rgb大神工程https://github.com/rbgirshick/py-faster-rcnn
1. 修改配置Makefile.config编译py-faster-rcnn
2.下载VOC2007数据集，解压到py-faster-rcnn/data文件夹下，用自己的数据集替换掉py-faster-rcnn/data/VOCdevkit2007/VOC2007/下的Annotations、ImageSets、JPEGImages三个文件夹。
VOC2007数据集：https://pan.baidu.com/s/1DxbGqZdDBs6HW5VODtFLug
3.下载ImageNet数据集预训练模型作为权值初始化，解压到py-faster-rcnn/data文件夹下。
预训练模型：https://pan.baidu.com/s/1s7QJEODvL3cd7V6fVa6CwA
4.修改py-faster-rcnn/models/pascal_voc/ZF/faster_rcnn_alt_opt/stage1_fast_rcnn_train.pt
name: "ZF"
layer {
name: 'data'
type: 'Python'
top: 'data'
top: 'rois'
top: 'labels'
top: 'bbox_targets'
top: 'bbox_inside_weights'
top: 'bbox_outside_weights'
python_param {
module: 'roi_data_layer.layer'
layer: 'RoIDataLayer'
param_str: "'num_classes': 2" #我只有person一类，该值为类别数+1
}
}
layer {
name: "cls_score"
type: "InnerProduct"
bottom: "fc7"
top: "cls_score"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
inner_product_param {
num_output: 2 #我只有person一类，该值为类别数+1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bbox_pred"
type: "InnerProduct"
bottom: "fc7"
top: "bbox_pred"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
inner_product_param {
num_output: 8 #我只有person一类，该值为（类别数+1）*4
weight_filler {
type: "gaussian"
std: 0.001
}
bias_filler {
type: "constant"
value: 0
}
}
}
5.修改py-faster-rcnn/models/pascal_voc/ZF/faster_rcnn_alt_opt/stage1_rpn_train.pt
name: "ZF"
layer {
name: 'input-data'
type: 'Python'
top: 'data'
top: 'im_info'
top: 'gt_boxes'
python_param {
module: 'roi_data_layer.layer'
layer: 'RoIDataLayer'
param_str: "'num_classes': 2" #我只有person一类，该值为类别数+1
}
}
6.修改py-faster-rcnn/models/pascal_voc/ZF/faster_rcnn_alt_opt/stage2_fast_rcnn_train.pt
name: "ZF"
layer {
name: 'data'
type: 'Python'
top: 'data'
top: 'rois'
top: 'labels'
top: 'bbox_targets'
top: 'bbox_inside_weights'
top: 'bbox_outside_weights'
python_param {
module: 'roi_data_layer.layer'
layer: 'RoIDataLayer'
param_str: "'num_classes': 2" #我只有person一类，该值为类别数+1
}
}
layer {
name: "cls_score"
type: "InnerProduct"
bottom: "fc7"
top: "cls_score"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
inner_product_param {
num_output: 2 #我只有person一类，该值为类别数+1
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bbox_pred"
type: "InnerProduct"
bottom: "fc7"
top: "bbox_pred"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
inner_product_param {
num_output: 8 #我只有person一类，该值为（类别数+1）*4
weight_filler {
type: "gaussian"
std: 0.001
}
bias_filler {
type: "constant"
value: 0
}
}
}
7.修改py-faster-rcnn/models/pascal_voc/ZF/faster_rcnn_alt_opt/stage2_rpn_train.pt
name: "ZF"
layer {
name: 'input-data'
type: 'Python'
top: 'data'
top: 'im_info'
top: 'gt_boxes'
python_param {
module: 'roi_data_layer.layer'
layer: 'RoIDataLayer'
param_str: "'num_classes': 2" #我只有person一类，该值为类别数+1
}
}
8.修改py-faster-rcnn/models/pascal_voc/ZF/faster_rcnn_alt_opt/faster_rcnn_test.pt
layer {
name: "cls_score"
type: "InnerProduct"
bottom: "fc7"
top: "cls_score"
inner_product_param {
num_output: 2 #我只有person一类，该值为类别数+1
}
}
layer {
name: "bbox_pred"
type: "InnerProduct"
bottom: "fc7"
top: "bbox_pred"
inner_product_param {
num_output: 8 #我只有person一类，该值为（类别数+1）*4
}
}
9.修改py-faster-rcnn/lib/datasets/pascal_voc.py
class pascal_voc(imdb):
def __init__(self, image_set, year, devkit_path=None):
imdb.__init__(self, 'voc_' + year + '_' + image_set)
self._year = year
self._image_set = image_set
self._devkit_path = self._get_default_path() if devkit_path is None \
else devkit_path
self._data_path = os.path.join(self._devkit_path, 'VOC' + self._year)
self._classes = ('__background__', # always index 0
'person') #修改自己的标签名
self._class_to_ind = dict(zip(self.classes, xrange(self.num_classes)))
self._image_ext = '.jpg'
self._image_index = self._load_image_set_index()
标签中不用大写字母和中文字符，否则需要另外修改
10. train
删除output文件夹
删除py-faster-rcnn/data/cache文件夹下文件
删除py-faster-rcnn/data/VOCdevkit2007/annotations_cache文件夹下文件
删除 ./data/cache/voc_2007_trainval_gt_roidb.pkl
根目录执行
./experiments/scripts/faster_rcnn_alt_opt.sh 0 ZF pascal_voc
训练结束，模型在output文件夹下。
11.训练时数据类型报错
minibatch.py中，numpy.round函数，只进行四舍五入，不进行取整，导致以该结果进行索引时会报错。
_get_bbox_regression_labels(bbox_target_data, num_classes)函数中start类型定义错误会报错。
修改后的minibatch.py
# --------------------------------------------------------
# Fast R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------
"""Compute minibatch blobs for training a Fast R-CNN network."""
import numpy as np
import numpy.random as npr
import cv2
from fast_rcnn.config import cfg
from utils.blob import prep_im_for_blob, im_list_to_blob
def get_minibatch(roidb, num_classes):
"""Given a roidb, construct a minibatch sampled from it."""
num_images = len(roidb)
# Sample random scales to use for each image in this batch
random_scale_inds = npr.randint(0, high=len(cfg.TRAIN.SCALES),
size=num_images)
assert(cfg.TRAIN.BATCH_SIZE % num_images == 0), \
'num_images ({}) must divide BATCH_SIZE ({})'. \
format(num_images, cfg.TRAIN.BATCH_SIZE)
rois_per_image = cfg.TRAIN.BATCH_SIZE / num_images
#fg_rois_per_image = np.round(cfg.TRAIN.FG_FRACTION * rois_per_image)
fg_rois_per_image = int(np.round(cfg.TRAIN.FG_FRACTION * rois_per_image)) ########################修改处
# Get the input image blob, formatted for caffe
im_blob, im_scales = _get_image_blob(roidb, random_scale_inds)
blobs = {'data': im_blob}
if cfg.TRAIN.HAS_RPN:
assert len(im_scales) == 1, "Single batch only"
assert len(roidb) == 1, "Single batch only"
# gt boxes: (x1, y1, x2, y2, cls)
gt_inds = np.where(roidb[0]['gt_classes'] != 0)[0]
gt_boxes = np.empty((len(gt_inds), 5), dtype=np.float32)
gt_boxes[:, 0:4] = roidb[0]['boxes'][gt_inds, :] * im_scales[0]
gt_boxes[:, 4] = roidb[0]['gt_classes'][gt_inds]
blobs['gt_boxes'] = gt_boxes
blobs['im_info'] = np.array(
[[im_blob.shape[2], im_blob.shape[3], im_scales[0]]],
dtype=np.float32)
else: # not using RPN
# Now, build the region of interest and label blobs
rois_blob = np.zeros((0, 5), dtype=np.float32)
labels_blob = np.zeros((0), dtype=np.float32)
bbox_targets_blob = np.zeros((0, 4 * num_classes), dtype=np.float32)
bbox_inside_blob = np.zeros(bbox_targets_blob.shape, dtype=np.float32)
# all_overlaps = []
for im_i in xrange(num_images):
labels, overlaps, im_rois, bbox_targets, bbox_inside_weights \
= _sample_rois(roidb[im_i], fg_rois_per_image, rois_per_image,
num_classes)
# Add to RoIs blob
rois = _project_im_rois(im_rois, im_scales[im_i])
batch_ind = im_i * np.ones((rois.shape[0], 1))
rois_blob_this_image = np.hstack((batch_ind, rois))
rois_blob = np.vstack((rois_blob, rois_blob_this_image))
# Add to labels, bbox targets, and bbox loss blobs
labels_blob = np.hstack((labels_blob, labels))
bbox_targets_blob = np.vstack((bbox_targets_blob, bbox_targets))
bbox_inside_blob = np.vstack((bbox_inside_blob, bbox_inside_weights))
# all_overlaps = np.hstack((all_overlaps, overlaps))
# For debug visualizations
# _vis_minibatch(im_blob, rois_blob, labels_blob, all_overlaps)
blobs['rois'] = rois_blob
blobs['labels'] = labels_blob
if cfg.TRAIN.BBOX_REG:
blobs['bbox_targets'] = bbox_targets_blob
blobs['bbox_inside_weights'] = bbox_inside_blob
blobs['bbox_outside_weights'] = \
np.array(bbox_inside_blob > 0).astype(np.float32)
return blobs
def _sample_rois(roidb, fg_rois_per_image, rois_per_image, num_classes):
"""Generate a random sample of RoIs comprising foreground and background
examples.
"""
# label = class RoI has max overlap with
labels = roidb['max_classes']
overlaps = roidb['max_overlaps']
rois = roidb['boxes']
# Select foreground RoIs as those with >= FG_THRESH overlap
fg_inds = np.where(overlaps >= cfg.TRAIN.FG_THRESH)[0]
# Guard against the case when an image has fewer than fg_rois_per_image
# foreground RoIs
fg_rois_per_this_image = np.minimum(fg_rois_per_image, fg_inds.size)
# Sample foreground regions without replacement
if fg_inds.size > 0:
fg_inds = npr.choice(
fg_inds, size=fg_rois_per_this_image, replace=False)
# Select background RoIs as those within [BG_THRESH_LO, BG_THRESH_HI)
bg_inds = np.where((overlaps < cfg.TRAIN.BG_THRESH_HI) &
(overlaps >= cfg.TRAIN.BG_THRESH_LO))[0]
# Compute number of background RoIs to take from this image (guarding
# against there being fewer than desired)
bg_rois_per_this_image = rois_per_image - fg_rois_per_this_image
bg_rois_per_this_image = np.minimum(bg_rois_per_this_image,
bg_inds.size)
# Sample foreground regions without replacement
if bg_inds.size > 0:
bg_inds = npr.choice(
bg_inds, size=bg_rois_per_this_image, replace=False)
# The indices that we're selecting (both fg and bg)
keep_inds = np.append(fg_inds, bg_inds)
# Select sampled values from various arrays:
labels = labels[keep_inds]
# Clamp labels for the background RoIs to 0
labels[fg_rois_per_this_image:] = 0
overlaps = overlaps[keep_inds]
rois = rois[keep_inds]
bbox_targets, bbox_inside_weights = _get_bbox_regression_labels(
roidb['bbox_targets'][keep_inds, :], num_classes)
return labels, overlaps, rois, bbox_targets, bbox_inside_weights
def _get_image_blob(roidb, scale_inds):
"""Builds an input blob from the images in the roidb at the specified
scales.
"""
num_images = len(roidb)
processed_ims = []
im_scales = []
for i in xrange(num_images):
im = cv2.imread(roidb[i]['image'])
if roidb[i]['flipped']:
im = im[:, ::-1, :]
target_size = cfg.TRAIN.SCALES[scale_inds[i]]
im, im_scale = prep_im_for_blob(im, cfg.PIXEL_MEANS, target_size,
cfg.TRAIN.MAX_SIZE)
im_scales.append(im_scale)
processed_ims.append(im)
# Create a blob to hold the input images
blob = im_list_to_blob(processed_ims)
return blob, im_scales
def _project_im_rois(im_rois, im_scale_factor):
"""Project image RoIs into the rescaled training image."""
rois = im_rois * im_scale_factor
return rois
def _get_bbox_regression_labels(bbox_target_data, num_classes):
"""Bounding-box regression targets are stored in a compact form in the
roidb.
This function expands those targets into the 4-of-4*K representation used
by the network (i.e. only one class has non-zero targets). The loss weights
are similarly expanded.
Returns:
bbox_target_data (ndarray): N x 4K blob of regression targets
bbox_inside_weights (ndarray): N x 4K blob of loss weights
"""
clss = bbox_target_data[:, 0]
bbox_targets = np.zeros((clss.size, 4 * num_classes), dtype=np.float32)
bbox_inside_weights = np.zeros(bbox_targets.shape, dtype=np.float32)
inds = np.where(clss > 0)[0]
for ind in inds:
cls = clss[ind]
#start = 4 * cls
start = int( 4 * cls ) ########################修改处
end = start + 4
bbox_targets[ind, start:end] = bbox_target_data[ind, 1:]
bbox_inside_weights[ind, start:end] = cfg.TRAIN.BBOX_INSIDE_WEIGHTS
return bbox_targets, bbox_inside_weights
def _vis_minibatch(im_blob, rois_blob, labels_blob, overlaps):
"""Visualize a mini-batch for debugging."""
import matplotlib.pyplot as plt
for i in xrange(rois_blob.shape[0]):
rois = rois_blob[i, :]
im_ind = rois[0]
roi = rois[1:]
im = im_blob[im_ind, :, :, :].transpose((1, 2, 0)).copy()
im += cfg.PIXEL_MEANS
im = im[:, :, (2, 1, 0)]
im = im.astype(np.uint8)
cls = labels_blob[i]
plt.imshow(im)
print 'class: ', cls, ' overlap: ', overlaps[i]
plt.gca().add_patch(
plt.Rectangle((roi[0], roi[1]), roi[2] - roi[0],
roi[3] - roi[1], fill=False,
edgecolor='r', linewidth=3)
)
plt.show()
12. test images，修改py-faster-rcnn/tools/demo.py
CLASSES = ('__background__',
'person')#修改自己的标签
NETS = {'vgg16': ('VGG16',
'VGG16_faster_rcnn_final.caffemodel'),
'zf': ('ZF',
#'ZF_faster_rcnn_final.caffemodel')}
'elevator_faster_rcnn_final.caffemodel')}#修改自己的模型
#im_names = ['000456.jpg', '000542.jpg', '001150.jpg',
# '001763.jpg', '004545.jpg']
im_names = ['1.jpg', '2.jpg', '3.jpg']#修改自己的测试图
根目录执行
./tools/demo.py --net zf
13. test a video
tools文件夹下增加一个demo_video.py
#!/usr/bin/env python
# --------------------------------------------------------
# Faster R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------
"""
Demo script showing detections in sample images.
See README.md for installation instructions before running.
"""
import _init_paths
from fast_rcnn.config import cfg
from fast_rcnn.test import im_detect
from fast_rcnn.nms_wrapper import nms
from utils.timer import Timer
import matplotlib.pyplot as plt
import numpy as np
import scipy.io as sio
import caffe, os, sys, cv2
import argparse
CLASSES = ('__background__',
'person') #修改自己的标签
NETS = {'vgg16': ('VGG16',
'VGG16_faster_rcnn_final.caffemodel'),
'zf': ('ZF',
#'ZF_faster_rcnn_final.caffemodel')}
'elevator_faster_rcnn_final.caffemodel')} #修改自己的模型
def vis_detections(im, class_name, dets, thresh=0.5):
"""Draw detected bounding boxes."""
inds = np.where(dets[:, -1] >= thresh)[0]
if len(inds) == 0:
return
im = im[:, :, (2, 1, 0)]
fig, ax = plt.subplots(figsize=(12, 12))
ax.imshow(im, aspect='equal')
for i in inds:
bbox = dets[i, :4]
score = dets[i, -1]
ax.add_patch(
plt.Rectangle((bbox[0], bbox[1]),
bbox[2] - bbox[0],
bbox[3] - bbox[1], fill=False,
edgecolor='red', linewidth=3.5)
)
ax.text(bbox[0], bbox[1] - 2,
'{:s} {:.3f}'.format(class_name, score),
bbox=dict(facecolor='blue', alpha=0.5),
fontsize=14, color='white')
ax.set_title(('{} detections with '
'p({} | box) >= {:.1f}').format(class_name, class_name,
thresh),
fontsize=14)
plt.axis('off')
plt.tight_layout()
plt.draw()
def demo(net, image_name):
"""Detect object classes in an image using pre-computed object proposals."""
# Load the demo image
#im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name)
#im = cv2.imread(im_file)
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = im_detect(net, im)
timer.toc()
print ('Detection took {:.3f}s for '
'{:d} object proposals').format(timer.total_time, boxes.shape[0])
# Visualize detections for each class
CONF_THRESH = 0.8
NMS_THRESH = 0.3
for cls_ind, cls in enumerate(CLASSES[1:]):
cls_ind += 1 # because we skipped background
cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]
cls_scores = scores[:, cls_ind]
dets = np.hstack((cls_boxes,
cls_scores[:, np.newaxis])).astype(np.float32)
keep = nms(dets, NMS_THRESH)
dets = dets[keep, :]
vis_detections(im, cls, dets, thresh=CONF_THRESH)
def parse_args():
"""Parse input arguments."""
parser = argparse.ArgumentParser(description='Faster R-CNN demo')
parser.add_argument('--gpu', dest='gpu_id', help='GPU device id to use [0]',
default=0, type=int)
parser.add_argument('--cpu', dest='cpu_mode',
help='Use CPU mode (overrides --gpu)',
action='store_true')
parser.add_argument('--net', dest='demo_net', help='Network to use [vgg16]',
choices=NETS.keys(), default='vgg16')
args = parser.parse_args()
return args
if __name__ == '__main__':
cfg.TEST.HAS_RPN = True # Use RPN for proposals
args = parse_args()
prototxt = os.path.join(cfg.MODELS_DIR, NETS[args.demo_net][0],
'faster_rcnn_alt_opt', 'faster_rcnn_test.pt')
caffemodel = os.path.join(cfg.DATA_DIR, 'faster_rcnn_models',
NETS[args.demo_net][1])
if not os.path.isfile(caffemodel):
raise IOError(('{:s} not found.\nDid you run ./data/script/'
'fetch_faster_rcnn_models.sh?').format(caffemodel))
if args.cpu_mode:
caffe.set_mode_cpu()
else:
caffe.set_mode_gpu()
caffe.set_device(args.gpu_id)
cfg.GPU_ID = args.gpu_id
net = caffe.Net(prototxt, caffemodel, caffe.TEST)
print '\n\nLoaded network {:s}'.format(caffemodel)
# Warmup on a dummy image
im = 128 * np.ones((300, 500, 3), dtype=np.uint8)
for i in xrange(2):
_, _= im_detect(net, im)
videoCapture = cv2.VideoCapture('/xxx/xxx/py-faster-rcnn/1.mp4') #测试一段取自自己数据集的视频
success, im = videoCapture.read()
while success :
demo(net, im)
success, im = videoCapture.read()
if cv2.waitKey(10) & 0xFF == ord('q'):
break
videoCapture.release()
cv2.destroyAllWindows()
根目录执行
python ./tools/demo_video.py --net zf
14. 计算mAP
删除 ./data/VOCdevkit2007/annotations_cache/annots.pkl
删除 ./data/cache/voc_2007_trainval_gt_roidb.pkl
根目录执行
python tools/test_net.py --gpu 0 --def models/pascal_voc/ZF/faster_rcnn_alt_opt/faster_rcnn_test.pt --net output/faster_rcnn_alt_opt/voc_2007_trainval/ZF_faster_rcnn_final.caffemodel --cfg experiments/cfgs/faster_rcnn_alt_opt.ym
参考
https://blog.csdn.net/u012910595/article/details/78481422
https://blog.csdn.net/sinat_30071459/article/details/51332084