资源简介
ssd模型文件,caffe_ssd_microsoft工程可以直接进行测试
https://github.com/weiliu89/caffe/tree/ssd原地址
代码片段和文件信息
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.
# 32 x 32
from_layer = net.keys()[-1]
# TODO(weiliu89): Construct the name using the last layer to avoid duplication.
# 16 x 16
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)
# 8 x 8
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)
# 4 x 4
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 1 2
lr_mult=lr_mult)
# 2 x 2
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 1 2
lr_mult=lr_mult)
# 1 x 1
from_layer = out_layer
out_layer = “conv10_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 = “conv10_2“
ConvBNlayer(net from_layer out_layer use_batchnorm use_relu 256 4 1 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/VOC0712Plus/create_data.sh
train_data = “examples/VOC0712Plus/VOC0712Plus_trainval_lmdb“
# The database file for testing data. Created by data/VOC0712Plus/create_data.sh
test_data = “examples/VOC0712Plus/VOC0712Plus_test_lmdb“
# Specify the batch sampler.
resize_width =
相关资源
- 邹博机器学习全套课件及代码
- SSD缺陷检测裂纹源代码
- 2016年中国科学院大学高级人工智能期
- ACL2019 (2).zip
- STM32F429 双LCD屏 正点原子阿波罗开发板
- inception_resnet_v2_2016_08_30预训练模型
- VGG_VOC0712_SSD_300x300_iter_120000.caffemodel
- 提取视频前景背景/运动目标检测
- 图像处理、分析与机器视觉第4版.[美
- 互联网信贷反欺诈模型
- 程序员的数学1-2-3
- 行人检测数据集/目标检测
- 云小蜜人工智能训练师ppt整理+常考知
- 应用随机过程 概率模型导论高清 第
- Hands On Machine Learning中+英
- AI for Games 3rd Edition
- 天津大学人工智能往年真题.zip
- yolo9000.weights
- 视频摄像头SSD模型目标检测.zip
- 线性代数及其应用 答案 学习指导 D
- mobil_mask_rcnn_coco.h5
- Gaussian_yolov3_BDD.weights权重文件
- Hands-On Machine Learning with Scikit-Learn an
- 2019张宇概率论与数理统计9讲 + 2019张
- U2Net 网络预训练模型u2net.pth
- 自动规划:理论与实践
- 硕博团队研发-足球走地大数据智能
- NLP汉语自然语言处理原理与实践最新
- 手势识别数据库已标记
- 无人驾驶车辆模型预测控制by龚建伟
评论
共有 条评论