如何训练新的快速rcnn图像集 [英] How to train new fast-rcnn imageset

问题描述

我正在使用 fast-rcnn 并尝试为新课程(标签)训练系统 我遵循了这个步骤: https://github.com/EdisonResearch/fast- rcnn/tree/master/help/train

I am using fast-rcnn and try to train the system for new class (label) I followed this: https://github.com/EdisonResearch/fast-rcnn/tree/master/help/train

1. 放置图像

1. Placed the images

放置注释

准备具有所有图像名称前缀的ImageSet

Prepare the ImageSet with all the image name prefix

准备好的选择性搜索输出:train.mat

Prepared selective search output: train.mat

我在运行train_net.py时失败，出现以下错误:

./tools/train_net.py --gpu 0 --solver models/VGG_1024_pascal2007/solver.prototxt --imdb voc_2007_train_top_5000 

Called with args: Namespace(cfg_file=None, gpu_id=0, imdb_name='voc_2007_train_top_5000', max_iters=40000, pretrained_model=None, randomize=False, solver='models/VGG_1024_pascal2007/solver.prototxt') Using config: {'DEDUP_BOXES': 0.0625,  'EPS': 1e-14,  'EXP_DIR': 'default',  'PIXEL_MEANS': array([[[ 102.9801,  115.9465,  122.7717]]]),  'RNG_SEED': 3,  'ROOT_DIR': '/home/hagay/fast-rcnn',  'TEST': {'BBOX_REG': True,
          'MAX_SIZE': 1000,
          'NMS': 0.3,
          'SCALES': [600],
          'SVM': False},  'TRAIN': {'BATCH_SIZE': 128,
           'BBOX_REG': True,
           'BBOX_THRESH': 0.5,
           'BG_THRESH_HI': 0.5,
           'BG_THRESH_LO': 0.1,
           'FG_FRACTION': 0.25,
           'FG_THRESH': 0.5,
           'IMS_PER_BATCH': 2,
           'MAX_SIZE': 1000,
           'SCALES': [600],
           'SNAPSHOT_INFIX': '',
           'SNAPSHOT_ITERS': 10000,
           'USE_FLIPPED': True,
           'USE_PREFETCH': False}} Loaded dataset `voc_2007_train` for training Appending horizontally-flipped training examples... voc_2007_train gt roidb loaded from /home/hagay/fast-rcnn/data/cache/voc_2007_train_gt_roidb.pkl /usr/local/lib/python2.7/dist-packages/numpy/core/fromnumeric.py:2507: VisibleDeprecationWarning: `rank` is deprecated; use the `ndim` attribute or function instead. To find the rank of a matrix see `numpy.linalg.matrix_rank`.   VisibleDeprecationWarning) wrote ss roidb to /home/hagay/fast-rcnn/data/cache/voc_2007_train_selective_search_IJCV_top_5000_roidb.pkl Traceback (most recent call last):   File "./tools/train_net.py", line 80, in <module>
    roidb = get_training_roidb(imdb)   File "/home/hagay/fast-rcnn/tools/../lib/fast_rcnn/train.py", line 107, in get_training_roidb
    imdb.append_flipped_images()   File "/home/hagay/fast-rcnn/tools/../lib/datasets/imdb.py", line 104, in append_flipped_images
    assert (boxes[:, 2] >= boxes[:, 0]).all() AssertionError

我的问题是:

1. 为什么会出现此错误?
2. 在训练之前，我是否需要重新缩放图像以修复:256x256?
3. 我需要准备一些东西来设置__background__类吗?

1. Why am I having this error?
2. Do I need to rescale the images to fix: 256x256 before training?
3. Do I need to prepare something in order to set the __background__ class?

推荐答案

查看以下博客文章，第4部分，第4期中描述的解决方案.解决方案是翻转x1和x2坐标值.

Check out the solution described in the following blog post, Part 4, Issue #4. The solution is to flip the x1 and x2 coordinate values.

https://huangying-zhan.github .io/2016/09/22/detection-faster-rcnn.html

以下是从链接复制的:

框[:，0]>框[:，2]

box [:, 0] > box[:, 2]

解决方案:在imdb.py中添加以下代码块

Solution: add the following code block in imdb.py

def append_flipped_images(self):
num_images = self.num_images
widths = self._get_widths()
for i in xrange(num_images):
    boxes = self.roidb[i]['boxes'].copy()
    oldx1 = boxes[:, 0].copy()
    oldx2 = boxes[:, 2].copy()
    boxes[:, 0] = widths[i] - oldx2
    boxes[:, 2] = widths[i] - oldx1
    for b in range(len(boxes)):
            if boxes[b][2] < boxes[b][0]:
                boxes[b][0]=0
    assert (boxes[:, 2] >= boxes[:, 0]).all()

这篇关于如何训练新的快速rcnn图像集的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！