_BATCH = 2
print 'Init model: '.format(init_model)
print 'RPN proposals: '.format(rpn_file)
print('Using config:')
pprint.pprint(cfg)
import caffe
_init_caffe(cfg)
roidb, imdb = get_roidb(imdb_name, rpn_file=rpn_file)
output_dir = get_output_dir(imdb)
print 'Output will be saved to `:s`'.format(output_dir)
# Train Fast R-CNN
model_paths = train_net(solver, roidb, output_dir,
pretrained_model=init_model,
max_iters=max_iters)
# Cleanup all but the final model
for i in model_paths[:-1]:
os.remove(i)
fast_rcnn_model_path = model_paths[-1]
# Send Fast R-CNN model path over the multiprocessing queue
queue.put('model_path': fast_rcnn_model_path)
if __name__ == '__main__': #建议读者调试这个函数，进去看看每个变量是怎么回事
args = parse_args() #解析系统传入的argv参数，解析完放到args中返回
print('Called with args:')
print(args)
if args.cfg_file is not None:
cfg_from_file(args.cfg_file) #如果输入了这个参数，就调用该函数，应该是做某些配置操作
if args.set_cfgs is not None:
cfg_from_list(args.set_cfgs)
cfg.GPU_ID = args.gpu_id # cfg是一个词典（edict）数据结构，从faster-rcnn.config引入的
# --------------------------------------------------------------------------
# Pycaffe doesn't reliably free GPU memory when instantiated nets are
# discarded (e.g. "del net" in Python code). To work around this issue, each
# training stage is executed in a separate process using
# multiprocessing.Process. #这里说的要使用多进程,因为在pycaffe中当某个网络被discard后，不能可靠保证释放内存资源；进程关闭后资源自然会释放
# --------------------------------------------------------------------------
# queue for communicated results between processes
mp_queue = mp.Queue() #mp指的是multiprocessing库，所以这里返回了一个用于多进程通信的队列对象
# solves, iters, etc. for each training stage
solvers, max_iters, rpn_test_prototxt = get_solvers(args.net_name) #这里返回了solvers的路径，maxiters的值，rpn_test_prototxt的路径
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
print 'Stage 1 RPN, init from ImageNet model'
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
# 这一步是用imageNet的模型初始化，然后训练rpn网络（整个训练过程可以参考作者的论文）
cfg.TRAIN.SNAPSHOT_INFIX = 'stage1'
mp_kwargs = dict(
queue=mp_queue,
imdb_name=args.imdb_name,
init_model=args.pretrained_model,
solver=solvers[0],
max_iters=max_iters[0],
cfg=cfg) # 这里把该阶段需要的参数都放到这里来了，即函数train_rpn的输入参数
p = mp.Process(target=train_rpn, kwargs=mp_kwargs) # 显然，这里准备启动一个新进程，调用函数train_rpn，传入参数kwargs，所以我们进入train_rpn函数看看是如何工作的
p.start()
rpn_stage1_out = mp_queue.get()
p.join()
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
print 'Stage 1 RPN, generate proposals'
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
# 这一步是利用上一步训练好的rpn网络，产生proposals供后面使用
mp_kwargs = dict(
queue=mp_queue,
imdb_name=args.imdb_name,
rpn_model_path=str(rpn_stage1_out['model_path']),
cfg=cfg,
rpn_test_prototxt=rpn_test_prototxt)
p = mp.Process(target=rpn_generate, kwargs=mp_kwargs)
p.start()
rpn_stage1_out['proposal_path'] = mp_queue.get()['proposal_path']
p.join()
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
print 'Stage 1 Fast R-CNN using RPN proposals, init from ImageNet model'
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
#这一步是再次用imageNet的模型初始化前5层卷积层，然后用上一步得到的proposals训练检测网络
cfg.TRAIN.SNAPSHOT_INFIX = 'stage1'
mp_kwargs = dict(
queue=mp_queue,
imdb_name=args.imdb_name,
init_model=args.pretrained_model,
solver=solvers[1],
max_iters=max_iters[1],
cfg=cfg,
rpn_file=rpn_stage1_out['proposal_path'])
p = mp.Process(target=train_fast_rcnn, kwargs=mp_kwargs)
p.start()
fast_rcnn_stage1_out = mp_queue.get()
p.join()
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
print 'Stage 2 RPN, init from stage 1 Fast R-CNN model'
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
#这一步固定上一步训练好的前五层卷积层，再次训练RPN，这样就得到最终RPN网络的参数了
cfg.TRAIN.SNAPSHOT_INFIX = 'stage2'
mp_kwargs = dict(
queue=mp_queue,
imdb_name=args.imdb_name,
init_model=str(fast_rcnn_stage1_out['model_path']),
solver=solvers[2],
max_iters=max_iters[2],
cfg=cfg)
p = mp.Process(target=train_rpn, kwargs=mp_kwargs)
p.start()
rpn_stage2_out = mp_queue.get()
p.join()
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
print 'Stage 2 RPN, generate proposals'
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
#利用最终确定的RPN网络产生proposals
mp_kwargs = dict(
queue=mp_queue,
imdb_name=args.imdb_name,
rpn_model_path=str(rpn_stage2_out['model_path']),
cfg=cfg,
rpn_test_prototxt=rpn_test_prototxt)
p = mp.Process(target=rpn_generate, kwargs=mp_kwargs)
p.start()
rpn_stage2_out['proposal_path'] = mp_queue.get()['proposal_path']
p.join()
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
print 'Stage 2 Fast R-CNN, init from stage 2 RPN R-CNN model'
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
#利用上一步产生的proposals，训练出最终的检测网络
cfg.TRAIN.SNAPSHOT_INFIX = 'stage2'
mp_kwargs = dict(
queue=mp_queue,
imdb_name=args.imdb_name,
init_model=str(rpn_stage2_out['model_path']),
solver=solvers[3],
max_iters=max_iters[3],
cfg=cfg,
rpn_file=rpn_stage2_out['proposal_path'])
p = mp.Process(target=train_fast_rcnn, kwargs=mp_kwargs)
p.start()
fast_rcnn_stage2_out = mp_queue.get()
p.join()
# Create final model (just a copy of the last stage)
final_path = os.path.join(
os.path.dirname(fast_rcnn_stage2_out['model_path']),
args.net_name + '_faster_rcnn_final.caffemodel')
print 'cp -> '.format(
fast_rcnn_stage2_out['model_path'], final_path)
shutil.copy(fast_rcnn_stage2_out['model_path'], final_path)
print 'Final model: '.format(final_path)
分析上面训练调用的函数train_net，该函数位于：./lib/fast_rcnn/train.py文件中
# --------------------------------------------------------
# Fast R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------
"""Train a Fast R-CNN network."""
import caffe
from fast_rcnn.config import cfg
import roi_data_layer.roidb as rdl_roidb
from utils.timer import Timer
import numpy as np
import os
from caffe.proto import caffe_pb2
import google.protobuf as pb2
class SolverWrapper(object):
"""A simple wrapper around Caffe's solver.
This wrapper gives us control over he snapshotting process, which we
use to unnormalize the learned bounding-box regression weights.
"""
#这就是SolverWrapper的构造函数
def __init__(self, solver_prototxt, roidb, output_dir,
pretrained_model=None):
"""Initialize the SolverWrapper."""
self.output_dir = output_dir
if (cfg.TRAIN.HAS_RPN and cfg.TRAIN.BBOX_REG and
cfg.TRAIN.BBOX_NORMALIZE_TARGETS):
# RPN can only use precomputed normalization because there are no
# fixed statistics to compute a priori
assert cfg.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED
if cfg.TRAIN.BBOX_REG:
print 'Computing bounding-box regression targets...'
self.bbox_means, self.bbox_stds = \\
rdl_roidb.add_bbox_regression_targets(roidb)
print 'done'
# 这句话调用了caffe的SGDSolver，这个是caffe在C++中实现的一个类，用来进行随机梯度下降优化，该类根据solver_prototxt中定义的网络和求解参数，完成网络
# 初始化，然后返回类SGDSolver的一个实例，关于该类的设计可以参考caffe的网站：http://caffe.berkeleyvision.org/doxygen/classcaffe_1_1SGDSolver.html
# 然后作者把该对象作为SolverWrapper的一个成员，命名为solver
self.solver = caffe.SGDSolver(solver_prototxt)
if pretrained_model is not None:
print ('Loading pretrained model '
'weights from :s').format(pretrained_model)
self.solver.net.copy_from(pretrained_model)#这句话完成对网络的初始化
self.solver_param = caffe_pb2.SolverParameter()
with open(solver_prototxt, 'rt') as f:
pb2.text_format.Merge(f.read(), self.solver_param)#这句话应该是设置了self.solver_param这个成员的参数
self.solver.net.layers[0].set_roidb(roidb)#这句话传入训练的数据：roidb
def snapshot(self):
"""Take a snapshot of the network after unnormalizing the learned
bounding-box regression weights. This enables easy use at test-time.
"""
net = self.solver.net
scale_bbox_params = (cfg.TRAIN.BBOX_REG and
cfg.TRAIN.BBOX_NORMALIZE_TARGETS and
net.params.has_key('bbox_pred'))
if scale_bbox_params:
# save original values
orig_0 = net.params['bbox_pred'][0].data.copy()
orig_1 = net.params['bbox_pred'][1].data.copy()
# scale and shift with bbox reg unnormalization; then save snapshot
net.params['bbox_pred'][0].data[...] = \\
(net.params['bbox_pred'][0].data *
self.bbox_stds[:, np.newaxis])
net.params['bbox_pred'][1].data[...] = \\
(net.params['bbox_pred'][1].data *
self.bbox_stds + self.bbox_means)
infix = ('_' + cfg.TRAIN.SNAPSHOT_INFIX
if cfg.TRAIN.SNAPSHOT_INFIX != '' else '')
filename = (self.solver_param.snapshot_prefix + infix +
'_iter_:d'.format(self.solver.iter) + '.caffemodel')
filename = os.path.join(self.output_dir, filename)
net.save(str(filename))
print 'Wrote snapshot to: :s'.format(filename)
if scale_bbox_params:
# restore net to original state
net.params['bbox_pred'][0].data[...] = orig_0
net.params['bbox_pred'][1].data[...] = orig_1
return filename
def train_model(self, max_iters):
"""Network training loop."""
last_snapshot_iter = -1
timer = Timer()
model_paths = []
while self.solver.iter < max_iters:
# Make one SGD update
timer.tic()#作者测量一次迭代花的时间
self.solver.step(1)# 做一次梯度下降优化
timer.toc()
if self.solver.iter % (10 * self.solver_param.display) == 0:
print 'speed: :.3fs / iter'.format(timer.average_time)
if self.solver.iter % cfg.TRAIN.SNAPSHOT_ITERS == 0:
last_snapshot_iter = self.solver.iter
model_paths.append(self.snapshot())
if last_snapshot_iter != self.solver.iter:
model_paths.append(self.snapshot())
return model_paths
def get_training_roidb(imdb):
"""Returns a roidb (Region of Interest database) for use in training."""
if cfg.TRAIN.USE_FLIPPED:
print 'Appending horizontally-flipped training examples...'
imdb.append_flipped_images()
print 'done'
print 'Preparing training data...'
rdl_roidb.prepare_roidb(imdb)
print 'done'
return imdb.roidb
def filter_roidb(roidb):
"""Remove roidb entries that have no usable RoIs."""
def is_valid(entry):
# Valid images have:
# (1) At least one foreground RoI OR
# (2) At least one background RoI
overlaps = entry['max_overlaps']
# find boxes with sufficient overlap
fg_inds = np.where(overlaps >= cfg.TRAIN.FG_THRESH)[0]
# Select background RoIs as those within [BG_THRESH_LO, BG_THRESH_HI)
bg_inds = np.where((overlaps < cfg.TRAIN.BG_THRESH_HI) &
(overlaps >= cfg.TRAIN.BG_THRESH_LO))[0]
# image is only valid if such boxes exist
valid = len(fg_inds) > 0 or len(bg_inds) > 0
return valid
num = len(roidb)
filtered_roidb = [entry for entry in roidb if is_valid(entry)]
num_after = len(filtered_roidb)
print 'Filtered roidb entries: -> '.format(num - num_after,
num, num_after)
return filtered_roidb
# 该函数先是调用了该文件中定义的类SolverWrapper的构造函数，返回了该类的一个对象sw，然后调用了sw的train_model方法进行训练
# 传入参数，搭建caffe的网络结构，用预训练模型完成初始化，这些过程就是在该构造函数中实现的，进入这个构造函数看看
def train_net(solver_prototxt, roidb, output_dir,
pretrained_model=None, max_iters=40000):
"""Train a Fast R-CNN network."""
roidb = filter_roidb(roidb)#删除一些不满足要求的输入图片
sw = SolverWrapper(solver_prototxt, roidb, output_dir,
pretrained_model=pretrained_model)#调用构造函数
print 'Solving...'
model_paths = sw.train_model(max_iters)#开始训练模型
print 'done solving'
return model_paths
作者：香蕉麦乐迪--sloanqin--覃元元
fasterrcnn算法训练代码解析(代码片段)
这周看完faster-rcnn后，应该对其源码进行一个解析，以便后面的使用。那首先直接先主函数出发py-faster-rcnn/tools/train_faster_rcnn_alt_opt.py我们在后端的运行命令为python ./py-faster-rcnn/tools/train_faster_rcnn_alt_opt.py--gpu0--net_nameZF--weightsd 查看详情
faster-rcnn之rpn网络的结构解析(代码片段)
【说明】：欢迎加入：faster-rcnn交流群238138700，我想很多人在看faster-rcnn的时候，都会被RPN的网络结构和连接方式纠结，作者在文中说的不是很清晰，这里给出解析；【首先】：大家应该要了解卷积... 查看详情
faster-rcnn之训练数据是如何准备的：imdb和roidb的产生(代码片段)
【说明】：欢迎加入：faster-rcnn交流群238138700，关于imdb和roidb的生成都是在函数train_rpn的中，所以我们从这个函数开始，逐个跟进看如何执行得到我们需要的imdb和roidb：deftrain_rpn(queue=None,imdb_name=None,in... 查看详情
为啥faster-rcnn端到端训练只做近似？
】为啥faster-rcnn端到端训练只做近似？【英文标题】：Whyfaster-rcnnendtoendtrainingonlymakesapproximation?为什么faster-rcnn端到端训练只做近似？【发布时间】：2018-05-0107:07:05【问题描述】：在更快的rcnn(https://arxiv.org/abs/1506.01497)中，有两种... 查看详情
faster-rcnn训练自己的数据集
...n.net/sinat_30071459/article/details/50723212按照下面这个博客修改faster-rcnn源码，训练自己的数据:http://blog.csdn.net/sinat_30071459/article/details/51332084训练自己的数据的时候如果提示assert(boxes[:,2] 查看详情
折腾faster-rcnn（三）--训练篇
...（空格分隔）：Linux深度学习前面，我们已经成功跑起来faster-rcnn，并且自己动手训练了PascalVOC2007图像集，但是笔者接下来继续沿着官方文件跑PascalVOC2012，训练到第二阶段的某个点，程序就开始报错退出。查看logs发现，找不到... 查看详情
如何在faster-rcnn上训练自己的数据集
参考技术A不要发私信 查看详情
faster-rcnn之基于roidbget_minibatch（数据准备操作）(代码片段)
【说明】：欢迎加入：faster-rcnn交流群238138700，这个函数，输入是roidb，根据roidb中给出的图片的信息，读取图片的源文件，然后整理成blobs，供给网络训练使用；defget_minibatch(roidb,num_classes):这个... 查看详情
在自定义数据集上训练 Faster-RCNN 模型时加载检查点
】在自定义数据集上训练Faster-RCNN模型时加载检查点【英文标题】：LoadingcheckpointswhiletrainingaFaster-RCNNmodelonacustomdataset【发布时间】：2021-12-1002:16:09【问题描述】：我正在尝试使用Faster-RCNN架构（准确地说是FasterR-CNNResNet50V1640x640，... 查看详情
深度学习和目标检测系列教程10-300：通过torch训练第一个faster-rcnn模型(代码片段)
@Author：Runsen上次介绍了Faster-RCNN模型，那么今天就开始训练第一个Faster-RCNN模型。本文将展示如何在水果图像数据集上使用Faster-RCNN模型。代码的灵感来自此处的Pytorch文档教程和Kagglehttps://pytorch.org/tutorials/intermediate/torc... 查看详情
faster-rcnn训练自己的数据集——备忘
...。刚刚调通，记下来，以备以后自己少走些弯路。配置py-faster-rcnn没什么好记的，文档也很多。先说下数据集，需要准备三个文件夹：Annotations Images &n 查看详情
转载faster-rcnn+zf用自己的数据集训练模型(matlab版本)
...以看http://blog.csdn.net/sinat_30071459/article/details/50723212） Faster-RCNN源码下载地址：Matlab版本：https://github.com/ShaoqingRen/faster_rcnnPyt 查看详情
pytorch Faster-RCNN 的验证损失
】pytorchFaster-RCNN的验证损失【英文标题】：ValidationlossforpytorchFaster-RCNN【发布时间】：2020-06-0522:10:21【问题描述】：我目前正在使用从pytorch预训练的Faster-RCNN模型（例如在torchvisiontutorial中）的迁移学习对自定义数据集进行对象检... 查看详情
windows下使用自己制作的数据集训练faster-rcnn（tensorflow版）用于目标检测
步骤一下载配置windows下tensorflow版faster-rcnn，参考博客：windows10下运行tensorflow版的faster-Rcnn步骤二制作自己的数据集参考博客：http://blog.csdn.net/u011574296/article/details/78953681步骤三用你的Annotations，Imag 查看详情
深度学习和目标检测系列教程11-300：小麦数据集训练faster-rcnn模型(代码片段)
@Author：Runsen上次训练的Faster-RCNN的数据格式是xml和jpg图片提供，在很多Object-Detection中，数据有的是csv格式，数据集来源：https://www.kaggle.com/c/global-wheat-detectionwidth和heigth是图片的长和宽，b 查看详情
深度学习faster-rcnn网络(代码片段)
目录1网络工作流程1.1数据加载1.2模型加载1.3模型预测过程1.3.1RPN获取候选区域1.3.2FastRCNN进行目标检测2模型结构详解2.1backbone2.2RPN网络2.2.1anchors2.2.2RPN分类2.2.3RPN回归2.2.4Proposal层2.4ROIPooling2.5目标分类与回归3FasterRCNN的训练3.1RPN网络... 查看详情
[语音识别]kaldi--aidatatang_200zh脚本解析:音素训练(代码片段)
...no||exit1;流程：1.apply-cmvn#对feats.scp做归一化处理2.add-deltas#训练数据增加差分量，比如16维度mfcc特征增加2阶差分量后变成48维度2.gmm-init-mono#初始化单音素模型，生成0.mdl、t 查看详情
接口测试脚本之jsoup解析html
第一次接触jsoup还是在处理收货地址的时候，当时在写一个下单流程，需要省市区id以及详细门牌号等等，因此同事介绍了jsoup,闲来无事，在此闲扯一番！1.我们来看下，什么是jsoup,先来看看官方文档是怎么说的：jsoup:JavaHTMLParser... 查看详情