def detect(net, im):
"""Detect object classes in an image using pre-computed object proposals."""
########!!!!!!!!!!!! cancel iamge load, use image pass in
# 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 = 0.4
NMS_THRESH = 0.3
# For human detecting
# pdb.set_trace()
cls_ind = 15
cls = CLASSES[cls_ind]
# 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, :]
#print dets
return cls, dets
def setupNet():
#if __name__ == '__main__':
cfg.TEST.HAS_RPN = True # Use RPN for proposals
#args = parse_args()
demo_net = 'zf'
gpu_id = 0
cpu_mode = 0
prototxt = os.path.join(cfg.MODELS_DIR, NETS[demo_net][0],
'faster_rcnn_alt_opt', 'faster_rcnn_test.pt')
caffemodel = os.path.join(cfg.DATA_DIR, 'faster_rcnn_models',
NETS[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 cpu_mode:
caffe.set_mode_cpu()
else:
caffe.set_mode_gpu()
caffe.set_device(gpu_id)
cfg.GPU_ID = 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)
print 'Network is loaded'
return net
def get_query_local_feat(self, query, box=None):
'''
Extract local query feature using bbx
'''
if box is None:
# For paris and oxford
query, bbx = self.query_info(query)
else:
# locations are provided
xmin = box[0]
ymin = box[1]
xmax = box[2]
ymax = box[3]
im = cv2.imread(query)
height = np.shape(im)[0]
width = np.shape(im)[1]
# Forward pass
scores, boxes = test_ops.im_detect(self.net, im, boxes=None)
# Get conv5 layer
feat = self.net.blobs[self.layer].data.squeeze()
# Get the image/feature ratio
mult_h = float(np.shape(feat)[1]) / height
mult_w = float(np.shape(feat)[2]) / width
# Resize the bounding box to feature size
if box is None:
# Adjust query bounding box to feature space
bbx[0] *= mult_w
bbx[2] *= mult_w
bbx[1] *= mult_h
bbx[3] *= mult_h
else:
bbx = [
int(math.floor(xmin * mult_w)),
int(math.floor(ymin * mult_h)),
int(math.ceil(xmax * mult_w)),
int(math.ceil(ymax * mult_h))
]
# Crop local features with bounding box
local_feat = feat[:, bbx[1]:bbx[3], bbx[0]:bbx[2]]
# sum pool
if self.pooling is 'sum':
local_feat = np.sum(np.sum(local_feat, axis=1), axis=1)
else:
local_feat = np.max(np.max(local_feat, axis=1), axis=1)
return local_feat
def extract_feat_image(self,image):
im = cv2.imread(image)
scores, boxes = test_ops.im_detect(self.net, im, boxes=None)
feat = self.net.blobs[self.layer].data
return feat
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('/home/shelly/superstar/star/SuperNova/static/upload',image_name)
# change filepath
im_file = os.path.join(
'/home/shelly/flask/star/star/SuperNova/static/upload', 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 = 0.1
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, image_name, thresh=CONF_THRESH)
def demo(sess, 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_file = os.path.join('/home/corgi/Lab/label/pos_frame/ACCV/training/000001/',image_name)
im = cv2.imread(im_file)
# Detect all object classes and regress object bounds
timer = Timer()
timer.tic()
scores, boxes = im_detect(sess, 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
im = im[:, :, (2, 1, 0)]
fig, ax = plt.subplots(figsize=(12, 12))
ax.imshow(im, aspect='equal')
CONF_THRESH = 0.5
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, ax, thresh=CONF_THRESH)
def test(a):
cfg.TEST.HAS_RPN = True # Use RPN for proposals
# args = parse_args()
prototxt = 'static/model/faster_rcnn_test.pt'
caffemodel = 'static/model/VGG16_faster_rcnn_final.caffemodel'
if not os.path.isfile(caffemodel):
raise IOError(('{:s} not found.\nDid you run ./data/script/'
'fetch_faster_rcnn_models.sh?').format(caffemodel))
caffe.set_mode_gpu()
caffe.set_device(0)
cfg.GPU_ID = 0
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)
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
print 'Demo for data/demo/{}'.format(a)
demo(net, a)
# plt.savefig("/home/shelly/superstar/star/SuperNova/index/static/test3.jpg",dpi=300)
# change filepath
plt.savefig(
"/home/shelly/flask/star/star/SuperNova/index/static/test3.jpg",
dpi=300)
def extract_feat_image(self, image, layer_roi='pool5'): im = cv2.imread(image) scores, boxes = test_ops.im_detect(self.net, im, boxes = None, REG_BOXES=self.REG_BOXES) # extract feature feat = self.net.blobs[layer_roi].data return feat, boxes, scores
def get_query_local_feat(self, query, box=None):
im = cv2.imread(query)
_ = test_ops.im_detect(self.net, im, boxes=None)
feat = self.net.blobs[self.layer].data.squeeze()
height, width = im.shape
mult_h = float(np.shape(feat)[1]) / height
mult_w = float(np.shape(feat)[2]) / width
if box is None:
query, bbx = self.query_info(query)
bbx[0] *= mult_w
bbx[2] *= mult_w
bbx[1] *= mult_h
bbx[3] *= mult_h
else:
xmin, ymin, xmax, ymax = box[0:4]
bbx = [
int(math.floor(xmin * mult_w)),
int(math.floor(ymin * mult_h)),
int(math.ceil(xmax * mult_w)),
int(math.ceil(ymax * mult_h))
]
local_feat = feat[:, bbx[1]:bbx[3], bbx[0]:bbx[2]]
return self.pool_feats(local_feat)
def image2features(self, im):
scores, boxes = test_ops.im_detect(self.net,
im,
boxes=None,
REG_BOXES=self.use_regressed_boxes)
feat = self.net.blobs[self.layer_roi].data
return feat, boxes, scores
def extract_feat_image(self, image):
im = cv2.imread(image)
scores, boxes = test_ops.im_detect(self.net, im, boxes=None)
feat = self.net.blobs[self.layer].data
return feat
def extract_feat_image(self, sess, image):
im = cv2.imread(image)
layer_roi = 'pool_5'
scores, boxes, feat = test_ops.im_detect(sess, self.net, layer_roi, im, False, boxes = None)
return feat,boxes,scores
def get_query_local_feat(self,query,box=None):
'''
Extract local query feature using bbx
'''
if box is None:
# For paris and oxford
query,bbx = self.query_info(query)
else:
# locations are provided
xmin = box[0]
ymin = box[1]
xmax = box[2]
ymax = box[3]
im = cv2.imread(query)
height = np.shape(im)[0]
width = np.shape(im)[1]
# Forward pass
scores, boxes = test_ops.im_detect(self.net, im, boxes = None)
# Get conv5 layer
feat = self.net.blobs[self.layer].data.squeeze()
# Get the image/feature ratio
mult_h = float(np.shape(feat)[1])/height
mult_w = float(np.shape(feat)[2])/width
# Resize the bounding box to feature size
if box is None:
# Adjust query bounding box to feature space
bbx[0] *= mult_w
bbx[2] *= mult_w
bbx[1] *= mult_h
bbx[3] *= mult_h
else:
bbx = [int(math.floor(xmin*mult_w)),int(math.floor(ymin*mult_h)),int(math.ceil(xmax*mult_w)),int(math.ceil(ymax*mult_h))]
# Crop local features with bounding box
local_feat = feat[:,bbx[1]:bbx[3],bbx[0]:bbx[2]]
# sum pool
if self.pooling is 'sum':
local_feat = np.sum(np.sum(local_feat,axis=1),axis=1)
else:
local_feat = np.max(np.max(local_feat,axis=1),axis=1)
return local_feat
def demo(net, image_name):
im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name)
im = cv2.imread(im_file)
det_boxes, det_probs, det_class = im_detect(net, im)
print('det_boxes: ', det_boxes)
print('det_probs: ', det_probs)
print('det_class: ', det_class)
def extract_feat_image(self, image, layer_roi='pool5'):
im = cv2.imread(image)
scores, boxes = test_ops.im_detect(self.net,
im,
boxes=None,
REG_BOXES=self.REG_BOXES)
# extract feature
feat = self.net.blobs[layer_roi].data
return feat, boxes, scores
def extract_feat_image(self, sess, image):
im = cv2.imread(image)
scores, boxes, feat = test_ops.im_detect(sess,
self.net,
self.layer,
im,
True,
boxes=None)
# feat = self.net.get_output(self.layer)
return feat
def get_query_local_feat(self, query, box=None):
im = cv2.imread(query)
_ = test_ops.im_detect(self.net, im, boxes = None)
feat = self.net.blobs[self.layer].data.squeeze()
height, width = im.shape
mult_h = float(np.shape(feat)[1]) / height
mult_w = float(np.shape(feat)[2]) / width
if box is None:
query, bbx = self.query_info(query)
bbx[0] *= mult_w
bbx[2] *= mult_w
bbx[1] *= mult_h
bbx[3] *= mult_h
else:
xmin, ymin, xmax, ymax = box[0:4]
bbx = [int(math.floor(xmin*mult_w)),int(math.floor(ymin*mult_h)),int(math.ceil(xmax*mult_w)),int(math.ceil(ymax*mult_h))]
local_feat = feat[:,bbx[1]:bbx[3],bbx[0]:bbx[2]]
return self.pool_feats(local_feat)
def demo(sess, net, image_name):
"""Detect object classes in an image using pre-computed object proposals."""
# im_names = ['000456.jpg', '000542.jpg', '001150.jpg',
# '001763.jpg', '004545.jpg']
#一张张图片输入
# net = vgg16()
# demo(sess, net, im_name)
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()
#输入 net = vgg16() im一张图片
scores, boxes = im_detect(sess, net, im)
# post_nms_topN = cfg[cfg_key].RPN_POST_NMS_TOP_N#__C.TEST.RPN_POST_NMS_TOP_N = 300 非极大值抑制输出的 最大个数
# nms_thresh = cfg[cfg_key].RPN_NMS_THRESH#__C.TEST.RPN_NMS_THRESH = 0.7
# scores 是rpn scores = self._predictions['cls_prob'] = 每个类别的概率cls_score 讲过soft_max得到
# pred_boxes
# pred_boxes = bbox_transform_inv(boxes, box_deltas)
# 做回归预测 两条路劲rpn得到的的 box_deltas 作为 dx dy dw dh 与 筛选出来的框做回归预测
# pred_boxes anchors回归预测后的值
# return scores, pred_boxes
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:]):#CLASSES就是英文标签
cls_ind += 1 # because we skipped background
cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]
#得到抽取出来的 一个框 一个 boxes shape (?, 21*4) 得到 [?*21,4]
cls_scores = scores[:, cls_ind]#scores shape (？，21) # 得到[?*21]
dets = np.hstack((cls_boxes,# [?*21,4]
cls_scores[:, np.newaxis])).astype(np.float32)#[?*21,1]
#得到的是[?*21,x,y,w,h,scores] 0.3
#所有的框预测 21个类别 输入的是 所有的框预测一个类别的框与得分值
# 是一个一个类别输入NMS 假如类别1 则输入 [?,x,y,w,h,scores]
keep = nms(dets, NMS_THRESH)#为什么要用 (cpu)gpu_nms.pys
#nms 纯python语言实现：简介方便、速度慢
#Cython是一个快速生成Python扩展模块的工具，从语法层面上来讲是Python语法和C语言语法的混血，
# 当Python性能遇到瓶颈时，Cython直接将C的原生速度植入Python程序，这样使Python程序无需使用C重写
# ，能快速整合原有的Python程序，这样使得开发效率和执行效率都有很大的提高，而这些中间的部分，
# 都是Cython帮我们做了。
#https://www.cnblogs.com/king-lps/p/9031568.html 解释
# 之前的 非极大值抑制 作用实在rpn路径上的 rpn路径就是为了做推荐而已 推荐 VGG16特征出来的框，但是太多 所以需要筛选
#这里 是筛选出来之后 再做 nms
#CONF_THRESH = 0.8
#NMS_THRESH = 0.3
dets = dets[keep, :]
#im输入的图像经过限制在600，1000
#cls 是实际的英文标签
# dets是 [?*21,x,y,w,h,scores] 经过nms 得到 的 0.3
#for cls_ind, cls in enumerate(CLASSES[1:]):#CLASSES就是英文标签
#所有的框预测 21个类别 输入的是 所有的框预测一个类别的框与得分值
# 进行NMS后 得到的框就是需要输出的框 他对应的英文标签是 cls #CONF_THRESH = 0.8
vis_detections(im, cls, dets, thresh=CONF_THRESH)
def image2features(self, im):
_ = test_ops.im_detect(self.net, im, boxes=None)
feats = self.net.blobs[self.layer].data.squeeze()
return self.pool_feats(feats)
def image2features(self, im):
scores, boxes = test_ops.im_detect(self.net, im, boxes=None, REG_BOXES=self.use_regressed_boxes)
feat = self.net.blobs[self.layer_roi].data
return feat, boxes, scores
if not os.path.isfile(args.model):
raise IOError(('{:s} not found.\nDid you run ./data/script/'
'fetch_faster_rcnn_models.sh?').format(caffemodel))
# init session
sess = tf.Session(config=tf.ConfigProto(allow_soft_placement=True))
# load network
net = get_network(args.demo_net)
# load model
saver = tf.train.Saver()
saver.restore(sess, args.model)
#sess.run(tf.initialize_all_variables())
print '\n\nLoaded network {:s}'.format(args.model)
# Warmup on a dummy image
im = 128 * np.ones((720, 1280, 3), dtype=np.uint8)
for i in xrange(2):
_, _ = im_detect(sess, net, im)
#im_names = ['000001.jpg','000002.jpg','000005.jpg','000050.jpg','000100.jpg']
im_names = [
'000456.jpg', '000542.jpg', '001150.jpg', '001763.jpg', '004545.jpg'
]
for im_name in im_names:
print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
print 'Demo for data/demo/{}'.format(im_name)
demo(sess, net, im_name)
plt.show()
