i'm using yolo to detect object but i want to set timer for the detected object, can anyone help me?
so i want to make the object detecting with limited time for my projcet
i'm try my best but i don't have any idea how to do it
here is my code:
import cv2 as cv
import numpy as np
cap = cv.VideoCapture(0)
whT = 320
confThreshold = 0.1
nmsThreshold = 0.4
classesFile = "coco.names"
classNames = []
with open(classesFile, 'rt') as f:
classNames = [line.strip() for line in f.readlines()]
modelConfiguration = "yolov4.cfg"
modelWeights = "yolov4.weights"
net = cv.dnn.readNetFromDarknet(modelConfiguration, modelWeights)
net.setPreferableBackend(cv.dnn.DNN_BACKEND_OPENCV)
net.setPreferableTarget(cv.dnn.DNN_TARGET_CPU)
def findObjects(outputs,img):
hT, wT, cT = img.shape
bbox = []
classIds = []
confs = []
for output in outputs:
for det in output:
scores = det[5:]
classId = np.argmax(scores)
confidence = scores[classId]
if confidence > confThreshold:
w,h = int(det[2]*wT) , int(det[3]*hT)
x,y = int((det[0]*wT)-w/2) , int((det[1]*hT)-h/2)
bbox.append([x,y,w,h])
classIds.append(classId)
confs.append(float(confidence))
indices = cv.dnn.NMSBoxes(bbox, confs, confThreshold, nmsThreshold)
font = cv.FONT_HERSHEY_PLAIN
for i in indices:
label = str(classNames[classIds[i]])
x, y, w, h = bbox[i]
#print(x,y,w,h)
cv.rectangle(img, (x, y), (x+w,y+h), (255, 0 , 255), 2)
cv.putText(img, label, (x, y + 30), font, 3, (0,0,0), 3)
print("Jenis Mobil: " + label)
#cv.putText(img,f'{classNames[classIds[i]].upper()} {int(confs[i]*100)}%', (x, y-10), cv.FONT_HERSHEY_SIMPLEX, 0.6, (255, 0, 255), 2)
while True:
success, img = cap.read()
blob = cv.dnn.blobFromImage(img, 1 / 255, (whT, whT), [0, 0, 0], 1, crop=False)
net.setInput(blob)
layersNames = net.getLayerNames()
outputNames = [(layersNames[i - 1]) for i in net.getUnconnectedOutLayers()]
outputs = net.forward(outputNames)
findObjects(outputs,img)
cv.imshow('Image', img)
key = cv.waitKey(1)
if key == 27:
break
cap.release()
cv.destroyAllWindows()
Related
I want to pass continuous video stream to pyqt5 qlabel named label_cam to show up in ui using QThread but it keep failed showing the video stream on the qlabel. The video stream is later aimed to recognize people out.
I have been trying to connect the signal "change_Pixmap" from the VideoThread class to the "set_image" function in the "label_cam" object but i guess the flow of code or variable assign is wrong. Below is my code.
class FaceRecogScreen(QDialog):
def init(self):
super(FaceRecogScreen, self).init()
uic.loadUi("face_recog.ui", self)
self.update_date_time()
self.pushButton_back.clicked.connect(self.back_to_main3)
self.load_model()
def load_model(self):
self.prototxt = "deploy.prototxt.txt"
self.model = "res10_300x300_ssd_iter_140000.caffemodel"
print("[INFORMATION] Loading model....")
self.net = cv2.dnn.readNetFromCaffe(self.prototxt, self.model)
weight = "facenet_keras_weights.h5"
self.model2 = load_model('FaceNetModel.h5')
self.model2.load_weights(weight)
self.collected_encodings = pickle.loads(open('face_encoding.pickle', "rb").read())
infile = open('face_encoding', 'rb')
data = pickle.load(infile)
self.knownEncodings, self.knownNames = data['encodings'], data['names']
self.knownEncodings = np.array(self.knownEncodings)
self.knownNames = np.array(self.knownNames)
self.clf = svm.SVC(gamma="scale", probability=True, tol=0.01)
self.clf.fit(self.knownEncodings, self.knownNames)
# self.label_cam= VideoLabel()
self.thread = VideoThread(self)
self.thread.change_Pixmap.connect(self.set_image)
# call the run() function in VideoThread class
self.thread.start()
# self.thread.change_Pixmap.connect(self.label_cam.set_image)
# # call the run() function in VideoThread class
# self.thread.start()
# layout = self.layout()
# layout.addWidget(self.label_cam)
# self.thread.run.start()
def update_date_time(self):
# Get the current date and time
date_time = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
self.label_datetime.setText(date_time)
# Update the date and time in the table
def back_to_main3(self):
pushButton_back = WelcomeScreen()
widget.addWidget(pushButton_back)
widget.setCurrentIndex(widget.currentIndex()+1)
def set_image(self, frame):
self.setPixmap(QPixmap.fromImage(frame))
class VideoThread(QtCore.QThread):
change_Pixmap = QtCore.pyqtSignal(QtGui.QImage)
def run(self):
cap = cv2.VideoCapture(1)
while True:
ret, frame = cap.read()
if ret:
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
h, w, ch = frame.shape
bytesPerLine = ch * w
convertToQtFormat = QtGui.QImage(frame.data, w, h, bytesPerLine, QtGui.QImage.Format_RGB888)
p = convertToQtFormat.scaled(640, 480, QtCore.Qt.KeepAspectRatio)
self.change_Pixmap.emit(p)
(h, w) = frame.shape[:2]
blob = cv2.dnn.blobFromImage(cv2.resize(
frame, (160, 160)), 1.0, (300, 300), (104, 177, 123))
self.net.setInput(blob)
detections = self.net.forward()
self.frame = frame
# self.frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
cv2.normalize(frame, None, 0, 1.0, cv2.NORM_MINMAX, dtype=cv2.CV_32F)
pixels = np.expand_dims(frame, axis=0)
encode = self.model2.predict(pixels)
face_name = []
for encoding in encode:
name = self.clf.predict([encoding])
face_name.extend(name)
for i in range(0, detections.shape[2]):
confidence = detections[0, 0, i, 2]
if confidence < 0.5:
continue
box = detections[0, 0, i, 3:7]*np.array([w, h, w, h])
(startX, startY, endX, endY) = box.astype("int")
text = "{:.2f}%".format(confidence*100)
y = startY - 10 if startY - 10 > 10 else startY*10
if name == 'unknown':
cv2.rectangle(frame, (startX, y), (endX, endY), (0, 0, 255), 2)
cv2.putText(frame, name, (startX, startY),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2)
else:
cv2.rectangle(frame, (startX, y), (endX, endY), (0, 255, 0), 2)
cv2.putText(frame, name[0], (startX, startY),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 0), 2)
I have trained a model using yolov7 https://colab.research.google.com/drive/1X9A8odmK4k6l26NDviiT6dd6TgR-piOa#scrollTo=nD-uPyQ_2jiN colab file. After training I got a file named best.pt and I want to use it as a service/application in python. There is a yolov3 example which I created. This one was using .weights so how can I use .pt?
import cv2
import numpy as np
import time
import os
def getPhoto():
ROOT_DIR = os.path.dirname(__file__)
URL = "http://192.168.1.3:4747/video"
PC_CAM = 0
net = cv2.dnn.readNet(
f"{ROOT_DIR}\\yolov3_custom_final.weights",
f"{ROOT_DIR}\\yolov3_custom.cfg",
)
classes = []
with open(f"{ROOT_DIR}\\classes.txt", "r") as f:
classes = f.read().splitlines()
timeElapsed = 0
wCam, hCam = 640, 360
font = cv2.FONT_HERSHEY_PLAIN
colors = np.random.uniform(0, 255, size=(2, 3))
cap = cv2.VideoCapture(URL)
cap.set(3, wCam)
cap.set(4, hCam)
while True:
_, img = cap.read()
cv2.imshow("Detection Screen", img)
if cv2.waitKey(1) == ord("c"):
break
height, width, _ = img.shape
blob = cv2.dnn.blobFromImage(
img, 1 / 255, (416, 416), (0, 0, 0), swapRB=True, crop=False
)
net.setInput(blob)
output_layers_names = net.getUnconnectedOutLayersNames()
layerOutputs = net.forward(output_layers_names)
boxes = []
confidences = []
class_ids = []
for output in layerOutputs:
for detection in output:
scores = detection[5:]
class_id = np.argmax(scores)
confidence = scores[class_id]
if confidence > 0.6:
center_x = int(detection[0] * width)
center_y = int(detection[1] * height)
w = int(detection[2] * width)
h = int(detection[3] * height)
x = int(center_x - w / 2)
y = int(center_y - h / 2)
boxes.append([x, y, w, h])
confidences.append((float(confidence)))
class_ids.append(class_id)
indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.2, 0.4)
if len(indexes) > 0:
for i in indexes.flatten():
x, y, w, h = boxes[i]
label = str(classes[class_ids[i]])
confidence = str(round(confidences[i], 2))
color = colors[i]
cv2.rectangle(img, (x, y), (x + w, y + h), color, 2)
cv2.putText(
img,
label + " " + confidence,
(x, y + 20),
font,
2,
(255, 255, 0),
2,
)
cv2.imwrite(f"{ROOT_DIR}\\DetectedPhoto.jpg", img)
print("Image Saved")
getPhoto()
I want to detect vehicle plates using .pt file and cut vehicle plates and save them as .jpeg.
you can do this with detect.py insided yolov7 folder. Run this:
python detect.py --weights best.pt --source image.jpg
you can download yolov7 with this method:
git clone https://github.com/WongKinYiu/yolov7.git
in yolov7 you can see detect.py
I was trying to run my yolov5 custom model on cpu and I got this error.
this is the github page I have used : https://github.com/Amelia0911/onnxruntime-for-yolov5
import onnxruntime
from models.utils import *
import time
IMAGE_SIZE = (416, 416)
CONF_TH = 0.3
NMS_TH = 0.45
CLASSES = 80
model = onnxruntime.InferenceSession("models_train/bestnone.onnx")
anchor_list = [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]]
stride = [8, 16, 32]
def draw(img, boxinfo, dst, id):
for *xyxy, conf, cls in boxinfo:
label = '{}|{}'.format(int(cls), '%.2f' % conf)
plot_one_box(xyxy, img, label=label, color=[0, 0, 255])
cv2.imencode('.jpg', img)[1].tofile(dst)
def detect(image):
img = cv2.resize(image,IMAGE_SIZE)
img = img.transpose(2, 0, 1)
dataset = (img, image)
img = dataset[0].astype('float32')
img_size = [dataset[0].shape[1], dataset[0].shape[2]]
img /= 255.0
img = img.reshape(1, 3, img_size[0], img_size[1])
inputs = {model.get_inputs()[0].name: img}
pred = torch.tensor(model.run(None, inputs)[0])
anchor = torch.tensor(anchor_list).float().view(3, -1, 2)
area = img_size[0]*img_size[1]
size = [int(area/stride[0]**2), int(area/stride[1]**2), int(area/stride[2]**2)]
feature = [[int(j/stride[i]) for j in img_size] for i in range(3)]
y = []
y.append(pred[:, :size[0]*3, :])
y.append(pred[:, size[0]*3:size[0]*3+size[1]*3, :])
y.append(pred[:, size[0]*3+size[1]*3:, :])
grid = []
for k, f in enumerate(feature):
grid.append([[i, j] for j in range(f[0]) for i in range(f[1])])
z = []
for i in range(3):
src = y[i]
xy = src[..., 0:2] * 2. - 0.5
wh = (src[..., 2:4] * 2) ** 2
dst_xy = []
dst_wh = []
for j in range(3):
dst_xy.append((xy[:, j*size[i]:(j+1)*size[i], :] + torch.tensor(grid[i])) * stride[i])
dst_wh.append(wh[:, j*size[i]:(j+1)*size[i], :] * anchor[i][j])
src[..., 0:2] = torch.from_numpy(np.concatenate((dst_xy[0], dst_xy[1], dst_xy[2]), axis=1))
src[..., 2:4] = torch.from_numpy(np.concatenate((dst_wh[0], dst_wh[1], dst_wh[2]), axis=1))
z.append(src.view(1, -1, CLASSES+5)) #85
pred = torch.cat(z, 1)
pred = nms(pred, CONF_TH, NMS_TH)
for det in pred:
if det is not None and len(det):
det[:, :4] = scale_coords(img.shape[2:], det[:, :4], dataset[1].shape).round()
if det == None:
return np.array([])
return det
if __name__ == '__main__':
import time
src = 'Temp-640x640.jpg'
t1 = time.time()
img = cv2.imdecode(np.fromfile(src, dtype=np.uint8), -1)
print(IMAGE_SIZE)
results = detect(img)
t2 = time.time()
print(results)
print("onnxruntime time = ", t2 - t1)
if results is not None and len(results):
draw(img, results, 'dst3.jpg', str(id))
print('Down!')
when I run this code I got the following error:
File "C:\Users\acer\.spyder-py3\metallic surface defect detection\3_onnx_cpu_detec.py", line 85, in <module>
results = detect(img)
File "C:\Users\acer\.spyder-py3\metallic surface defect detection\3_onnx_cpu_detec.py", line 30, in detect
img = img.reshape(1, 3, img_size[0], img_size[1])
ValueError: cannot reshape array of size 692224 into shape (1,3,416,416)
I think it is a color channel issue. I have tried to fix it .But it doesn't work .If someone know how to fix it please inform me.Thanks in advance
the tensor is:
batch(3) * length(5) * dim(2)
tensor = tf.constant([[[1,1],[2,2],[3,3],[4,4],[5,5]],[[1,1],[2,2],[3,3],[4,4],[5,5]],[[1,1],[2,2],[3,3],[4,4],[5,5]]] )
and i want get more slices by length_index [0,0],[0,1] ... [3,4],[4,4] according to length_axis_index[0,1,2,3,4],the operation like
spans_length=0
with tf.variable_scope("loss_span"):
output=[]
for i in range(0,1+n_spans):
for j in range(1,seq_length):
if j + i < seq_length:
res = tf.slice(output_layer_sequence, [0, j, 0], [-1, j+i-j+1, -1])
res = tf.reduce_sum(res,axis=1)
output.append(res)
# output = tf.convert_to_tensor(output)
spans_length+=1
output = tf.convert_to_tensor(output)
vsp = tf.transpose(output, [1,0,2])#batch , spans_length,hidden_size
vsp = tf.reshape(vsp,[-1,hidden_size])#batch * span_length,hidden_size
span_logits = tf.matmul(vsp, output_span_weight, transpose_b=True) # output:[batch * spans_length,class_labels]
span_logits = tf.nn.bias_add(span_logits, output_span_bias) # output:[batch * spans_length,class_labels]
span_matrix = tf.reshape(span_logits,[-1,spans_length,class_labels],name="span_matrix_val")#[batch , spans_length,class_labels]
label_span_logists = tf.one_hot(indices=label_span,depth=class_labels, on_value=1, off_value=0, axis=-1, dtype=tf.int32)
label_span_logists=tf.cast(label_span_logists,tf.int64)
span_loss = tf.nn.softmax_cross_entropy_with_logits(logits=span_matrix, labels=label_span_logists)
span_loss = tf.reduce_mean(span_loss, name='loss_span')
when i doing such operation, training model 's time is very long;how to speed it.thanks
This code works:
# tensor = tf.constant([[[1,1],[2,2],[3,3],[4,4],[5,5]],[[1,1],[2,2],[3,3],[4,4],[5,5]],[[1,1],[2,2],[3,3],[4,4],[5,5]]] )
tensor = tf.random.uniform((3, 2000, 2))
length = tf.shape(tensor)[1].numpy()
output = []
for begins in range(length):
for size in range(length - begins):
res = tf.slice(tensor, [0, begins, 0], [-1, size + 1, -1])
res = tf.reduce_sum(res)
output.append(res)
output = tf.convert_to_tensor(output)
I tried to use tf.scan(), but I don't see any benefits:
output = tf.constant([], tf.int32)
for begins in range(length):
t = tensor[:, begins:, :]
t = tf.transpose(t, (1, 0, 2))
t = tf.scan(lambda a, x: a + x, t)
t = tf.transpose(t, (1, 0, 2))
t = tf.reduce_sum(t, [0, 2])
output = tf.concat([output, t], 0)
Edits:
Tried to apply reduce_sum() along the unused dimension [0, 2] in preprocessing:
tensor = tf.reduce_sum(tensor, [0, 2])
output = tf.constant([])
for begins in range(length):
t = tensor[begins:]
t = tf.scan(lambda a, x: a + x, t)
output = tf.concat([output, t], 0)
Still don't see performance benefits.
for i in range(0,50):
for j in range(1,200):
if j + i < 200:
res = tf.slice(output_layer_sequence, [0, j, 0], [-1, j+i-j+1, -1])
res = tf.reduce_sum(res,axis=1)
output.append(res)
output = tf.convert_to_tensor(output)
when i doing such operation, training time is very long;how to speed it.thanks
I've got a rough and ready function that can be used to compare two sets of values using histograms:
I want to set the individual edge colors of each of the histograms in the top plot (much as how I set the individual sets of values used for each histogram). How could this be done?
import os
import datavision
import matplotlib.pyplot
import numpy
import shijian
def main():
a = numpy.random.normal(2, 2, size = 120)
b = numpy.random.normal(2, 2, size = 120)
save_histogram_comparison_matplotlib(
values_1 = a,
values_2 = b,
label_1 = "a",
label_2 = "b",
normalize = True,
label_ratio_x = "measurement",
label_y = "",
title = "comparison of a and b",
filename = "histogram_comparison_1.png"
)
def save_histogram_comparison_matplotlib(
values_1 = None,
values_2 = None,
filename = None,
directory = ".",
number_of_bins = None,
normalize = True,
label_x = "",
label_y = None,
label_ratio_x = None,
label_ratio_y = "ratio",
title = "comparison",
label_1 = "1",
label_2 = "2",
overwrite = True,
LaTeX = False,
#aspect = None,
font_size = 20,
color_1 = "#3861AA",
color_2 = "#00FF00",
color_3 = "#7FDADC",
color_edge_1 = "#3861AA", # |<---------- insert magic for these
color_edge_2 = "#00FF00", # |
alpha = 0.5,
width_line = 1
):
matplotlib.pyplot.ioff()
if LaTeX is True:
matplotlib.pyplot.rc("text", usetex = True)
matplotlib.pyplot.rc("font", family = "serif")
if number_of_bins is None:
number_of_bins_1 = datavision.propose_number_of_bins(values_1)
number_of_bins_2 = datavision.propose_number_of_bins(values_2)
number_of_bins = int((number_of_bins_1 + number_of_bins_2) / 2)
if filename is None:
if title is None:
filename = "histogram_comparison.png"
else:
filename = shijian.propose_filename(
filename = title + ".png",
overwrite = overwrite
)
else:
filename = shijian.propose_filename(
filename = filename,
overwrite = overwrite
)
values = []
values.append(values_1)
values.append(values_2)
bar_width = 0.8
figure, (axis_1, axis_2) = matplotlib.pyplot.subplots(
nrows = 2,
gridspec_kw = {"height_ratios": (2, 1)}
)
ns, bins, patches = axis_1.hist(
values,
color = [
color_1,
color_2
],
normed = normalize,
histtype = "stepfilled",
bins = number_of_bins,
alpha = alpha,
label = [label_1, label_2],
rwidth = bar_width,
linewidth = width_line,
#edgecolor = [color_edge_1, color_edge_2] <---------- magic here? dunno
)
axis_1.legend(
loc = "best"
)
bars = axis_2.bar(
bins[:-1],
ns[0] / ns[1],
alpha = 1,
linewidth = 0, #width_line
width = bins[1] - bins[0]
)
for bar in bars:
bar.set_color(color_3)
axis_1.set_xlabel(label_x, fontsize = font_size)
axis_1.set_ylabel(label_y, fontsize = font_size)
axis_2.set_xlabel(label_ratio_x, fontsize = font_size)
axis_2.set_ylabel(label_ratio_y, fontsize = font_size)
#axis_1.xticks(fontsize = font_size)
#axis_1.yticks(fontsize = font_size)
#axis_2.xticks(fontsize = font_size)
#axis_2.yticks(fontsize = font_size)
matplotlib.pyplot.suptitle(title, fontsize = font_size)
if not os.path.exists(directory):
os.makedirs(directory)
#if aspect is None:
# matplotlib.pyplot.axes().set_aspect(
# 1 / matplotlib.pyplot.axes().get_data_ratio()
# )
#else:
# matplotlib.pyplot.axes().set_aspect(aspect)
figure.tight_layout()
matplotlib.pyplot.subplots_adjust(top = 0.9)
matplotlib.pyplot.savefig(
directory + "/" + filename,
dpi = 700
)
matplotlib.pyplot.close()
if __name__ == "__main__":
main()
You may simply plot two different histograms but share the bins.
import numpy as np; np.random.seed(3)
import matplotlib.pyplot as plt
a = np.random.normal(size=(89,2))
kws = dict(histtype= "stepfilled",alpha= 0.5, linewidth = 2)
hist, edges,_ = plt.hist(a[:,0], bins = 6,color="lightseagreen", label = "A", edgecolor="k", **kws)
plt.hist(a[:,1], bins = edges,color="gold", label = "B", edgecolor="crimson", **kws)
plt.show()
Use the lists of Patches objects returned by the hist() function.
In your case, you have two datasets, so your variable patches will be a list containing two lists, each with the Patches objects used to draw the bars on your plot.
You can easily set the properties on all of these objects using the setp() function. For example:
a = np.random.normal(size=(100,))
b = np.random.normal(size=(100,))
c,d,e = plt.hist([a,b], color=['r','g'])
plt.setp(e[0], edgecolor='k', lw=2)
plt.setp(e[1], edgecolor='b', lw=3)