def detect_image(self, image_id, image):
self.confidence = 0.01
self.iou = 0.45
f = open("./input/detection-results/" + image_id + ".txt", "w")
with torch.no_grad():
image_shape = np.array(np.shape(image)[0:2])
old_width = image_shape[1]
old_height = image_shape[0]
width, height = get_new_img_size(old_width, old_height)
image = image.resize([width, height], Image.BICUBIC)
photo = np.array(image, dtype=np.float32) / 255
photo = np.transpose(photo, (2, 0, 1))
images = []
images.append(photo)
images = np.asarray(images)
images = torch.from_numpy(images)
if self.cuda:
images = images.cuda()
roi_cls_locs, roi_scores, rois, roi_indices = self.model(images)
decodebox = DecodeBox(self.std, self.mean, self.num_classes)
outputs = decodebox.forward(roi_cls_locs,
roi_scores,
rois,
height=height,
width=width,
nms_iou=self.iou,
score_thresh=self.confidence)
if len(outputs) == 0:
return
bbox = outputs[:, :4]
conf = outputs[:, 4]
label = outputs[:, 5]
bbox[:, 0::2] = (bbox[:, 0::2]) / width * old_width
bbox[:, 1::2] = (bbox[:, 1::2]) / height * old_height
bbox = np.array(bbox, np.int32)
for i, c in enumerate(label):
predicted_class = self.class_names[int(c)]
score = str(conf[i])
left, top, right, bottom = bbox[i]
f.write("%s %s %s %s %s %s\n" %
(predicted_class, score[:6], str(int(left)), str(
int(top)), str(int(right)), str(int(bottom))))
f.close()
return
def detect_image(self, image_id, image):
self.confidence = 0.01
f = open("./input/detection-results/" + image_id + ".txt", "w")
image_shape = np.array(np.shape(image)[0:2])
old_width, old_height = image_shape[1], image_shape[0]
old_image = copy.deepcopy(image)
#---------------------------------------------------------#
# 给原图像进行resize，resize到短边为600的大小上
#---------------------------------------------------------#
width, height = get_new_img_size(old_width, old_height)
image = image.resize([width, height], Image.BICUBIC)
photo = np.array(image, dtype=np.float64)
#-----------------------------------------------------------#
# 图片预处理，归一化。
#-----------------------------------------------------------#
photo = preprocess_input(np.expand_dims(photo, 0))
rpn_pred = self.model_rpn.predict(photo)
#-----------------------------------------------------------#
# 将建议框网络的预测结果进行解码
#-----------------------------------------------------------#
base_feature_width, base_feature_height = self.get_img_output_length(
width, height)
anchors = get_anchors([base_feature_width, base_feature_height], width,
height)
rpn_results = self.bbox_util.detection_out_rpn(rpn_pred, anchors)
#-------------------------------------------------------------#
# 在获得建议框和共享特征层后，将二者传入classifier中进行预测
#-------------------------------------------------------------#
base_layer = rpn_pred[2]
proposal_box = np.array(rpn_results)[:, :, 1:]
temp_ROIs = np.zeros_like(proposal_box)
temp_ROIs[:, :, [0, 1, 2, 3]] = proposal_box[:, :, [1, 0, 3, 2]]
classifier_pred = self.model_classifier.predict(
[base_layer, temp_ROIs])
#-------------------------------------------------------------#
# 利用classifier的预测结果对建议框进行解码，获得预测框
#-------------------------------------------------------------#
results = self.bbox_util.detection_out_classifier(
classifier_pred, proposal_box, self.config, self.confidence)
if len(results[0]) == 0:
return old_image
results = np.array(results[0])
boxes = results[:, :4]
top_conf = results[:, 4]
top_label_indices = results[:, 5]
boxes[:, [0, 2]] = boxes[:, [0, 2]] * old_width
boxes[:, [1, 3]] = boxes[:, [1, 3]] * old_height
for i, c in enumerate(top_label_indices):
predicted_class = self.class_names[int(c)]
score = str(top_conf[i])
left, top, right, bottom = boxes[i]
f.write("%s %s %s %s %s %s\n" %
(predicted_class, score[:6], str(int(left)), str(
int(top)), str(int(right)), str(int(bottom))))
f.close()
return
def detect_image(self, image):
image_shape = np.array(np.shape(image)[0:2])
old_width = image_shape[1]
old_height = image_shape[0]
old_image = copy.deepcopy(image)
width, height = get_new_img_size(old_width, old_height)
image = image.resize([width, height])
photo = np.array(image, dtype=np.float64)
# 图片预处理，归一化
photo = preprocess_input(np.expand_dims(photo, 0))
preds = self.model_rpn.predict(photo)
# 将预测结果进行解码
anchors = get_anchors(self.get_img_output_length(width, height), width,
height)
rpn_results = self.bbox_util.detection_out(preds,
anchors,
1,
confidence_threshold=0)
R = rpn_results[0][:, 2:]
R[:, 0] = np.array(np.round(R[:, 0] * width / self.config.rpn_stride),
dtype=np.int32)
R[:, 1] = np.array(np.round(R[:, 1] * height / self.config.rpn_stride),
dtype=np.int32)
R[:, 2] = np.array(np.round(R[:, 2] * width / self.config.rpn_stride),
dtype=np.int32)
R[:, 3] = np.array(np.round(R[:, 3] * height / self.config.rpn_stride),
dtype=np.int32)
R[:, 2] -= R[:, 0]
R[:, 3] -= R[:, 1]
base_layer = preds[2]
delete_line = []
for i, r in enumerate(R):
if r[2] < 1 or r[3] < 1:
delete_line.append(i)
R = np.delete(R, delete_line, axis=0)
bboxes = []
probs = []
labels = []
for jk in range(R.shape[0] // self.config.num_rois + 1):
ROIs = np.expand_dims(R[self.config.num_rois *
jk:self.config.num_rois * (jk + 1), :],
axis=0)
if ROIs.shape[1] == 0:
break
if jk == R.shape[0] // self.config.num_rois:
#pad R
curr_shape = ROIs.shape
target_shape = (curr_shape[0], self.config.num_rois,
curr_shape[2])
ROIs_padded = np.zeros(target_shape).astype(ROIs.dtype)
ROIs_padded[:, :curr_shape[1], :] = ROIs
ROIs_padded[0, curr_shape[1]:, :] = ROIs[0, 0, :]
ROIs = ROIs_padded
[P_cls, P_regr] = self.model_classifier.predict([base_layer, ROIs])
for ii in range(P_cls.shape[1]):
if np.max(P_cls[0, ii, :-1]) < self.confidence:
continue
label = np.argmax(P_cls[0, ii, :-1])
(x, y, w, h) = ROIs[0, ii, :]
cls_num = np.argmax(P_cls[0, ii, :-1])
(tx, ty, tw, th) = P_regr[0, ii, 4 * cls_num:4 * (cls_num + 1)]
tx /= self.config.classifier_regr_std[0]
ty /= self.config.classifier_regr_std[1]
tw /= self.config.classifier_regr_std[2]
th /= self.config.classifier_regr_std[3]
cx = x + w / 2.
cy = y + h / 2.
cx1 = tx * w + cx
cy1 = ty * h + cy
w1 = math.exp(tw) * w
h1 = math.exp(th) * h
x1 = cx1 - w1 / 2.
y1 = cy1 - h1 / 2.
x2 = cx1 + w1 / 2
y2 = cy1 + h1 / 2
x1 = int(round(x1))
y1 = int(round(y1))
x2 = int(round(x2))
y2 = int(round(y2))
bboxes.append([x1, y1, x2, y2])
probs.append(np.max(P_cls[0, ii, :-1]))
labels.append(label)
if len(bboxes) == 0:
return old_image
# 筛选出其中得分高于confidence的框
labels = np.array(labels)
probs = np.array(probs)
boxes = np.array(bboxes, dtype=np.float32)
boxes[:, 0] = boxes[:, 0] * self.config.rpn_stride / width
boxes[:, 1] = boxes[:, 1] * self.config.rpn_stride / height
boxes[:, 2] = boxes[:, 2] * self.config.rpn_stride / width
boxes[:, 3] = boxes[:, 3] * self.config.rpn_stride / height
results = np.array(
self.bbox_util.nms_for_out(np.array(labels), np.array(probs),
np.array(boxes), self.num_classes - 1,
0.4))
top_label_indices = results[:, 0]
top_conf = results[:, 1]
boxes = results[:, 2:]
boxes[:, 0] = boxes[:, 0] * old_width
boxes[:, 1] = boxes[:, 1] * old_height
boxes[:, 2] = boxes[:, 2] * old_width
boxes[:, 3] = boxes[:, 3] * old_height
font = ImageFont.truetype(font='model_data/simhei.ttf',
size=np.floor(3e-2 * np.shape(image)[1] +
0.5).astype('int32'))
thickness = (np.shape(old_image)[0] +
np.shape(old_image)[1]) // old_width * 2
image = old_image
for i, c in enumerate(top_label_indices):
predicted_class = self.class_names[int(c)]
score = top_conf[i]
left, top, right, bottom = boxes[i]
top = top - 5
left = left - 5
bottom = bottom + 5
right = right + 5
top = max(0, np.floor(top + 0.5).astype('int32'))
left = max(0, np.floor(left + 0.5).astype('int32'))
bottom = min(
np.shape(image)[0],
np.floor(bottom + 0.5).astype('int32'))
right = min(
np.shape(image)[1],
np.floor(right + 0.5).astype('int32'))
# 画框框
label = '{} {:.2f}'.format(predicted_class, score)
draw = ImageDraw.Draw(image)
label_size = draw.textsize(label, font)
label = label.encode('utf-8')
print(label)
if top - label_size[1] >= 0:
text_origin = np.array([left, top - label_size[1]])
else:
text_origin = np.array([left, top + 1])
for i in range(thickness):
draw.rectangle([left + i, top + i, right - i, bottom - i],
outline=self.colors[int(c)])
draw.rectangle(
[tuple(text_origin),
tuple(text_origin + label_size)],
fill=self.colors[int(c)])
draw.text(text_origin,
str(label, 'UTF-8'),
fill=(0, 0, 0),
font=font)
del draw
return image
def detect_image(self, image_id, image, savepath):
image_shape = np.array(np.shape(image)[0:2])
old_width = image_shape[1]
old_height = image_shape[0]
old_image = copy.deepcopy(image)
width, height = get_new_img_size(old_width, old_height)
image = image.resize([width, height])
photo = np.array(image, dtype=np.float32) / 255
photo = np.transpose(photo, (2, 0, 1))
with torch.no_grad():
images = []
images.append(photo)
images = np.asarray(images)
images = torch.from_numpy(images).cuda()
roi_cls_locs, roi_scores, rois, roi_indices, feature = self.model(
images)
decodebox = DecodeBox(self.std, self.mean, self.num_classes)
outputs = decodebox.forward(roi_cls_locs,
roi_scores,
rois,
feature,
height=height,
width=width,
score_thresh=self.confidence)
if len(outputs) == 0:
return old_image
if np.size(outputs, 0) > 4:
outputs = outputs[np.argsort(outputs[:, 4])]
outputs = outputs[-4:, :]
bbox = outputs[:, :4]
conf = outputs[:, 4]
label = outputs[:, 5]
f = outputs[:, 6:]
f_size = np.size(f, 0)
if f_size < 4:
k = 4 - f_size
cc = 0
for lab in label:
if (lab == 1) or (lab == 3) or (lab == 5):
conbin_f = f[cc, :]
conbin_f = conbin_f.reshape(1, 2048)
for num in range(0, k):
f = np.append(f, conbin_f, axis=0)
break
cc = cc + 1
bbox[:, 0::2] = (bbox[:, 0::2]) / width * old_width
bbox[:, 1::2] = (bbox[:, 1::2]) / height * old_height
bbox = np.array(bbox, np.int32)
f = np.array(f, np.float32).reshape((4, 2048))
print(np.size(f))
# image = old_image
# thickness = (np.shape(old_image)[0] + np.shape(old_image)[1]) // old_width * 2
# font = ImageFont.truetype(font='model_data/simhei.ttf',
# size=np.floor(3e-2 * np.shape(image)[1] + 0.5).astype('int32'))
#
# for i, c in enumerate(label):
# predicted_class = self.class_names[int(c)]
# score = conf[i]
#
# left, top, right, bottom = bbox[i]
# top = top - 5
# left = left - 5
# bottom = bottom + 5
# right = right + 5
#
# top = max(0, np.floor(top + 0.5).astype('int32'))
# left = max(0, np.floor(left + 0.5).astype('int32'))
# bottom = min(np.shape(image)[0], np.floor(bottom + 0.5).astype('int32'))
# right = min(np.shape(image)[1], np.floor(right + 0.5).astype('int32'))
#
# # 画框框
# label = '{} {:.2f}'.format(predicted_class, score)
# draw = ImageDraw.Draw(image)
# label_size = draw.textsize(label, font)
# label = label.encode('utf-8')
# print(label)
#
# if top - label_size[1] >= 0:
# text_origin = np.array([left, top - label_size[1]])
# else:
# text_origin = np.array([left, top + 1])
#
# for i in range(thickness):
# draw.rectangle(
# [left + i, top + i, right - i, bottom - i],
# outline=self.colors[int(c)])
# draw.rectangle(
# [tuple(text_origin), tuple(text_origin + label_size)],
# fill=self.colors[int(c)])
# draw.text(text_origin, str(label, 'UTF-8'), fill=(0, 0, 0), font=font)
# del draw
#
# image.save(savepath)
if np.size(f, 0) != 4:
print(
"xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
)
return {
'image_id': image_id,
'image_h': height,
'image_w': width,
'num_boxes': np.size(bbox, 0),
'boxes': base64.b64encode(bbox),
'features': base64.b64encode(f)
}
def detect_image(self, image):
with torch.no_grad():
start_time = time.time()
image_shape = np.array(np.shape(image)[0:2])
old_width = image_shape[1]
old_height = image_shape[0]
old_image = copy.deepcopy(image)
width, height = get_new_img_size(old_width, old_height)
image = image.resize([width, height], Image.BICUBIC)
photo = np.array(image, dtype=np.float32) / 255
photo = np.transpose(photo, (2, 0, 1))
images = []
images.append(photo)
images = np.asarray(images)
images = torch.from_numpy(images)
if self.cuda:
images = images.cuda()
#非凸性优化，边界框矫正
roi_cls_locs, roi_scores, rois, roi_indices = self.model(images)
decodebox = DecodeBox(self.std, self.mean, self.num_classes)
outputs = decodebox.forward(roi_cls_locs,
roi_scores,
rois,
height=height,
width=width,
nms_iou=self.iou,
score_thresh=self.confidence)
if len(outputs) == 0:
return old_image
bbox = outputs[:, :4]
conf = outputs[:, 4]
label = outputs[:, 5]
bbox[:, 0::2] = (bbox[:, 0::2]) / width * old_width
bbox[:, 1::2] = (bbox[:, 1::2]) / height * old_height
bbox = np.array(bbox, np.int32)
image = old_image
thickness = (np.shape(old_image)[0] +
np.shape(old_image)[1]) // old_width * 2
font = ImageFont.truetype(font='model_data/simhei.ttf',
size=np.floor(3e-2 * np.shape(image)[1] +
0.5).astype('int32'))
for i, c in enumerate(label):
predicted_class = self.class_names[int(c)]
score = conf[i]
left, top, right, bottom = bbox[i]
top = top - 5
left = left - 5
bottom = bottom + 5
right = right + 5
top = max(0, np.floor(top + 0.5).astype('int32'))
left = max(0, np.floor(left + 0.5).astype('int32'))
bottom = min(
np.shape(image)[0],
np.floor(bottom + 0.5).astype('int32'))
right = min(
np.shape(image)[1],
np.floor(right + 0.5).astype('int32'))
#图片输出
label = '{}'.format(predicted_class)
draw = ImageDraw.Draw(image)
label_size = draw.textsize(label, font)
label = label.encode('utf-8')
print(label)
if top - label_size[1] >= 0:
text_origin = np.array([left, top - label_size[1]])
else:
text_origin = np.array([left, top + 1])
for i in range(thickness):
draw.rectangle([left + i, top + i, right - i, bottom - i],
outline=self.colors[int(c)])
draw.rectangle(
[tuple(text_origin),
tuple(text_origin + label_size)],
fill=self.colors[int(c)])
draw.text(text_origin,
str(label, 'UTF-8'),
fill=(0, 0, 0),
font=font)
del draw
print("time:", time.time() - start_time)
return image
def detect_image(self, image):
image_shape = np.array(np.shape(image)[0:2])
old_width, old_height = image_shape[1], image_shape[0]
old_image = copy.deepcopy(image)
#---------------------------------------------------------#
# Reset the original image to the size of 600 short edges
#---------------------------------------------------------#
width, height = get_new_img_size(old_width, old_height)
image = image.resize([width, height], Image.BICUBIC)
photo = np.array(image, dtype=np.float64)
#-----------------------------------------------------------#
# Image preprocessing and normalization.
#-----------------------------------------------------------#
photo = preprocess_input(np.expand_dims(photo, 0))
rpn_pred = self.model_rpn.predict(photo)
#-----------------------------------------------------------#
# The prediction result of the suggestion box network is decoded
#-----------------------------------------------------------#
base_feature_width, base_feature_height = self.get_img_output_length(
width, height)
anchors = get_anchors([base_feature_width, base_feature_height], width,
height)
rpn_results = self.bbox_util.detection_out_rpn(rpn_pred, anchors)
#-------------------------------------------------------------#
# After obtaining the suggestion box and the shared feature layer, they are passed into the classifier for prediction
#-------------------------------------------------------------#
base_layer = rpn_pred[2]
proposal_box = np.array(rpn_results)[:, :, 1:]
temp_ROIs = np.zeros_like(proposal_box)
temp_ROIs[:, :, [0, 1, 2, 3]] = proposal_box[:, :, [1, 0, 3, 2]]
classifier_pred = self.model_classifier.predict(
[base_layer, temp_ROIs])
#-------------------------------------------------------------#
# The prediction frame is obtained by decoding the suggestion box by using the prediction results of classifier
#-------------------------------------------------------------#
results = self.bbox_util.detection_out_classifier(
classifier_pred, proposal_box, self.config, self.confidence)
if len(results[0]) == 0:
return old_image
results = np.array(results[0])
boxes = results[:, :4]
top_conf = results[:, 4]
top_label_indices = results[:, 5]
boxes[:, [0, 2]] = boxes[:, [0, 2]] * old_width
boxes[:, [1, 3]] = boxes[:, [1, 3]] * old_height
font = ImageFont.truetype(font='model_data/simhei.ttf',
size=np.floor(3e-2 * np.shape(image)[1] +
0.5).astype('int32'))
thickness = max(
(np.shape(old_image)[0] + np.shape(old_image)[1]) // old_width * 2,
1)
image = old_image
for i, c in enumerate(top_label_indices):
predicted_class = self.class_names[int(c)]
score = top_conf[i]
left, top, right, bottom = boxes[i]
top = top - 5
left = left - 5
bottom = bottom + 5
right = right + 5
top = max(0, np.floor(top + 0.5).astype('int32'))
left = max(0, np.floor(left + 0.5).astype('int32'))
bottom = min(
np.shape(image)[0],
np.floor(bottom + 0.5).astype('int32'))
right = min(
np.shape(image)[1],
np.floor(right + 0.5).astype('int32'))
# 画框框
label = '{} {:.2f}'.format(predicted_class, score)
draw = ImageDraw.Draw(image)
label_size = draw.textsize(label, font)
label = label.encode('utf-8')
print(label, top, left, bottom, right)
if top - label_size[1] >= 0:
text_origin = np.array([left, top - label_size[1]])
else:
text_origin = np.array([left, top + 1])
for i in range(thickness):
draw.rectangle([left + i, top + i, right - i, bottom - i],
outline=self.colors[int(c)])
draw.rectangle(
[tuple(text_origin),
tuple(text_origin + label_size)],
fill=self.colors[int(c)])
draw.text(text_origin,
str(label, 'UTF-8'),
fill=(0, 0, 0),
font=font)
del draw
return image
def get_FPS(self, image, test_interval):
#-------------------------------------#
# 转换成RGB图片，可以用于灰度图预测。
#-------------------------------------#
image = image.convert("RGB")
image_shape = np.array(np.shape(image)[0:2])
old_width, old_height = image_shape[1], image_shape[0]
#---------------------------------------------------------#
# 给原图像进行resize，resize到短边为600的大小上
#---------------------------------------------------------#
width, height = get_new_img_size(old_width, old_height)
image = image.resize([width,height], Image.BICUBIC)
photo = np.array(image,dtype = np.float64)
#-----------------------------------------------------------#
# 图片预处理，归一化。
#-----------------------------------------------------------#
photo = preprocess_input(np.expand_dims(photo,0))
rpn_pred = self.model_rpn.predict(photo)
#-----------------------------------------------------------#
# 将建议框网络的预测结果进行解码
#-----------------------------------------------------------#
base_feature_width, base_feature_height = self.get_img_output_length(width, height)
anchors = get_anchors([base_feature_width, base_feature_height], width, height)
rpn_results = self.bbox_util.detection_out_rpn(rpn_pred, anchors)
#-------------------------------------------------------------#
# 在获得建议框和共享特征层后，将二者传入classifier中进行预测
#-------------------------------------------------------------#
base_layer = rpn_pred[2]
proposal_box = np.array(rpn_results)[:, :, 1:]
temp_ROIs = np.zeros_like(proposal_box)
temp_ROIs[:, :, [0, 1, 2, 3]] = proposal_box[:, :, [1, 0, 3, 2]]
classifier_pred = self.model_classifier.predict([base_layer, temp_ROIs])
#-------------------------------------------------------------#
# 利用classifier的预测结果对建议框进行解码，获得预测框
#-------------------------------------------------------------#
results = self.bbox_util.detection_out_classifier(classifier_pred, proposal_box, self.config, self.confidence)
if len(results[0])>0:
results = np.array(results[0])
boxes = results[:, :4]
top_conf = results[:, 4]
top_label_indices = results[:, 5]
boxes[:, [0, 2]] = boxes[:, [0, 2]] * old_width
boxes[:, [1, 3]] = boxes[:, [1, 3]] * old_height
t1 = time.time()
for _ in range(test_interval):
rpn_pred = self.model_rpn.predict(photo)
#-----------------------------------------------------------#
# 将建议框网络的预测结果进行解码
#-----------------------------------------------------------#
base_feature_width, base_feature_height = self.get_img_output_length(width, height)
anchors = get_anchors([base_feature_width, base_feature_height], width, height)
rpn_results = self.bbox_util.detection_out_rpn(rpn_pred, anchors)
#-------------------------------------------------------------#
# 在获得建议框和共享特征层后，将二者传入classifier中进行预测
#-------------------------------------------------------------#
base_layer = rpn_pred[2]
proposal_box = np.array(rpn_results)[:, :, 1:]
temp_ROIs = np.zeros_like(proposal_box)
temp_ROIs[:, :, [0, 1, 2, 3]] = proposal_box[:, :, [1, 0, 3, 2]]
classifier_pred = self.model_classifier.predict([base_layer, temp_ROIs])
#-------------------------------------------------------------#
# 利用classifier的预测结果对建议框进行解码，获得预测框
#-------------------------------------------------------------#
results = self.bbox_util.detection_out_classifier(classifier_pred, proposal_box, self.config, self.confidence)
if len(results[0])>0:
results = np.array(results[0])
boxes = results[:, :4]
top_conf = results[:, 4]
top_label_indices = results[:, 5]
boxes[:, [0, 2]] = boxes[:, [0, 2]] * old_width
boxes[:, [1, 3]] = boxes[:, [1, 3]] * old_height
t2 = time.time()
tact_time = (t2 - t1) / test_interval
return tact_time
def detect_image(self, image_id, image):
self.confidence = 0.05
f = open("./input/detection-results/" + image_id + ".txt", "w")
image_shape = np.array(np.shape(image)[0:2])
old_width = image_shape[1]
old_height = image_shape[0]
old_image = copy.deepcopy(image)
width, height = get_new_img_size(old_width, old_height)
image = image.resize([width, height])
photo = np.array(image, dtype=np.float64)
# 图片预处理，归一化
photo = preprocess_input(np.expand_dims(photo, 0))
preds = self.model_rpn.predict(photo)
# 将预测结果进行解码
anchors = get_anchors(self.get_img_output_length(width, height), width,
height)
rpn_results = self.bbox_util.detection_out(preds,
anchors,
1,
confidence_threshold=0)
R = rpn_results[0][:, 2:]
R[:, 0] = np.array(np.round(R[:, 0] * width / self.config.rpn_stride),
dtype=np.int32)
R[:, 1] = np.array(np.round(R[:, 1] * height / self.config.rpn_stride),
dtype=np.int32)
R[:, 2] = np.array(np.round(R[:, 2] * width / self.config.rpn_stride),
dtype=np.int32)
R[:, 3] = np.array(np.round(R[:, 3] * height / self.config.rpn_stride),
dtype=np.int32)
R[:, 2] -= R[:, 0]
R[:, 3] -= R[:, 1]
base_layer = preds[2]
delete_line = []
for i, r in enumerate(R):
if r[2] < 1 or r[3] < 1:
delete_line.append(i)
R = np.delete(R, delete_line, axis=0)
bboxes = []
probs = []
labels = []
for jk in range(R.shape[0] // self.config.num_rois + 1):
ROIs = np.expand_dims(R[self.config.num_rois *
jk:self.config.num_rois * (jk + 1), :],
axis=0)
if ROIs.shape[1] == 0:
break
if jk == R.shape[0] // self.config.num_rois:
#pad R
curr_shape = ROIs.shape
target_shape = (curr_shape[0], self.config.num_rois,
curr_shape[2])
ROIs_padded = np.zeros(target_shape).astype(ROIs.dtype)
ROIs_padded[:, :curr_shape[1], :] = ROIs
ROIs_padded[0, curr_shape[1]:, :] = ROIs[0, 0, :]
ROIs = ROIs_padded
[P_cls, P_regr] = self.model_classifier.predict([base_layer, ROIs])
for ii in range(P_cls.shape[1]):
if np.max(P_cls[0, ii, :]) < self.confidence or np.argmax(
P_cls[0, ii, :]) == (P_cls.shape[2] - 1):
continue
label = np.argmax(P_cls[0, ii, :])
(x, y, w, h) = ROIs[0, ii, :]
cls_num = np.argmax(P_cls[0, ii, :])
(tx, ty, tw, th) = P_regr[0, ii, 4 * cls_num:4 * (cls_num + 1)]
tx /= self.config.classifier_regr_std[0]
ty /= self.config.classifier_regr_std[1]
tw /= self.config.classifier_regr_std[2]
th /= self.config.classifier_regr_std[3]
cx = x + w / 2.
cy = y + h / 2.
cx1 = tx * w + cx
cy1 = ty * h + cy
w1 = math.exp(tw) * w
h1 = math.exp(th) * h
x1 = cx1 - w1 / 2.
y1 = cy1 - h1 / 2.
x2 = cx1 + w1 / 2
y2 = cy1 + h1 / 2
x1 = int(round(x1))
y1 = int(round(y1))
x2 = int(round(x2))
y2 = int(round(y2))
bboxes.append([x1, y1, x2, y2])
probs.append(np.max(P_cls[0, ii, :]))
labels.append(label)
if len(bboxes) == 0:
return old_image
# 筛选出其中得分高于confidence的框
labels = np.array(labels)
probs = np.array(probs)
boxes = np.array(bboxes, dtype=np.float32)
boxes[:, 0] = boxes[:, 0] * self.config.rpn_stride / width
boxes[:, 1] = boxes[:, 1] * self.config.rpn_stride / height
boxes[:, 2] = boxes[:, 2] * self.config.rpn_stride / width
boxes[:, 3] = boxes[:, 3] * self.config.rpn_stride / height
results = np.array(
self.bbox_util.nms_for_out(np.array(labels), np.array(probs),
np.array(boxes), self.num_classes - 1,
0.4))
top_label_indices = results[:, 0]
top_conf = results[:, 1]
boxes = results[:, 2:]
boxes[:, 0] = boxes[:, 0] * old_width
boxes[:, 1] = boxes[:, 1] * old_height
boxes[:, 2] = boxes[:, 2] * old_width
boxes[:, 3] = boxes[:, 3] * old_height
for i, c in enumerate(top_label_indices):
predicted_class = self.class_names[int(c)]
score = str(top_conf[i])
left, top, right, bottom = boxes[i]
f.write("%s %s %s %s %s %s\n" %
(predicted_class, score[:6], str(int(left)), str(
int(top)), str(int(right)), str(int(bottom))))
f.close()
return
def detect_image(self, image):
#-------------------------------------#
# 转换成RGB图片，可以用于灰度图预测。
#-------------------------------------#
image = image.convert("RGB")
image_shape = np.array(np.shape(image)[0:2])
old_width, old_height = image_shape[1], image_shape[0]
old_image = copy.deepcopy(image)
#---------------------------------------------------------#
# 给原图像进行resize，resize到短边为600的大小上
#---------------------------------------------------------#
width, height = get_new_img_size(old_width, old_height)
image = image.resize([width, height], Image.BICUBIC)
photo = np.array(image, dtype=np.float64)
#-----------------------------------------------------------#
# 图片预处理，归一化。
#-----------------------------------------------------------#
photo = preprocess_input(np.expand_dims(photo, 0))
rpn_pred = self.model_rpn_get_pred(photo)
rpn_pred = [x.numpy() for x in rpn_pred]
#-----------------------------------------------------------#
# 将建议框网络的预测结果进行解码
#-----------------------------------------------------------#
base_feature_width, base_feature_height = self.get_img_output_length(
width, height)
anchors = get_anchors([base_feature_width, base_feature_height], width,
height)
rpn_results = self.bbox_util.detection_out_rpn(rpn_pred, anchors)
#-------------------------------------------------------------#
# 在获得建议框和共享特征层后，将二者传入classifier中进行预测
#-------------------------------------------------------------#
base_layer = rpn_pred[2]
proposal_box = np.array(rpn_results)[:, :, 1:]
temp_ROIs = np.zeros_like(proposal_box)
temp_ROIs[:, :, [0, 1, 2, 3]] = proposal_box[:, :, [1, 0, 3, 2]]
classifier_pred = self.model_classifier_get_pred(
[base_layer, temp_ROIs])
classifier_pred = [x.numpy() for x in classifier_pred]
#-------------------------------------------------------------#
# 利用classifier的预测结果对建议框进行解码，获得预测框
#-------------------------------------------------------------#
results = self.bbox_util.detection_out_classifier(
classifier_pred, proposal_box, self.config, self.confidence)
if len(results[0]) == 0:
return old_image
results = np.array(results[0])
boxes = results[:, :4]
top_conf = results[:, 4]
top_label_indices = results[:, 5]
boxes[:, [0, 2]] = boxes[:, [0, 2]] * old_width
boxes[:, [1, 3]] = boxes[:, [1, 3]] * old_height
font = ImageFont.truetype(font='model_data/simhei.ttf',
size=np.floor(3e-2 * np.shape(image)[1] +
0.5).astype('int32'))
thickness = max(
(np.shape(old_image)[0] + np.shape(old_image)[1]) // old_width * 2,
1)
image = old_image
for i, c in enumerate(top_label_indices):
predicted_class = self.class_names[int(c)]
score = top_conf[i]
left, top, right, bottom = boxes[i]
top = top - 5
left = left - 5
bottom = bottom + 5
right = right + 5
top = max(0, np.floor(top + 0.5).astype('int32'))
left = max(0, np.floor(left + 0.5).astype('int32'))
bottom = min(
np.shape(image)[0],
np.floor(bottom + 0.5).astype('int32'))
right = min(
np.shape(image)[1],
np.floor(right + 0.5).astype('int32'))
# 画框框
label = '{} {:.2f}'.format(predicted_class, score)
draw = ImageDraw.Draw(image)
label_size = draw.textsize(label, font)
label = label.encode('utf-8')
print(label, top, left, bottom, right)
if top - label_size[1] >= 0:
text_origin = np.array([left, top - label_size[1]])
else:
text_origin = np.array([left, top + 1])
for i in range(thickness):
draw.rectangle([left + i, top + i, right - i, bottom - i],
outline=self.colors[int(c)])
draw.rectangle(
[tuple(text_origin),
tuple(text_origin + label_size)],
fill=self.colors[int(c)])
draw.text(text_origin,
str(label, 'UTF-8'),
fill=(0, 0, 0),
font=font)
del draw
return image
def detect_image(self, image):
# 1 处理图片
image_shape = np.array(np.shape(image)[0:2])
old_width = image_shape[1]
old_height = image_shape[0]
old_image = copy.deepcopy(image)
# 1.1 图片resize，最短边600
width,height = get_new_img_size(old_width,old_height)
image = image.resize([width,height])
photo = np.array(image,dtype = np.float64)
# 2 图片预处理，归一化，导入rpn网络进行预测得到置信度和预测偏移值
photo = preprocess_input(np.expand_dims(photo,0))
preds = self.model_rpn.predict(photo)
# 3 生成先验框
anchors = get_anchors(self.get_img_output_length(width,height),width,height)
# 4 将预测结果进行解码--nms筛选得到建议框 **********************
rpn_results = self.bbox_util.detection_out(preds,anchors,1,confidence_threshold=0.8)
# temp是解码后的建议框
# temp = copy.deepcopy(rpn_results[0][:, 2:])
R = rpn_results[0][:, 2:] # r.num=300
# 5 下面处理后的框是放在featureMap上，数值大小在0，38之间 左上角右下角
R[:,0] = np.array(np.round(R[:, 0]*width/self.config.rpn_stride),dtype=np.int32)
R[:,1] = np.array(np.round(R[:, 1]*height/self.config.rpn_stride),dtype=np.int32)
R[:,2] = np.array(np.round(R[:, 2]*width/self.config.rpn_stride),dtype=np.int32)
R[:,3] = np.array(np.round(R[:, 3]*height/self.config.rpn_stride),dtype=np.int32)
R[:, 2] -= R[:, 0] # 得到建议框的左上角xy
R[:, 3] -= R[:, 1] # 得到建议框的宽高wh
base_layer = preds[2]
delete_line = []
for i,r in enumerate(R):
if r[2] < 1 or r[3] < 1:
delete_line.append(i)
R = np.delete(R,delete_line,axis=0)
bboxes = []
probs = []
labels = []
# 6 分批次把建议框传入classifier
for jk in range(R.shape[0]//self.config.num_rois + 1): # 300//32+1
ROIs = np.expand_dims(R[self.config.num_rois*jk:self.config.num_rois*(jk+1), :], axis=0)
# ROIs=32
if ROIs.shape[1] == 0:
break
# 对最后一次建议框填充到32个
if jk == R.shape[0]//self.config.num_rois:
# pad R
curr_shape = ROIs.shape
target_shape = (curr_shape[0],self.config.num_rois,curr_shape[2])
ROIs_padded = np.zeros(target_shape).astype(ROIs.dtype)
ROIs_padded[:, :curr_shape[1], :] = ROIs
ROIs_padded[0, curr_shape[1]:, :] = ROIs[0, 0, :]
ROIs = ROIs_padded
# P_cls种类，置信度, P_regr
[P_cls, P_regr] = self.model_classifier.predict([base_layer,ROIs]) # ROIs = 32
for ii in range(P_cls.shape[1]):
# 6.1 判断置信度是否大于阈值
if np.max(P_cls[0, ii, :]) < self.confidence or np.argmax(P_cls[0, ii, :]) == (P_cls.shape[2] - 1):
continue
# 建议框类别
label = np.argmax(P_cls[0, ii, :])
# 建议框坐标
(x, y, w, h) = ROIs[0, ii, :]
#
cls_num = np.argmax(P_cls[0, ii, :])
(tx, ty, tw, th) = P_regr[0, ii, 4*cls_num:4*(cls_num+1)]
# 建议框的调整参数
tx /= self.config.classifier_regr_std[0] # 8.0
ty /= self.config.classifier_regr_std[1]
tw /= self.config.classifier_regr_std[2] # 4.0
th /= self.config.classifier_regr_std[3]
# 6.2 解码 - 中心
cx = x + w/2.
cy = y + h/2.
# 调整后的中心
cx1 = tx * w + cx
cy1 = ty * h + cy
w1 = math.exp(tw) * w
h1 = math.exp(th) * h
# 左上角
x1 = cx1 - w1/2.
y1 = cy1 - h1/2.
x2 = cx1 + w1/2
y2 = cy1 + h1/2
# 右上角
x1 = int(round(x1))
y1 = int(round(y1))
x2 = int(round(x2))
y2 = int(round(y2))
bboxes.append([x1,y1,x2,y2])
probs.append(np.max(P_cls[0, ii, :]))
labels.append(label)
if len(bboxes)==0:
return old_image
# 6.3 筛选出其中得分高于confidence的框
labels = np.array(labels)
probs = np.array(probs)
boxes = np.array(bboxes,dtype=np.float32)
# 把box转化为小数
boxes[:,0] = boxes[:,0]*self.config.rpn_stride/width
boxes[:,1] = boxes[:,1]*self.config.rpn_stride/height
boxes[:,2] = boxes[:,2]*self.config.rpn_stride/width
boxes[:,3] = boxes[:,3]*self.config.rpn_stride/height
# 6.4 NMS
results = np.array(self.bbox_util.nms_for_out(np.array(labels),np.array(probs),np.array(boxes),self.num_classes-1,0.4))
top_label_indices = results[:,0]
top_conf = results[:,1]
boxes = results[:,2:]
# 7 映射到原图
boxes[:,0] = boxes[:,0]*old_width
boxes[:,1] = boxes[:,1]*old_height
boxes[:,2] = boxes[:,2]*old_width
boxes[:,3] = boxes[:,3]*old_height
font = ImageFont.truetype(font='model_data/simhei.ttf',size=np.floor(3e-2 * np.shape(image)[1] + 0.5).astype('int32'))
thickness = (np.shape(old_image)[0] + np.shape(old_image)[1]) // width
image = old_image
for i, c in enumerate(top_label_indices):
predicted_class = self.class_names[int(c)]
score = top_conf[i]
left, top, right, bottom = boxes[i]
top = top - 5
left = left - 5
bottom = bottom + 5
right = right + 5
top = max(0, np.floor(top + 0.5).astype('int32'))
left = max(0, np.floor(left + 0.5).astype('int32'))
bottom = min(np.shape(image)[0], np.floor(bottom + 0.5).astype('int32'))
right = min(np.shape(image)[1], np.floor(right + 0.5).astype('int32'))
# 画框
label = '{} {:.2f}'.format(predicted_class, score)
draw = ImageDraw.Draw(image)
label_size = draw.textsize(label, font)
label = label.encode('utf-8')
print(label)
if top - label_size[1] >= 0:
text_origin = np.array([left, top - label_size[1]])
else:
text_origin = np.array([left, top + 1])
for i in range(thickness):
draw.rectangle(
[left + i, top + i, right - i, bottom - i],
outline=self.colors[int(c)])
draw.rectangle(
[tuple(text_origin), tuple(text_origin + label_size)],
fill=self.colors[int(c)])
draw.text(text_origin, str(label,'UTF-8'), fill=(0, 0, 0), font=font)
del draw
return image
