我使用德国交通标志检测数据集来训练YOLOv3。当我预测时，我就会得到结果。但是，使用此代码我似乎无法在检测结果周围绘制边界框。现在，这不是我的意图。我想把结果删掉。但我不确定如何将 YOLOv3 预测结果转换为图像上的坐标，以便将其剪掉。你能帮我解决这个问题吗？
class BoundBox:
def __init__(self, xmin, ymin, xmax, ymax, objness = None, classes = None):
self.xmin = xmin
self.ymin = ymin
self.xmax = xmax
self.ymax = ymax
self.objness = objness
self.classes = classes
self.label = -1
self.score = -1
def get_label(self):
if self.label == -1:
self.label = np.argmax(self.classes)
return self.label
def get_score(self):
if self.score == -1:
self.score = self.classes[self.get_label()]
return self.score
def _sigmoid(x):
return 1. / (1. + np.exp(-x))
def decode_netout(netout, anchors, obj_thresh, net_h, net_w):
grid_h, grid_w = netout.shape[:2]
nb_box = 3
netout = netout.reshape((grid_h, grid_w, nb_box, -1))
nb_class = netout.shape[-1] - 5
boxes = []
netout[..., :2] = _sigmoid(netout[..., :2])
netout[..., 4:] = _sigmoid(netout[..., 4:])
netout[..., 5:] = netout[..., 4][..., np.newaxis] * netout[..., 5:]
netout[..., 5:] *= netout[..., 5:] > obj_thresh
for i in range(grid_h*grid_w):
row = i / grid_w
col = i % grid_w
for b in range(nb_box):
# 4th element is objectness score
objectness = netout[int(row)][int(col)][b][4]
if(objectness.all() <= obj_thresh): continue
# first 4 elements are x, y, w, and h
x, y, w, h = netout[int(row)][int(col)][b][:4]
x = (col + x) / grid_w # center position, unit: image width
y = (row + y) / grid_h # center position, unit: image height
w = anchors[2 * b + 0] * np.exp(w) / net_w # unit: image width
h = anchors[2 * b + 1] * np.exp(h) / net_h # unit: image height
# last elements are class probabilities
classes = netout[int(row)][col][b][5:]
box = BoundBox(x-w/2, y-h/2, x+w/2, y+h/2, objectness, classes)
boxes.append(box)
return boxes
def correct_yolo_boxes(boxes, image_h, image_w, net_h, net_w):
new_w, new_h = net_w, net_h
for i in range(len(boxes)):
x_offset, x_scale = (net_w - new_w)/2./net_w, float(new_w)/net_w
y_offset, y_scale = (net_h - new_h)/2./net_h, float(new_h)/net_h
boxes[i].xmin = int((boxes[i].xmin - x_offset) / x_scale * image_w)
boxes[i].xmax = int((boxes[i].xmax - x_offset) / x_scale * image_w)
boxes[i].ymin = int((boxes[i].ymin - y_offset) / y_scale * image_h)
boxes[i].ymax = int((boxes[i].ymax - y_offset) / y_scale * image_h)
def _interval_overlap(interval_a, interval_b):
x1, x2 = interval_a
x3, x4 = interval_b
if x3 < x1:
if x4 < x1:
return 0
else:
return min(x2,x4) - x1
else:
if x2 < x3:
return 0
else:
return min(x2,x4) - x3
def bbox_iou(box1, box2):
intersect_w = _interval_overlap([box1.xmin, box1.xmax], [box2.xmin, box2.xmax])
intersect_h = _interval_overlap([box1.ymin, box1.ymax], [box2.ymin, box2.ymax])
intersect = intersect_w * intersect_h
w1, h1 = box1.xmax-box1.xmin, box1.ymax-box1.ymin
w2, h2 = box2.xmax-box2.xmin, box2.ymax-box2.ymin
union = w1*h1 + w2*h2 - intersect
return float(intersect) / union
def do_nms(boxes, nms_thresh):
if len(boxes) > 0:
nb_class = len(boxes[0].classes)
else:
return
for c in range(nb_class):
sorted_indices = np.argsort([-box.classes[c] for box in boxes])
for i in range(len(sorted_indices)):
index_i = sorted_indices[i]
if boxes[index_i].classes[c] == 0: continue
for j in range(i+1, len(sorted_indices)):
index_j = sorted_indices[j]
if bbox_iou(boxes[index_i], boxes[index_j]) >= nms_thresh:
boxes[index_j].classes[c] = 0
# load and prepare an image
def load_image_pixels(filename, shape):
# load the image to get its shape
image = load_img(filename)
width, height = image.size
# load the image with the required size
image = load_img(filename, target_size=shape)
# convert to numpy array
image = img_to_array(image)
# scale pixel values to [0, 1]
image = image.astype('float32')
image /= 255.0
# add a dimension so that we have one sample
image = expand_dims(image, 0)
return image, width, height
# get all of the results above a threshold
def get_boxes(boxes, labels, thresh):
v_boxes, v_labels, v_scores = list(), list(), list()
# enumerate all boxes
for box in boxes:
# enumerate all possible labels
for i in range(len(labels)):
# check if the threshold for this label is high enough
if box.classes[i] > thresh:
v_boxes.append(box)
v_labels.append(labels[i])
v_scores.append(box.classes[i]*100)
# don't break, many labels may trigger for one box
return v_boxes, v_labels, v_scores
# draw all results
def draw_boxes(filename, v_boxes, v_labels, v_scores):
# load the image
data = plt.imread(filename)
# plot the image
plt.imshow(data)
# get the context for drawing boxes
ax = plt.gca()
# plot each box
for i in range(len(v_boxes)):
box = v_boxes[i]
# get coordinates
y1, x1, y2, x2 = box.ymin, box.xmin, box.ymax, box.xmax
# calculate width and height of the box
width, height = x2 - x1, y2 - y1
# create the shape
rect = Rectangle((x1, y1), width, height, fill=False, color='white')
# draw the box
ax.add_patch(rect)
# draw text and score in top left corner
label = "%s (%.3f)" % (v_labels[i], v_scores[i])
plt.text(x1, y1, label, color='white')
# show the plot
plt.show()
# load yolov3 model
model = load_model('/content/drive/MyDrive/model.h5', custom_objects={'yolo_loss': yolo_loss})
# define the expected input shape for the model
input_w, input_h = 416, 416
# define our new photo
photo_filename = '/content/images/00008.jpg'
# load and prepare image
image, image_w, image_h = load_image_pixels(photo_filename, (input_w, input_h))
# make prediction
yhat = model.predict(image)
# summarize the shape of the list of arrays
print([a.shape for a in yhat])
# define the anchors
anchors = [[116,90, 156,198, 373,326], [30,61, 62,45, 59,119], [10,13, 16,30, 33,23]]
# define the probability threshold for detected objects
class_threshold = 0.6
boxes = list()
for i in range(len(yhat)):
# decode the output of the network
boxes += decode_netout(yhat[i][0], anchors[i], class_threshold, input_h, input_w)
# correct the sizes of the bounding boxes for the shape of the image
correct_yolo_boxes(boxes, image_h, image_w, input_h, input_w)
# suppress non-maximal boxes
do_nms(boxes, 0.5)
# define the labels
labels = ["1", "2", "3", "4"]
# get the details of the detected objects
v_boxes, v_labels, v_scores = get_boxes(boxes, labels, class_threshold)
# summarize what we found
for i in range(len(v_boxes)):
print(v_labels[i], v_scores[i])
# draw what we found
draw_boxes(photo_filename, v_boxes, v_labels, v_scores)
代码已经提供边界框坐标。需要做的就是使用这些坐标来裁剪图像中检测到的对象。以下是执行此操作的更新后的
draw_boxes
函数：
import matplotlib.pyplot as plt
from matplotlib.patches import Rectangle
from PIL import Image
def draw_boxes(filename, v_boxes, v_labels, v_scores):
# load the image
data = plt.imread(filename)
# plot the image
plt.imshow(data)
# get the context for drawing boxes
ax = plt.gca()
# 创建一个列表来存储裁剪后的对象
cropped_objects = []
# 循环遍历每个框
for i in range(len(v_boxes)):
box = v_boxes[i]
# get coordinates
y1, x1, y2, x2 = box.ymin, box.xmin, box.ymax, box.xmax
# calculate width and height of the box
width, height = x2 - x1, y2 - y1
# create the shape
rect = Rectangle((x1, y1), width, height, fill=False, color='white')
# draw the box
ax.add_patch(rect)
# draw text and score in top left corner
label = "%s (%.3f)" % (v_labels[i], v_scores[i])
plt.text(x1, y1, label, color='white')
# 使用 PIL 裁剪检测到的对象
cropped_object = Image.open(filename).crop((x1, y1, x2, y2))
cropped_objects.append(cropped_object)
# show the plot
plt.show()
# 返回裁剪后的对象
return cropped_objects
# ... （的代码的其余部分）
# 获取检测到的对象
cropped_objects = draw_boxes(photo_filename, v_boxes, v_labels, v_scores)
# 现在可以保存或使用 cropped_objects 列表，它包含图像中每个检测到的对象的 PIL.Image 对象。
# 例如，要保存第一个检测到的对象：
cropped_objects[0].save("cropped_object.jpg")
这段代码进行以下更改：
-
导入 PIL 的 Image：
添加
from PIL import Image以便使用 PIL 处理图像裁剪。 -
在
draw_boxes函数中裁剪对象：-
创建一个名为
cropped_objects的列表来存储裁剪的对象。 -
在循环的每个边界框中，使用
Image.open(filename).crop((x1, y1, x2, y2))从原始图像中裁剪对象，并将其附加到cropped_objects列表中。
-
创建一个名为
-
返回
cropped_objects：draw_boxes函数现在返回cropped_objects列表。 -
使用裁剪的对象：
现在，
cropped_objects列表包含从图像中检测到的每个对象的 PIL.Image 对象。现在可以循环遍历列表并保存每个对象或对每个对象执行其他操作。
这段代码现在将在检测到的边界框周围绘制边界框，并还将每个检测到的对象裁剪到 PIL.Image 对象列表中，可以将其保存或用于进一步处理。
标签：python,opencv,computer-vision,yolo From： 67059442