TensorRT maskrcnn windows下使用自己的数据集（一）

  • 环境准备
    maskrcnn源码：
    https://github.com/matterport/Mask_RCNN
    -- 前向推理环境：
    系统：windows10
    工具：CUDA10.0.130、cudnn7.6.3.30、TensorRT7.0.0.11
    IDE：Visual Studio2019
    -- 训练及模型转换环境：
    系统：Ubuntu18.04，docker-nvidia
    工具：python3.6、tensorflow1.14.0、keras2.1.13、nvcr.io/nvidia/tensorflow:19.10-py3
  • 数据集
    使用自己的数据集制作成coco格式。
  • 训练
git clone https://github.com/matterport/Mask_RCNN.git
cd samples/
mkdir yourtrain 
cd yourtrain
cp ../../coco/coco.py ./
mv coco.py yourtrain.py

修改yourtrain.py训练参数：

class CocoConfig(Config):
    # 改成你想要的名字
    NAME = "yourtrain"
    #每张gpu处理的图片数量，更加你的gpu的性能修改，性能不行就改1
    IMAGES_PER_GPU = 2
    # 你用于训练的gpu的数量，IMAGES_PER_GPU*GPU_COUNT 就是你的batchsize
    GPU_COUNT = 2

    # 改成你的数据的label数量加1
    NUM_CLASSES = 1 + 1 # COCO has 80 classes
    # added 主干网络可以是ResNet50也可以是res101，这里不写BACKBONE那就是默认res101
    BACKBONE = 'resnet50'
    #输入图片512*512
    IMAGE_MIN_DIM = 512
    IMAGE_MAX_DIM = 512
    #anchor大小，根据情况改
    RPN_ANCHOR_SCALES = (14, 28, 56, 112, 224)
    #其他参数可以看情况改，其他参数名可看mrcnn/config.py

开始训练

cd Mask_RCNN   #cd回Mask_RCNN主文件夹
CUDA_VISIBLE_DEVICES=0,1 python samples/yourtrain/yourtrain.py train --dataset=你的coco格式的数据集文件夹/ --model=imagenet --logs=你存模型的路径/logs    #生成的h5模型会存储在logs下，CUDA_VISIBLE_DEVICES是gpu的序号，自行修改
  • 模型转换
    1、在Ubuntu环境下安装好docker-nvidia
    2、拉去nvidia docker container
docker run --rm -it --gpus all -v $TRT_SOURCE:/workspace/TensorRT -v $TRT_RELEASE:/tensorrt nvcr.io/nvidia/tensorflow:19.10-py3 /bin/bash
#最好记下container的序号或名称，之后可以docker attach 容器序号进入容器

3、看看有没有workspace/TensorRT文件夹，没有就如下操作

cd workspace
git clone https://github.com/NVIDIA/TensorRT.git
cd TensorRT/samples/opensource/sampleUffMaskRCNN/converted/
pip3 install -r requirements.txt

4、出去容器（快捷键alt+q+p），把TensorRT7.0.0.11中的模型转换python安装包docker cp到docker中的TensorRT/samples/opensource/sampleUffMaskRCNN/converted/下

docker cp uff-*-py2.py3-none-any.whl 容器序号:/workspace/TensorRT/samples/opensource/sampleUffMaskRCNN/converted/
docker cp graphsurgeon-*-py2.py3-none-any.whl 容器序号:/workspace/TensorRT/samples/opensource/sampleUffMaskRCNN/converted/

5、进入到docker容器下安装

pip3 uff-*-py2.py3-none-any.whl
pip3 graphsurgeon-*-py2.py3-none-any.whl

6、修改转换模型代码nchw->nhwc

vim /usr/lib/python3.6/dist-packages/uff/converters/tensorflow/converter_functions.py

搜索uff_graph.conv_transpose，即输入/uff_graph.conv_transpose，回车，修改如成如下：

uff_graph.conv_transpose(
    inputs[0], inputs[2], inputs[1],

7、下载Mask_RCNN，（因为h5中只存了权重，没有网络图，转换需要网络代码）

git clone https://github.com/matterport/Mask_RCNN.git
export PYTHONPATH=$PYTHONPATH:$PWD/Mask_RCNN

8、修改mrcnn_to_trt_single.py

class InferenceConfig(CocoConfig):
    GPU_COUNT = 1
    IMAGES_PER_GPU = 1
    BACKBONE = 'resnet50' # added ResNet50
    IMAGE_MIN_DIM = 512
    IMAGE_MAX_DIM = 512

9、修改config.py，输入，label数等，res101结构改为res50结构

roi = gs.create_plugin_node("ROI", op="ProposalLayer_TRT", prenms_topk=1024, keep_topk=1000, iou_threshold=0.7)
roi_align_classifier = gs.create_plugin_node("roi_align_classifier", op="PyramidROIAlign_TRT", pooled_size=7)
mrcnn_detection = gs.create_plugin_node("mrcnn_detection", op="DetectionLayer_TRT", num_classes=2, keep_topk=100, score_threshold=0.7, iou_threshold=0.3)

timedistributed_remove_list = [
        "mrcnn_class_conv1/Reshape/shape", "mrcnn_class_conv1/Reshape", "mrcnn_class_conv1/Reshape_1/shape", "mrcnn_class_conv1/Reshape_1",
        "mrcnn_class_bn1/Reshape/shape", "mrcnn_class_bn1/Reshape", "mrcnn_class_bn1/Reshape_5/shape", "mrcnn_class_bn1/Reshape_5",
        "mrcnn_class_conv2/Reshape/shape", "mrcnn_class_conv2/Reshape", "mrcnn_class_conv2/Reshape_1/shape", "mrcnn_class_conv2/Reshape_1",
        "mrcnn_class_bn2/Reshape/shape", "mrcnn_class_bn2/Reshape", "mrcnn_class_bn2/Reshape_5/shape", "mrcnn_class_bn2/Reshape_5",
        "mrcnn_class_logits/Reshape/shape", "mrcnn_class_logits/Reshape","mrcnn_class_logits/Reshape_1/shape", "mrcnn_class_logits/Reshape_1",
        "mrcnn_class/Reshape/shape", "mrcnn_class/Reshape","mrcnn_class/Reshape_1/shape", "mrcnn_class/Reshape_1",
        "mrcnn_bbox_fc/Reshape/shape", "mrcnn_bbox_fc/Reshape","mrcnn_bbox_fc/Reshape_1/shape", "mrcnn_bbox_fc/Reshape_1",

        "mrcnn_mask_conv1/Reshape/shape", "mrcnn_mask_conv1/Reshape", "mrcnn_mask_conv1/Reshape_1/shape", "mrcnn_mask_conv1/Reshape_1",
        "mrcnn_mask_bn1/Reshape/shape", "mrcnn_mask_bn1/Reshape", "mrcnn_mask_bn1/Reshape_5/shape", "mrcnn_mask_bn1/Reshape_5",
        "mrcnn_mask_conv2/Reshape/shape", "mrcnn_mask_conv2/Reshape", "mrcnn_mask_conv2/Reshape_1/shape", "mrcnn_mask_conv2/Reshape_1",
        "mrcnn_mask_bn2/Reshape/shape", "mrcnn_mask_bn2/Reshape", "mrcnn_mask_bn2/Reshape_5/shape", "mrcnn_mask_bn2/Reshape_5",
        "mrcnn_mask_conv3/Reshape/shape", "mrcnn_mask_conv3/Reshape", "mrcnn_mask_conv3/Reshape_1/shape", "mrcnn_mask_conv3/Reshape_1",
        "mrcnn_mask_bn3/Reshape/shape", "mrcnn_mask_bn3/Reshape", "mrcnn_mask_bn3/Reshape_5/shape", "mrcnn_mask_bn3/Reshape_5",
        "mrcnn_mask_conv4/Reshape/shape", "mrcnn_mask_conv4/Reshape", "mrcnn_mask_conv4/Reshape_1/shape", "mrcnn_mask_conv4/Reshape_1",
        "mrcnn_mask_bn4/Reshape/shape", "mrcnn_mask_bn4/Reshape", "mrcnn_mask_bn4/Reshape_5/shape", "mrcnn_mask_bn4/Reshape_5",
        "mrcnn_mask_deconv/Reshape/shape", "mrcnn_mask_deconv/Reshape", "mrcnn_mask_deconv/Reshape_1/shape", "mrcnn_mask_deconv/Reshape_1",
        "mrcnn_mask/Reshape/shape", "mrcnn_mask/Reshape", "mrcnn_mask/Reshape_1/shape", "mrcnn_mask/Reshape_1",
        ]
...
timedistributed_connect_pairs = [
        ("mrcnn_mask_deconv/Relu", "mrcnn_mask/convolution"), # mrcnn_mask_deconv -> mrcnn_mask
        ("activation_40/Relu", "mrcnn_mask_deconv/conv2d_transpose"), #active74 -> mrcnn_mask_deconv
        ("mrcnn_mask_bn4/batchnorm/add_1","activation_40/Relu"),  # mrcnn_mask_bn4 -> active74
        ("mrcnn_mask_conv4/BiasAdd", "mrcnn_mask_bn4/batchnorm/mul_1"), #mrcnn_mask_conv4 -> mrcnn_mask_bn4
        ("activation_39/Relu", "mrcnn_mask_conv4/convolution"), #active73 -> mrcnn_mask_conv4
        ("mrcnn_mask_bn3/batchnorm/add_1","activation_39/Relu"), #mrcnn_mask_bn3 -> active73
        ("mrcnn_mask_conv3/BiasAdd", "mrcnn_mask_bn3/batchnorm/mul_1"), #mrcnn_mask_conv3 -> mrcnn_mask_bn3
        ("activation_38/Relu", "mrcnn_mask_conv3/convolution"), #active72 -> mrcnn_mask_conv3
        ("mrcnn_mask_bn2/batchnorm/add_1","activation_38/Relu"), #mrcnn_mask_bn2 -> active72
        ("mrcnn_mask_conv2/BiasAdd", "mrcnn_mask_bn2/batchnorm/mul_1"), #mrcnn_mask_conv2 -> mrcnn_mask_bn2
        ("activation_37/Relu", "mrcnn_mask_conv2/convolution"), #active71 -> mrcnn_mask_conv2
        ("mrcnn_mask_bn1/batchnorm/add_1","activation_37/Relu"), #mrcnn_mask_bn1 -> active71
        ("mrcnn_mask_conv1/BiasAdd", "mrcnn_mask_bn1/batchnorm/mul_1"), #mrcnn_mask_conv1 -> mrcnn_mask_bn1
        ("roi_align_mask_trt", "mrcnn_mask_conv1/convolution"), #roi_align_mask -> mrcnn_mask_conv1


        ("mrcnn_class_bn2/batchnorm/add_1","activation_35/Relu"), # mrcnn_class_bn2 -> active 69
        ("mrcnn_class_conv2/BiasAdd", "mrcnn_class_bn2/batchnorm/mul_1"), # mrcnn_class_conv2 -> mrcnn_class_bn2
        ("activation_34/Relu", "mrcnn_class_conv2/convolution"), # active 68 -> mrcnn_class_conv2
        ("mrcnn_class_bn1/batchnorm/add_1","activation_34/Relu"), # mrcnn_class_bn1 -> active 68
        ("mrcnn_class_conv1/BiasAdd", "mrcnn_class_bn1/batchnorm/mul_1"), # mrcnn_class_conv1 -> mrcnn_class_bn1
        ("roi_align_classifier", "mrcnn_class_conv1/convolution"), # roi_align_classifier -> mrcnn_class_conv1
        ]

---
dense_compatible_connect_pairs = [
        ("activation_35/Relu","mrcnn_bbox_fc/MatMul"), #activation_69 -> mrcnn_bbox_fc
        ("activation_35/Relu", "mrcnn_class_logits/MatMul"), #activation_69 -> mrcnn_class_logits
        ("mrcnn_class_logits/BiasAdd", "mrcnn_class/Softmax"), #mrcnn_class_logits -> mrcnn_class
        ("mrcnn_class/Softmax", "mrcnn_detection"), #mrcnn_class -> mrcnn_detection
        ("mrcnn_bbox_fc/BiasAdd", "mrcnn_detection"), #mrcnn_bbox_fc -> mrcnn_detection
        ]

10、把训练好的h5文件docker cp到容器中，然后如下转换

ython3 mrcnn_to_trt_single.py -w mask_rcnn_yourtrain.h5 -o mrcnn_nchw.uff -p ./config.py

生成mrcnn_nchw.uff，取出到windows备用

©著作权归作者所有,转载或内容合作请联系作者
  • 人面猴
    序言：七十年代末，一起剥皮案震惊了整个滨河市，随后出现的几起案子，更是在滨河造成了极大的恐慌，老刑警刘岩，带你破解...
    沈念sama阅读 212,816评论 6赞 492
  • 死咒
    序言：滨河连续发生了三起死亡事件，死亡现场离奇诡异，居然都是意外死亡，警方通过查阅死者的电脑和手机，发现死者居然都...
    沈念sama阅读 90,729评论 3赞 385
  • 救了他两次的神仙让他今天三更去死
    文/潘晓璐 我一进店门，熙熙楼的掌柜王于贵愁眉苦脸地迎上来，“玉大人，你说我怎么就摊上这事。” “怎么了？”我有些...
    开封第一讲书人阅读 158,300评论 0赞 348
  • 道士缉凶录：失踪的卖姜人
    文/不坏的土叔 我叫张陵，是天一观的道长。 经常有香客问我，道长，这世上最难降的妖魔是什么？ 我笑而不...
    开封第一讲书人阅读 56,780评论 1赞 285
  • 港岛之恋（遗憾婚礼）
    正文 为了忘掉前任，我火速办了婚礼，结果婚礼上，老公的妹妹穿的比我还像新娘。我一直安慰自己，他们只是感情好，可当我...
    茶点故事阅读 65,890评论 6赞 385
  • 恶毒庶女顶嫁案：这布局不是一般人想出来的
    文/花漫 我一把揭开白布。 她就那样静静地躺着，像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上，一...
    开封第一讲书人阅读 50,084评论 1赞 291
  • 城市分裂传说
    那天，我揣着相机与录音，去河边找鬼。 笑死，一个胖子当着我的面吹牛，可吹牛的内容都是我干的。 我是一名探鬼主播，决...
    沈念sama阅读 39,151评论 3赞 410
  • 双鸳鸯连环套：你想象不到人心有多黑
    文/苍兰香墨 我猛地睁开眼，长吁一口气：“原来是场噩梦啊……” “哼！你这毒妇竟也来了？” 一声冷哼从身侧响起，我...
    开封第一讲书人阅读 37,912评论 0赞 268
  • 万荣杀人案实录
    序言：老挝万荣一对情侣失踪，失踪者是张志新（化名）和其女友刘颖，没想到半个月后，有当地人在树林里发现了一具尸体，经...
    沈念sama阅读 44,355评论 1赞 303
  • 护林员之死
    正文 独居荒郊野岭守林人离奇死亡，尸身上长有42处带血的脓包…… 初始之章·张勋 以下内容为张勋视角 年9月15日...
    茶点故事阅读 36,666评论 2赞 327
  • 白月光启示录
    正文 我和宋清朗相恋三年，在试婚纱的时候发现自己被绿了。 大学时的朋友给我发了我未婚夫和他白月光在一起吃饭的照片。...
    茶点故事阅读 38,809评论 1赞 341
  • 活死人
    序言：一个原本活蹦乱跳的男人离奇死亡，死状恐怖，灵堂内的尸体忽然破棺而出，到底是诈尸还是另有隐情，我是刑警宁泽，带...
    沈念sama阅读 34,504评论 4赞 334
  • 日本核电站爆炸内幕
    正文 年R本政府宣布，位于F岛的核电站，受9级特大地震影响，放射性物质发生泄漏。R本人自食恶果不足惜，却给世界环境...
    茶点故事阅读 40,150评论 3赞 317
  • 男人毒药：我在死后第九天来索命
    文/蒙蒙 一、第九天 我趴在偏房一处隐蔽的房顶上张望。 院中可真热闹，春花似锦、人声如沸。这庄子的主人今日做“春日...
    开封第一讲书人阅读 30,882评论 0赞 21
  • 一桩弑父案，背后竟有这般阴谋
    文/苍兰香墨 我抬头看了看天上的太阳。三九已至，却和暖如春，着一层夹袄步出监牢的瞬间，已是汗流浃背。 一阵脚步声响...
    开封第一讲书人阅读 32,121评论 1赞 267
  • 情欲美人皮
    我被黑心中介骗来泰国打工， 没想到刚下飞机就差点儿被人妖公主榨干…… 1. 我叫王不留，地道东北人。 一个月前我还...
    沈念sama阅读 46,628评论 2赞 362
  • 代替公主和亲
    正文 我出身青楼，却偏偏与公主长得像，于是被迫代替她去往敌国和亲。 传闻我的和亲对象是个残疾皇子，可洞房花烛夜当晚...
    茶点故事阅读 43,724评论 2赞 351