win10+maskrcnn-benchmark+cocodataset+GPU

windows不能讓maskrcnn-benchmark跑自己的訓練集嗎？不可能的，都是操作系統，只是網上的資料都是在Linux下面搞的。

首先聲明：顯存2G或者內存小於12G的滾一邊去，嗯，我的就是顯存2G的，一個同學4G的顯存8G的內存顯示內存不夠，給他加了一個4G的內存條後沒有顯示顯存不夠，也沒有顯示內存不夠，就是報了個index out of range的錯誤，我也不知道爲什麼

 

數據集準備

COCO數據集，自己的數據集也行，但是我沒試過，可以看其它文章，雖然他們都是Linux的，但是，都是操作系統，有什麼區別，數據集優先下載val2017、train2017和2017 Train/Val annotations，其它的就掛在那裏下載吧，指不定什麼時候要用

 

修改.yaml文件

這個肯定是要修改的，怎麼改你們自己搞，用哪個也自己搞，但是

DATASETS:
  TRAIN: ("coco_2014_train", "coco_2014_valminusminival")
  TEST: ("coco_2014_minival",)

這個是必須要改的，因爲它規定了你用的是哪個訓練集和測試集，而裏面寫的coco_2014_train、coco_2014_valminusminival、coco_2014_minival來自/maskrcnn_benchmark/config/paths_catalog.py，代碼如下

# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
"""Centralized catalog of paths."""

import os


class DatasetCatalog(object):
    DATA_DIR = "datasets"
    DATASETS = {
        "coco_2017_train": {
            "img_dir": "coco/train2017",
            "ann_file": "coco/annotations/instances_train2017.json"
        },
        "coco_2017_val": {
            "img_dir": "coco/val2017",
            "ann_file": "coco/annotations/instances_val2017.json"
        },
        "coco_2014_train": {
            "img_dir": "coco/train2014",
            "ann_file": "coco/annotations/instances_train2014.json"
        },
        "coco_2014_val": {
            "img_dir": "coco/val2014",
            "ann_file": "coco/annotations/instances_val2014.json"
        },
        "coco_2014_minival": {
            "img_dir": "coco/val2014",
            "ann_file": "coco/annotations/instances_minival2014.json"
        },
        "coco_2014_valminusminival": {
            "img_dir": "coco/val2014",
            "ann_file": "coco/annotations/instances_valminusminival2014.json"
        },
        "keypoints_coco_2014_train": {
            "img_dir": "coco/train2014",
            "ann_file": "coco/annotations/person_keypoints_train2014.json",
        },
        "keypoints_coco_2014_val": {
            "img_dir": "coco/val2014",
            "ann_file": "coco/annotations/person_keypoints_val2014.json"
        },
        "keypoints_coco_2014_minival": {
            "img_dir": "coco/val2014",
            "ann_file": "coco/annotations/person_keypoints_minival2014.json",
        },
        "keypoints_coco_2014_valminusminival": {
            "img_dir": "coco/val2014",
            "ann_file": "coco/annotations/person_keypoints_valminusminival2014.json",
        },
        "voc_2007_train": {
            "data_dir": "voc/VOC2007",
            "split": "train"
        },
        "voc_2007_train_cocostyle": {
            "img_dir": "voc/VOC2007/JPEGImages",
            "ann_file": "voc/VOC2007/Annotations/pascal_train2007.json"
        },
        "voc_2007_val": {
            "data_dir": "voc/VOC2007",
            "split": "val"
        },
        "voc_2007_val_cocostyle": {
            "img_dir": "voc/VOC2007/JPEGImages",
            "ann_file": "voc/VOC2007/Annotations/pascal_val2007.json"
        },
        "voc_2007_test": {
            "data_dir": "voc/VOC2007",
            "split": "test"
        },
        "voc_2007_test_cocostyle": {
            "img_dir": "voc/VOC2007/JPEGImages",
            "ann_file": "voc/VOC2007/Annotations/pascal_test2007.json"
        },
        "voc_2012_train": {
            "data_dir": "voc/VOC2012",
            "split": "train"
        },
        "voc_2012_train_cocostyle": {
            "img_dir": "voc/VOC2012/JPEGImages",
            "ann_file": "voc/VOC2012/Annotations/pascal_train2012.json"
        },
        "voc_2012_val": {
            "data_dir": "voc/VOC2012",
            "split": "val"
        },
        "voc_2012_val_cocostyle": {
            "img_dir": "voc/VOC2012/JPEGImages",
            "ann_file": "voc/VOC2012/Annotations/pascal_val2012.json"
        },
        "voc_2012_test": {
            "data_dir": "voc/VOC2012",
            "split": "test"
            # PASCAL VOC2012 doesn't made the test annotations available, so there's no json annotation
        },
        "cityscapes_fine_instanceonly_seg_train_cocostyle": {
            "img_dir": "cityscapes/images",
            "ann_file": "cityscapes/annotations/instancesonly_filtered_gtFine_train.json"
        },
        "cityscapes_fine_instanceonly_seg_val_cocostyle": {
            "img_dir": "cityscapes/images",
            "ann_file": "cityscapes/annotations/instancesonly_filtered_gtFine_val.json"
        },
        "cityscapes_fine_instanceonly_seg_test_cocostyle": {
            "img_dir": "cityscapes/images",
            "ann_file": "cityscapes/annotations/instancesonly_filtered_gtFine_test.json"
        }
    }

    @staticmethod
    def get(name):
        if "coco" in name:
            data_dir = DatasetCatalog.DATA_DIR
            attrs = DatasetCatalog.DATASETS[name]
            args = dict(
                root=os.path.join(data_dir, attrs["img_dir"]),
                ann_file=os.path.join(data_dir, attrs["ann_file"]),
            )
            return dict(
                factory="COCODataset",
                args=args,
            )
        elif "voc" in name:
            data_dir = DatasetCatalog.DATA_DIR
            attrs = DatasetCatalog.DATASETS[name]
            args = dict(
                data_dir=os.path.join(data_dir, attrs["data_dir"]),
                split=attrs["split"],
            )
            return dict(
                factory="PascalVOCDataset",
                args=args,
            )
        raise RuntimeError("Dataset not available: {}".format(name))


class ModelCatalog(object):
    S3_C2_DETECTRON_URL = "https://dl.fbaipublicfiles.com/detectron"
    C2_IMAGENET_MODELS = {
        "MSRA/R-50": "ImageNetPretrained/MSRA/R-50.pkl",
        "MSRA/R-50-GN": "ImageNetPretrained/47261647/R-50-GN.pkl",
        "MSRA/R-101": "ImageNetPretrained/MSRA/R-101.pkl",
        "MSRA/R-101-GN": "ImageNetPretrained/47592356/R-101-GN.pkl",
        "FAIR/20171220/X-101-32x8d": "ImageNetPretrained/20171220/X-101-32x8d.pkl",
    }

    C2_DETECTRON_SUFFIX = "output/train/{}coco_2014_train%3A{}coco_2014_valminusminival/generalized_rcnn/model_final.pkl"
    C2_DETECTRON_MODELS = {
        "35857197/e2e_faster_rcnn_R-50-C4_1x": "01_33_49.iAX0mXvW",
        "35857345/e2e_faster_rcnn_R-50-FPN_1x": "01_36_30.cUF7QR7I",
        "35857890/e2e_faster_rcnn_R-101-FPN_1x": "01_38_50.sNxI7sX7",
        "36761737/e2e_faster_rcnn_X-101-32x8d-FPN_1x": "06_31_39.5MIHi1fZ",
        "35858791/e2e_mask_rcnn_R-50-C4_1x": "01_45_57.ZgkA7hPB",
        "35858933/e2e_mask_rcnn_R-50-FPN_1x": "01_48_14.DzEQe4wC",
        "35861795/e2e_mask_rcnn_R-101-FPN_1x": "02_31_37.KqyEK4tT",
        "36761843/e2e_mask_rcnn_X-101-32x8d-FPN_1x": "06_35_59.RZotkLKI",
        "37129812/e2e_mask_rcnn_X-152-32x8d-FPN-IN5k_1.44x": "09_35_36.8pzTQKYK",
        # keypoints
        "37697547/e2e_keypoint_rcnn_R-50-FPN_1x": "08_42_54.kdzV35ao"
    }

    @staticmethod
    def get(name):
        if name.startswith("Caffe2Detectron/COCO"):
            return ModelCatalog.get_c2_detectron_12_2017_baselines(name)
        if name.startswith("ImageNetPretrained"):
            return ModelCatalog.get_c2_imagenet_pretrained(name)
        raise RuntimeError("model not present in the catalog {}".format(name))

    @staticmethod
    def get_c2_imagenet_pretrained(name):
        prefix = ModelCatalog.S3_C2_DETECTRON_URL
        name = name[len("ImageNetPretrained/"):]
        name = ModelCatalog.C2_IMAGENET_MODELS[name]
        url = "/".join([prefix, name])
        return url

    @staticmethod
    def get_c2_detectron_12_2017_baselines(name):
        # Detectron C2 models are stored following the structure
        # prefix/<model_id>/2012_2017_baselines/<model_name>.yaml.<signature>/suffix
        # we use as identifiers in the catalog Caffe2Detectron/COCO/<model_id>/<model_name>
        prefix = ModelCatalog.S3_C2_DETECTRON_URL
        dataset_tag = "keypoints_" if "keypoint" in name else ""
        suffix = ModelCatalog.C2_DETECTRON_SUFFIX.format(dataset_tag, dataset_tag)
        # remove identification prefix
        name = name[len("Caffe2Detectron/COCO/"):]
        # split in <model_id> and <model_name>
        model_id, model_name = name.split("/")
        # parsing to make it match the url address from the Caffe2 models
        model_name = "{}.yaml".format(model_name)
        signature = ModelCatalog.C2_DETECTRON_MODELS[name]
        unique_name = ".".join([model_name, signature])
        url = "/".join([prefix, model_id, "12_2017_baselines", unique_name, suffix])
        return url

看到那個DATASETS了麼，那就是coco_2014_train、coco_2014_valminusminival、coco_2014_minival的來源，你把訓練集和測試集改成自己想要的，保險起見，名字還是沿用DATASETS的比較好，然後把.yaml中的名字改成自己想要的DATASETS中的名字就行了，比如我是這樣改的：

DATASETS:
  TRAIN: ("coco_2017_train",)
  TEST: ("coco_2017_val",)

然後把paths_catalog.py中的DATASETS中的對應的訓練集和測試集的路徑改成自己的，雖然他用的是什麼coco/......，但是我們windows就有我們windows的粗暴路徑，比如這樣的

O:/Users/xxx/Anaconda3/envs/maskrcnn_benchmark/maskrcnn-benchmark/datasets/coco

記得斜槓的方向

 

訓練命令

這個其實官方就有提供，查看官方指南會好一點

我這裏就提供幾個能用的，記得在Anaconda Prompt (Anaconda3)裏面cd到maskrcnn_benchmark裏面

單GPU：

python tools/train_net.py --config-file O:/Users/XXX/Anaconda3/envs/maskrcnn_benchmark/maskrcnn-benchmark/configs/e2e_mask_rcnn_R_101_FPN_1x.yaml SOLVER.IMS_PER_BATCH 1 SOLVER.BASE_LR 0.0025 SOLVER.MAX_ITER 60000 SOLVER.STEPS "(30000, 40000)" TEST.IMS_PER_BATCH 1 MODEL.RPN.FPN_POST_NMS_TOP_N_TRAIN 2000

python tools/train_net.py --config-file O:/Users/XXX/Anaconda3/envs/maskrcnn_benchmark/maskrcnn-benchmark/configs/e2e_mask_rcnn_R_101_FPN_1x.yaml

python tools/train_net.py --config-file O:/Users/XXX/Anaconda3/envs/maskrcnn_benchmark/maskrcnn-benchmark/configs/e2e_mask_rcnn_R_101_FPN_1x.yaml SOLVER.IMS_PER_BATCH 2 SOLVER.BASE_LR 0.0025 SOLVER.MAX_ITER 60000 SOLVER.STEPS "(30000, 40000)" TEST.IMS_PER_BATCH 1 MODEL.RPN.FPN_POST_NMS_TOP_N_TRAIN 2000

python tools/train_net.py --config-file O:/Users/XXX/Anaconda3/envs/maskrcnn_benchmark/maskrcnn-benchmark/configs/e2e_mask_rcnn_R_101_FPN_1x.yaml SOLVER.IMS_PER_BATCH 2 SOLVER.BASE_LR 0.0025 SOLVER.MAX_ITER 720000 SOLVER.STEPS "(480000, 640000)" TEST.IMS_PER_BATCH 1 MODEL.RPN.FPN_POST_NMS_TOP_N_TRAIN 2000

多GPU直接看官方的吧

 

 

在添加兩張照片：

單GPU第一個命令：

單GPU第四個命令（基於官方參數修改）：

 

從圖中可以看出，顯存最低4G，最低4G，最低4G，內存若干，8G肯定不行

單GPU第二個命令，顯存16G也不行