安装
*************************************************************************
###0 安装 git,下载 SSD 安装包
sudo apt-get install git
git clone https://github.com/weiliu89/caffe.git
cd caffe
git checkout ssd
sudo apt-get install python-pip
sudo apt-get install python-numpy
sudo apt-get install python-scipy
pip install cython -i http://pypi.douban.com/simple
pip install eaydict
也可以指定git clone 存放地址
###1 修改Makefile.config文件
复制根目录下的Makefile.config.example为Makefile.config
然后根据自己的系统环境调整相应参数设置
MATLAB_DIR:
PYTHON_INCLUDE:
ablas:
###2 编译
make -j8
make py
make test -j8
make runtest -j8
Error1
如果有多GPU,运行make runtest 可能会出错,这时需要尝试
export CUDA_VISIBLE_DEVICES=0; make runtest -j8
如果出现错误: check failed :error == cudasuccess(10 vs. 0) invalid device ordinal
首先需要确保使用的是特定的GPU,或者尝试
unset CUDA_VISIBLE_DEVICES
Error2
使用caffe时编译出错
include and lib
使用自己机器编译的include和lib (caffe/build/lib, caffe/include)
caffe.pb.h丢失问题:
/home/xxx/caffe/include/caffe/blob.hpp:9:34: fatal error: caffe/proto/caffe.pb.h: No such file or directory
#include "caffe/proto/caffe.pb.h"
解决方法: 用protoc从caffe/src/caffe/proto/caffe.proto生成caffe.pb.h和caffe.pb.cc
li@li:~/caffe/src/caffe/proto$ protoc --cpp_out=/home/xxx/caffe/include/caffe/ caffe.proto
Error3
stdc++
linker error:
/usr/bin/ld: caffe_cnn_handler.o: undefined reference to symbol '_ZNSs4_Rep10_M_destroyERKSaIcE@@GLIBCXX_3.4'
//usr/lib/x86_64-linux-gnu/libstdc++.so.6: error adding symbols: DSO missing from command line
是找不到libstdc++.so.6,解决方法是在Makefile中加入:
LIBS += -L/usr/lib/x86_64-linux-gnu -lstdc++
*************************************************************************
测试
*************************************************************************
###1 下载训练好的模型,放到models/VGGNet/
比如:models_VGGNet_VOC0712_SSD_300x300.tar.gz,解压放到./models/VGGNet
models/VGGNet/VOC0712/SSD_300x300
models/VGGNet/VOC0712/SSD_300X300_webcam
###2 测试
根目录下 运行:
python examples/ssd/score_ssd_pascal.py (数值在0.718左右)
###3 演示
根目录下 运行:
python examles/ssd/ssd_pascal_webcam.py
*************************************************************************
训练
*************************************************************************
###1 制作自己的数据集(与faster rcnn类似)可参考我的另一篇博文:faster rcnn的安装、训练、调试
①新建
(1)data/VOCdevkit/VOC2007新建 Annotations;ImageSets/Main;JPEGImages
说明:
Annotations:保存标签txt转换的xml文件
JPEGImages: 图片文件
ImageSets/Main:文件名列表(不含后缀)
训练集: train.txt
训练验证集: trainval.txt
测试集: test.txt
验证集: val.txt
②拷贝
将data/VOC0712下面的create_list.sh、create_data.sh、labelmap_voc.prototxt拷贝到data/VOCdevkit2007/VOC2007/
③修改接口
**create_list.sh**:修改3处
1.root_dir=$HOME/data/VOCdevkit/
改写为 root_dir=$HOME/caffe/data/VOCdevkit/
2.for name in VOC2007 VOC2012
改写为 for name in VOC2007
3.$bash_dir/../../build/tools/get_image_size
改写为 $HOME/caffe/build/tools/get_image_size
**create_data.sh**修改5处
1.root_dir=$cur_dir/../..
改写为 root_dir=$HOME/caffe
2.data_root_dir="$HOME/data/VOCdevkit"
改写为 data_root_dir="$HOME/caffe/data/VOCdevkit"
3.dataset_name="VOC0712"
改写为 dataset_name="VOC2007"
4.mapfile="$root_dir/data/$dataset_name/labelmap_voc.prototxt"改写为 mapfile="$root_dir/data/VOCdevkit/$dataset_name/labelmap_voc.prototxt"
5.python $root_dir/scripts/create_annoset.py --anno-type=$anno_type --label-map-file=$mapfile --min-dim=$min_dim --max-dim=$max_dim --resize-width=$width --resize-height=$height --check-label $extra_cmd $data_root_dir $root_dir/data/$dataset_name/$subset.txt $data_root_dir/$dataset_name/$db/$dataset_name"_"$subset"_"$db examples/$dataset_name
改写为
python $root_dir/scripts/create_annoset.py --anno-type=$anno_type --label-map-file=$mapfile --min-dim=$min_dim --max-dim=$max_dim --resize-width=$width --resize-height=$height --check-label $extra_cmd $data_root_dir $root_dir/data/VOCdevkit/$dataset_name/$subset.txt $data_root_dir/$dataset_name/$db/$dataset_name"_"$subset"_"$db examples/$dataset_name
**labelmap_voc.prototxt**
需要注意是label需要小写,删除多余的label,保留label=0的背景,以及自己数据的name和label
例如:item {
name: "none_of_the_above"
label: 0
display_name: "background"
}
item {
name: "face"
label: 1
display_name: "face"
}
item {
name: "pedestrian"
label: 2
display_name: "pedestrian"
}
###2 转换成 LMDB 文件
到 ./examples 路径下新建VOC2007文件夹,用于创建LMDB文件软连接
然后到根目录下运行已经修改的sh文件
./data/VOCdevkit/VOC2007/create_list.sh
./data/VOCdevkit/VOC2007/create_data.sh
如果出现: no moudle named caffe/caffe-proto,
则在终端输入:export PYTHONPATH=$PYTHONPATH:/home/**(服务器的名字)/caffe/python
如果依然不行,打开 ./scripts/creta_annosetpy
在import sys后添加以下代码:
import os.path as osp
def add_path(path):
if path not in sys.path:
sys.path.insert(0,path)
caffe_path = osp.join('/home/****/caffe/python')
add_path(caffe_path)
###3如果是直接使用他人已经制作好的LMDB 文件,则只需创建链接文件
到 ./scripts 创建 create_link.py 文件,并粘贴如下代码:
import argparse
import os
import shutil
import subprocess
import sys
from caffe.proto import caffe_pb2
from google.protobuf import text_format
example_dir = '/home/li/caffe/examples/VOC2007'
out_dir = '/home/***/caffe/data/VOCdevkit/VOC2007/lmdb'
lmdb_name = ['VOC2007_test_lmdb', 'VOC2007_trainval_lmdb']
# check example_dir is exist
if not os.path.exists(example_dir):
os.makedirs(example_dir)
for lmdb_sub in lmdb_name:
link_dir = os.path.join(example_dir, lmdb_sub)
# check lin_dir is exist
if os.path.exists(link_dir):
os.unlink(link_dir)
os.symlink(os.path.join(out_dir,lmdb_sub), link_dir)
###4 下载预训练模型
下载预训练模型VGG_ILSVRC_16_layers_fc_reduced.caffemodel,放在 ./models/VGGNet/路径下
需要修改的地方在对应行之后用######标注出来了
from __future__ import print_function
import caffe
from caffe.model_libs import *
from google.protobuf import text_format
import math
import os
import shutil
import stat
import subprocess
import sys
# Add extra layers on top of a "base" network (e.g. VGGNet or Inception).
def AddExtraLayers(net, use_batchnorm=True, lr_mult=1):
use_relu = True
# Add additional convolutional layers.
# 19 x 19
from_layer = net.keys()[-1]
# TODO(weiliu89): Construct the name using the last layer to avoid duplication.
# 10 x 10
out_layer = "conv6_1"
ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 256, 1, 0, 1,
lr_mult=lr_mult)
from_layer = out_layer
out_layer = "conv6_2"
ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 512, 3, 1, 2,
lr_mult=lr_mult)
# 5 x 5
from_layer = out_layer
out_layer = "conv7_1"
ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 128, 1, 0, 1,
lr_mult=lr_mult)
from_layer = out_layer
out_layer = "conv7_2"
ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 256, 3, 1, 2,
lr_mult=lr_mult)
# 3 x 3
from_layer = out_layer
out_layer = "conv8_1"
ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 128, 1, 0, 1,
lr_mult=lr_mult)
from_layer = out_layer
out_layer = "conv8_2"
ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 256, 3, 0, 1,
lr_mult=lr_mult)
# 1 x 1
from_layer = out_layer
out_layer = "conv9_1"
ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 128, 1, 0, 1,
lr_mult=lr_mult)
from_layer = out_layer
out_layer = "conv9_2"
ConvBNLayer(net, from_layer, out_layer, use_batchnorm, use_relu, 256, 3, 0, 1,
lr_mult=lr_mult)
return net
### Modify the following parameters accordingly ###
# The directory which contains the caffe code.
# We assume you are running the script at the CAFFE_ROOT.
caffe_root = os.getcwd()
# Set true if you want to start training right after generating all files.
run_soon = True
# Set true if you want to load from most recently saved snapshot.
# Otherwise, we will load from the pretrain_model defined below.
resume_training = True
# If true, Remove old model files.
remove_old_models = False
# The database file for training data. Created by data/VOC0712/create_data.sh
train_data = "examples/VOC2007/VOC2007_trainval_lmdb"######
# The database file for testing data. Created by data/VOC0712/create_data.sh
test_data = "examples/VOC2007/VOC2007_test_lmdb"######
# Specify the batch sampler.
resize_width = 300
resize_height = 300
resize = "{}x{}".format(resize_width, resize_height)
batch_sampler = [
{
'sampler': {
},
'max_trials': 1,
'max_sample': 1,
},
{
'sampler': {
'min_scale': 0.3,
'max_scale': 1.0,
'min_aspect_ratio': 0.5,
'max_aspect_ratio': 2.0,
},
'sample_constraint': {
'min_jaccard_overlap': 0.1,
},
'max_trials': 50,
'max_sample': 1,
},
{
'sampler': {
'min_scale': 0.3,
'max_scale': 1.0,
'min_aspect_ratio': 0.5,
'max_aspect_ratio': 2.0,
},
'sample_constraint': {
'min_jaccard_overlap': 0.3,
},
'max_trials': 50,
'max_sample': 1,
},
{
'sampler': {
'min_scale': 0.3,
'max_scale': 1.0,
'min_aspect_ratio': 0.5,
'max_aspect_ratio': 2.0,
},
'sample_constraint': {
'min_jaccard_overlap': 0.5,
},
'max_trials': 50,
'max_sample': 1,
},
{
'sampler': {
'min_scale': 0.3,
'max_scale': 1.0,
'min_aspect_ratio': 0.5,
'max_aspect_ratio': 2.0,
},
'sample_constraint': {
'min_jaccard_overlap': 0.7,
},
'max_trials': 50,
'max_sample': 1,
},
{
'sampler': {
'min_scale': 0.3,
'max_scale': 1.0,
'min_aspect_ratio': 0.5,
'max_aspect_ratio': 2.0,
},
'sample_constraint': {
'min_jaccard_overlap': 0.9,
},
'max_trials': 50,
'max_sample': 1,
},
{
'sampler': {
'min_scale': 0.3,
'max_scale': 1.0,
'min_aspect_ratio': 0.5,
'max_aspect_ratio': 2.0,
},
'sample_constraint': {
'max_jaccard_overlap': 1.0,
},
'max_trials': 50,
'max_sample': 1,
},
]
train_transform_param = {
'mirror': True,
'mean_value': [104, 117, 123],
'resize_param': {
'prob': 1,
'resize_mode': P.Resize.WARP,
'height': resize_height,
'width': resize_width,
'interp_mode': [
P.Resize.LINEAR,
P.Resize.AREA,
P.Resize.NEAREST,
P.Resize.CUBIC,
P.Resize.LANCZOS4,
],
},
'distort_param': {
'brightness_prob': 0.5,
'brightness_delta': 32,
'contrast_prob': 0.5,
'contrast_lower': 0.5,
'contrast_upper': 1.5,
'hue_prob': 0.5,
'hue_delta': 18,
'saturation_prob': 0.5,
'saturation_lower': 0.5,
'saturation_upper': 1.5,
'random_order_prob': 0.0,
},
'expand_param': {
'prob': 0.5,
'max_expand_ratio': 4.0,
},
'emit_constraint': {
'emit_type': caffe_pb2.EmitConstraint.CENTER,
}
}
test_transform_param = {
'mean_value': [104, 117, 123],
'resize_param': {
'prob': 1,
'resize_mode': P.Resize.WARP,
'height': resize_height,
'width': resize_width,
'interp_mode': [P.Resize.LINEAR],
},
}
# If true, use batch norm for all newly added layers.
# Currently only the non batch norm version has been tested.
use_batchnorm = False
lr_mult = 1
# Use different initial learning rate.
if use_batchnorm:
base_lr = 0.0004
else:
# A learning rate for batch_size = 1, num_gpus = 1.
base_lr = 0.000004######
# Modify the job name if you want.
job_name = "SSD_{}".format(resize)
# The name of the model. Modify it if you want.
model_name = "VGG_VOC2007_{}".format(job_name)######
# Directory which stores the model .prototxt file.
save_dir = "models/VGGNet/VOC2007/{}".format(job_name)######
# Directory which stores the snapshot of models.
snapshot_dir = "models/VGGNet/VOC2007/{}".format(job_name)######
# Directory which stores the job script and log file.
job_dir = "jobs/VGGNet/VOC2007/{}".format(job_name)######
# Directory which stores the detection results.
output_result_dir = "{}/data/VOCdevkit/results/VOC2007/{}/Main".format(os.environ['HOME'], job_name)######
# model definition files.
train_net_file = "{}/train.prototxt".format(save_dir)
test_net_file = "{}/test.prototxt".format(save_dir)
deploy_net_file = "{}/deploy.prototxt".format(save_dir)
solver_file = "{}/solver.prototxt".format(save_dir)
# snapshot prefix.
snapshot_prefix = "{}/{}".format(snapshot_dir, model_name)
# job script path.
job_file = "{}/{}.sh".format(job_dir, model_name)
# Stores the test image names and sizes. Created by data/VOC0712/create_list.sh
name_size_file = "data/VOCdevkit/VOC2007/test_name_size.txt"######
# The pretrained model. We use the Fully convolutional reduced (atrous) VGGNet.
pretrain_model = "models/VGGNet/VGG_ILSVRC_16_layers_fc_reduced.caffemodel"######
# Stores LabelMapItem.
label_map_file = "data/VOCdevkit/VOC2007/labelmap_voc.prototxt"######
# MultiBoxLoss parameters.
num_classes = 2######
share_location = True
background_label_id=0
train_on_diff_gt = True
normalization_mode = P.Loss.VALID
code_type = P.PriorBox.CENTER_SIZE
ignore_cross_boundary_bbox = False
mining_type = P.MultiBoxLoss.MAX_NEGATIVE
neg_pos_ratio = 3.
loc_weight = (neg_pos_ratio + 1.) / 4.
multibox_loss_param = {
'loc_loss_type': P.MultiBoxLoss.SMOOTH_L1,
'conf_loss_type': P.MultiBoxLoss.SOFTMAX,
'loc_weight': loc_weight,
'num_classes': num_classes,
'share_location': share_location,
'match_type': P.MultiBoxLoss.PER_PREDICTION,
'overlap_threshold': 0.5,
'use_prior_for_matching': True,
'background_label_id': background_label_id,
'use_difficult_gt': train_on_diff_gt,
'mining_type': mining_type,
'neg_pos_ratio': neg_pos_ratio,
'neg_overlap': 0.5,
'code_type': code_type,
'ignore_cross_boundary_bbox': ignore_cross_boundary_bbox,
}
loss_param = {
'normalization': normalization_mode,
}
# parameters for generating priors.
# minimum dimension of input image
min_dim = 300
# conv4_3 ==> 38 x 38
# fc7 ==> 19 x 19
# conv6_2 ==> 10 x 10
# conv7_2 ==> 5 x 5
# conv8_2 ==> 3 x 3
# conv9_2 ==> 1 x 1
mbox_source_layers = ['conv4_3', 'fc7', 'conv6_2', 'conv7_2', 'conv8_2', 'conv9_2']
# in percent %
min_ratio = 20
max_ratio = 90
step = int(math.floor((max_ratio - min_ratio) / (len(mbox_source_layers) - 2)))
min_sizes = []
max_sizes = []
for ratio in xrange(min_ratio, max_ratio + 1, step):
min_sizes.append(min_dim * ratio / 100.)
max_sizes.append(min_dim * (ratio + step) / 100.)
min_sizes = [min_dim * 10 / 100.] + min_sizes
max_sizes = [min_dim * 20 / 100.] + max_sizes
steps = [8, 16, 32, 64, 100, 300]
aspect_ratios = [[2], [2, 3], [2, 3], [2, 3], [2], [2]]
# L2 normalize conv4_3.
normalizations = [20, -1, -1, -1, -1, -1]
# variance used to encode/decode prior bboxes.
if code_type == P.PriorBox.CENTER_SIZE:
prior_variance = [0.1, 0.1, 0.2, 0.2]
else:
prior_variance = [0.1]
flip = True
clip = False
# Solver parameters.
# Defining which GPUs to use.
gpus = "0"######
gpulist = gpus.split(",")
num_gpus = len(gpulist)
# Divide the mini-batch to different GPUs.
batch_size = 32######
accum_batch_size = 32######
iter_size = accum_batch_size / batch_size
solver_mode = P.Solver.CPU
device_id = 0
batch_size_per_device = batch_size
if num_gpus > 0:
batch_size_per_device = int(math.ceil(float(batch_size) / num_gpus))
iter_size = int(math.ceil(float(accum_batch_size) / (batch_size_per_device * num_gpus)))
solver_mode = P.Solver.GPU
device_id = int(gpulist[0])
if normalization_mode == P.Loss.NONE:
base_lr /= batch_size_per_device
elif normalization_mode == P.Loss.VALID:
base_lr *= 25. / loc_weight
elif normalization_mode == P.Loss.FULL:
# Roughly there are 2000 prior bboxes per image.
# TODO(weiliu89): Estimate the exact # of priors.
base_lr *= 2000.
# Evaluate on whole test set.
num_test_image = 15439######
test_batch_size = 8######
test_iter = num_test_image / test_batch_size
solver_param = {
# Train parameters
'base_lr': base_lr,
'weight_decay': 0.0005,
'lr_policy': "multistep",
'stepvalue': [80000, 100000, 120000],
'gamma': 0.1,
'momentum': 0.9,
'iter_size': iter_size,
'max_iter': 120000,
'snapshot': 80000,
'display': 10,
'average_loss': 10,
'type': "SGD",
'solver_mode': solver_mode,
'device_id': device_id,
'debug_info': False,
'snapshot_after_train': True,
# Test parameters
'test_iter': [test_iter],
'test_interval': 10000,
'eval_type': "detection",
'ap_version': "11point",
'test_initialization': False,
}
# parameters for generating detection output.
det_out_param = {
'num_classes': num_classes,
'share_location': share_location,
'background_label_id': background_label_id,
'nms_param': {'nms_threshold': 0.45, 'top_k': 400},
'save_output_param': {
'output_directory': output_result_dir,
'output_name_prefix': "comp4_det_test_",
'output_format': "VOC",
'label_map_file': label_map_file,
'name_size_file': name_size_file,
'num_test_image': num_test_image,
},
'keep_top_k': 200,
'confidence_threshold': 0.01,
'code_type': code_type,
}
# parameters for evaluating detection results.
det_eval_param = {
'num_classes': num_classes,
'background_label_id': background_label_id,
'overlap_threshold': 0.5,
'evaluate_difficult_gt': False,
'name_size_file': name_size_file,
}
### Hopefully you don't need to change the following ###
# Check file.
check_if_exist(train_data)
check_if_exist(test_data)
check_if_exist(label_map_file)
check_if_exist(pretrain_model)
make_if_not_exist(save_dir)
make_if_not_exist(job_dir)
make_if_not_exist(snapshot_dir)
# Create train net.
net = caffe.NetSpec()
net.data, net.label = CreateAnnotatedDataLayer(train_data, batch_size=batch_size_per_device,
train=True, output_label=True, label_map_file=label_map_file,
transform_param=train_transform_param, batch_sampler=batch_sampler)
VGGNetBody(net, from_layer='data', fully_conv=True, reduced=True, dilated=True,
dropout=False)
AddExtraLayers(net, use_batchnorm, lr_mult=lr_mult)
mbox_layers = CreateMultiBoxHead(net, data_layer='data', from_layers=mbox_source_layers,
use_batchnorm=use_batchnorm, min_sizes=min_sizes, max_sizes=max_sizes,
aspect_ratios=aspect_ratios, steps=steps, normalizations=normalizations,
num_classes=num_classes, share_location=share_location, flip=flip, clip=clip,
prior_variance=prior_variance, kernel_size=3, pad=1, lr_mult=lr_mult)
# Create the MultiBoxLossLayer.
name = "mbox_loss"
mbox_layers.append(net.label)
net[name] = L.MultiBoxLoss(*mbox_layers, multibox_loss_param=multibox_loss_param,
loss_param=loss_param, include=dict(phase=caffe_pb2.Phase.Value('TRAIN')),
propagate_down=[True, True, False, False])
with open(train_net_file, 'w') as f:
print('name: "{}_train"'.format(model_name), file=f)
print(net.to_proto(), file=f)
shutil.copy(train_net_file, job_dir)
# Create test net.
net = caffe.NetSpec()
net.data, net.label = CreateAnnotatedDataLayer(test_data, batch_size=test_batch_size,
train=False, output_label=True, label_map_file=label_map_file,
transform_param=test_transform_param)
VGGNetBody(net, from_layer='data', fully_conv=True, reduced=True, dilated=True,
dropout=False)
AddExtraLayers(net, use_batchnorm, lr_mult=lr_mult)
mbox_layers = CreateMultiBoxHead(net, data_layer='data', from_layers=mbox_source_layers,
use_batchnorm=use_batchnorm, min_sizes=min_sizes, max_sizes=max_sizes,
aspect_ratios=aspect_ratios, steps=steps, normalizations=normalizations,
num_classes=num_classes, share_location=share_location, flip=flip, clip=clip,
prior_variance=prior_variance, kernel_size=3, pad=1, lr_mult=lr_mult)
conf_name = "mbox_conf"
if multibox_loss_param["conf_loss_type"] == P.MultiBoxLoss.SOFTMAX:
reshape_name = "{}_reshape".format(conf_name)
net[reshape_name] = L.Reshape(net[conf_name], shape=dict(dim=[0, -1, num_classes]))
softmax_name = "{}_softmax".format(conf_name)
net[softmax_name] = L.Softmax(net[reshape_name], axis=2)
flatten_name = "{}_flatten".format(conf_name)
net[flatten_name] = L.Flatten(net[softmax_name], axis=1)
mbox_layers[1] = net[flatten_name]
elif multibox_loss_param["conf_loss_type"] == P.MultiBoxLoss.LOGISTIC:
sigmoid_name = "{}_sigmoid".format(conf_name)
net[sigmoid_name] = L.Sigmoid(net[conf_name])
mbox_layers[1] = net[sigmoid_name]
net.detection_out = L.DetectionOutput(*mbox_layers,
detection_output_param=det_out_param,
include=dict(phase=caffe_pb2.Phase.Value('TEST')))
net.detection_eval = L.DetectionEvaluate(net.detection_out, net.label,
detection_evaluate_param=det_eval_param,
include=dict(phase=caffe_pb2.Phase.Value('TEST')))
with open(test_net_file, 'w') as f:
print('name: "{}_test"'.format(model_name), file=f)
print(net.to_proto(), file=f)
shutil.copy(test_net_file, job_dir)
# Create deploy net.
# Remove the first and last layer from test net.
deploy_net = net
with open(deploy_net_file, 'w') as f:
net_param = deploy_net.to_proto()
# Remove the first (AnnotatedData) and last (DetectionEvaluate) layer from test net.
del net_param.layer[0]
del net_param.layer[-1]
net_param.name = '{}_deploy'.format(model_name)
net_param.input.extend(['data'])
net_param.input_shape.extend([
caffe_pb2.BlobShape(dim=[1, 3, resize_height, resize_width])])
print(net_param, file=f)
shutil.copy(deploy_net_file, job_dir)
# Create solver.
solver = caffe_pb2.SolverParameter(
train_net=train_net_file,
test_net=[test_net_file],
snapshot_prefix=snapshot_prefix,
**solver_param)
with open(solver_file, 'w') as f:
print(solver, file=f)
shutil.copy(solver_file, job_dir)
max_iter = 0
# Find most recent snapshot.
for file in os.listdir(snapshot_dir):
if file.endswith(".solverstate"):
basename = os.path.splitext(file)[0]
iter = int(basename.split("{}_iter_".format(model_name))[1])
if iter > max_iter:
max_iter = iter
train_src_param = '--weights="{}" \\\n'.format(pretrain_model)
if resume_training:
if max_iter > 0:
train_src_param = '--snapshot="{}_iter_{}.solverstate" \\\n'.format(snapshot_prefix, max_iter)
if remove_old_models:
# Remove any snapshots smaller than max_iter.
for file in os.listdir(snapshot_dir):
if file.endswith(".solverstate"):
basename = os.path.splitext(file)[0]
iter = int(basename.split("{}_iter_".format(model_name))[1])
if max_iter > iter:
os.remove("{}/{}".format(snapshot_dir, file))
if file.endswith(".caffemodel"):
basename = os.path.splitext(file)[0]
iter = int(basename.split("{}_iter_".format(model_name))[1])
if max_iter > iter:
os.remove("{}/{}".format(snapshot_dir, file))
# Create job file.
with open(job_file, 'w') as f:
f.write('cd {}\n'.format(caffe_root))
f.write('./build/tools/caffe train \\\n')
f.write('--solver="{}" \\\n'.format(solver_file))
f.write(train_src_param)
if solver_param['solver_mode'] == P.Solver.GPU:
f.write('--gpu {} 2>&1 | tee {}/{}.log\n'.format(gpus, job_dir, model_name))
else:
f.write('2>&1 | tee {}/{}.log\n'.format(job_dir, model_name))
# Copy the python script to job_dir.
py_file = os.path.abspath(__file__)
shutil.copy(py_file, job_dir)
# Run the job.
os.chmod(job_file, stat.S_IRWXU)
if run_soon:
subprocess.call(job_file, shell=True)
train\test\deploy\solver.prototxt等都是运行这个脚本自动生成的。
gpus='0,1,2,3',如果有一块GPU,则删除123,有两块则删除23
如果没有GPU,需要注释以下几行,程序会以cpu形式训练:(这个是解决 cudasucess(10vs0)的方法)
#ifnum_gpus >0:
#batch_size_per_device=int(math.ceil(float(batch_size)/num_gpus))
#iter_size = int(math.ceil(float(accum_batch_size)/(batch_size_per_device*num_gpus)))
#solver_model=P.Solver.GPU
#device_id=int(gpulist[0])
###5 修改 ./examples/ssd/ssd_pascal_webcam.py
对应修改就行了
###6 训练 在根目录下运行 python ./examples/ssd/ssd_pascal.py 如果出现 cudasucess(2vs0):说明显卡的计算能力有限,需要更改 caffe/examples/sdd/ssd_pascal.py 中的batch_size. 默认的32变小成16、8、4。