Styjun

If a non-friend comes across my Steam Wishlist, how easily can he gift me one of the games?

Why do players in the past play much longer tournaments than today's top players?

Is "I do not want you to go nowhere" a case of "DOUBLE-NEGATIVES" as claimed by Grammarly?

Referring to different instances of the same character in time travel

What's the minimum number of sensors for a hobby GPS waypoint-following UAV?

Reverse dots and boxes, swastika edition

How can I effectively communicate to recruiters that a phone call is not possible?

Why isn't there research to build a standard lunar, or Martian mobility platform?

How can a dictatorship government be beneficial to a dictator in a post-scarcity society?

Are randomly-generated passwords starting with "a" less secure?

Changing trains in the Netherlands

The monorail explodes before I can get on it

Why does the U.S. tolerate foreign influence from Saudi Arabia and Israel on its domestic policies while not tolerating that from China or Russia?

How to loop for 3 times in bash script when docker push fails?

Credit score and financing new car

Has anyone in space seen or photographed a simple laser pointer from Earth?

RPI3B+: What are the four components below the HDMI connector called?

Matchmaker, Matchmaker, make me a match

Professor falsely accusing me of cheating in a class he does not teach, 2 months after end of the class. What precautions should I take?

How to convert a file with several spaces into a tab-delimited file?

What's the point of having a RAID 1 configuration over incremental backups to a secondary drive?

Would dual wielding daggers be a viable choice for a covert bodyguard?

Generating random numbers that keep a minimum distance

Managing and organizing the massively increased number of classes after switching to SOLID?

Filtering returned values variable with majority votes

Are static class variables possible in Python?How do I sort a list of dictionaries by a value of the dictionary?How do I return multiple values from a function?Using global variables in a functionHow do I sort a dictionary by value?How do I pass a variable by reference?Checking whether a variable is an integer or notHow to access environment variable values?Classifiers confidence in opencv face detectorSelect rows from a DataFrame based on values in a column in pandas

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty margin-bottom:0;

0

Good day, I am new to python and currently I am trying to work with my object detection assignment. What I am currently working with is to do filtering and do counting for objects that have been detected. For e.g , I have 3 return variables such as boxes (bounding boxes that appeared, to do counting), classId and confidence (to determine the object classes and its probability) with

print (len(boxes),classId,confidence)

and i got values like this (1 sec for 50+ values)

(1, 'Sunbear', 0.91407496)

(1, 'Sunbear', 0.93277943)

(1, 'Sunbear', 0.8578589)

(2, 'Sunbear', 0.29979056)

(1, 'Sunbear', 0.8787856)

(2, 'Sunbear', 0.32679325)

(1, 'Sunbear', 0.79356045)

Here is what i wanted to do:

To take the majority values that appeared for every 10 ( or more) returned values for boxes, classId and confidence (average value for this), to eliminate random fluctuation. Here are part of my codes,

 classIds = []
 confidences = []
 boxes = []
 for out in outs:
 for detection in out:
 scores = detection[5:]
 classId = np.argmax(scores)
 confidence = scores[classId]
 if confidence > confThreshold:
 center_x = int(detection[0] * frameWidth)
 center_y = int(detection[1] * frameHeight)
 width = int(detection[2] * frameWidth)
 height = int(detection[3] * frameHeight)
 left = int(center_x - width / 2)
 top = int(center_y - height / 2)
 classIds.append(classId)
 confidences.append(float(confidence))
 boxes.append([left, top, width, height])
 if classId ==0:
 classId = 'Asian_elephant'
 elif classId ==1:
 classId = 'Sunbear'
 elif classId ==2:
 classId = 'Tapir'
 #print ()
 #logging.debug('%s %s %s', len(boxes), confidence,classId)
 #logging.debug(boxes)
 print ((len(boxes),classId,confidence))

Here is what I am trying to do:

If classId of 'Sunbear' appeared 5 times or more continuously , it will print the returned values and the count will reset back to 0 or else it will keep resetting to zero till the condition is met.

 count=0
 while classId=='Sunbear': 
 count+=1
 if count>=5:
 print ((len(boxes),classId,confidence))
 break

but somehow the returned values are the same in or outside the loop. Is this the right way of doing this, or there is some more efficient ways to do it. Please bear with me, I am new to programming, thanks in advance.

python object-detection

share|improve this question

edited Mar 26 at 6:39

gameon67

1,47199 silver badges2828 bronze badges

asked Mar 26 at 2:35

shijishiji

1

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  what's the result that you got?
  
  – gameon67
  Mar 26 at 4:19
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  @gameon67 something like this (1, 'Sunbear', 0.91407496) (1, 'Sunbear', 0.91407496) (1, 'Sunbear', 0.93277943) (1, 'Sunbear', 0.93277943) (1, 'Sunbear', 0.8578589) (1, 'Sunbear', 0.8578589) (2, 'Sunbear', 0.29979056) (2, 'Sunbear', 0.29979056) (1, 'Sunbear', 0.8787856) (1, 'Sunbear', 0.8787856) (2, 'Sunbear', 0.32679325) (2, 'Sunbear', 0.32679325) (1, 'Sunbear', 0.79356045) (1, 'Sunbear', 0.79356045) as you can see both inside and outside (loop) values are the same
  
  – shiji
  Mar 26 at 7:26
  
  

  
  
  
  

add a comment | 

0

Good day, I am new to python and currently I am trying to work with my object detection assignment. What I am currently working with is to do filtering and do counting for objects that have been detected. For e.g , I have 3 return variables such as boxes (bounding boxes that appeared, to do counting), classId and confidence (to determine the object classes and its probability) with

print (len(boxes),classId,confidence)

and i got values like this (1 sec for 50+ values)

(1, 'Sunbear', 0.91407496)

(1, 'Sunbear', 0.93277943)

(1, 'Sunbear', 0.8578589)

(2, 'Sunbear', 0.29979056)

(1, 'Sunbear', 0.8787856)

(2, 'Sunbear', 0.32679325)

(1, 'Sunbear', 0.79356045)

Here is what i wanted to do:

To take the majority values that appeared for every 10 ( or more) returned values for boxes, classId and confidence (average value for this), to eliminate random fluctuation. Here are part of my codes,

 classIds = []
 confidences = []
 boxes = []
 for out in outs:
 for detection in out:
 scores = detection[5:]
 classId = np.argmax(scores)
 confidence = scores[classId]
 if confidence > confThreshold:
 center_x = int(detection[0] * frameWidth)
 center_y = int(detection[1] * frameHeight)
 width = int(detection[2] * frameWidth)
 height = int(detection[3] * frameHeight)
 left = int(center_x - width / 2)
 top = int(center_y - height / 2)
 classIds.append(classId)
 confidences.append(float(confidence))
 boxes.append([left, top, width, height])
 if classId ==0:
 classId = 'Asian_elephant'
 elif classId ==1:
 classId = 'Sunbear'
 elif classId ==2:
 classId = 'Tapir'
 #print ()
 #logging.debug('%s %s %s', len(boxes), confidence,classId)
 #logging.debug(boxes)
 print ((len(boxes),classId,confidence))

Here is what I am trying to do:

If classId of 'Sunbear' appeared 5 times or more continuously , it will print the returned values and the count will reset back to 0 or else it will keep resetting to zero till the condition is met.

 count=0
 while classId=='Sunbear': 
 count+=1
 if count>=5:
 print ((len(boxes),classId,confidence))
 break

but somehow the returned values are the same in or outside the loop. Is this the right way of doing this, or there is some more efficient ways to do it. Please bear with me, I am new to programming, thanks in advance.

python object-detection

share|improve this question

edited Mar 26 at 6:39

gameon67

1,47199 silver badges2828 bronze badges

asked Mar 26 at 2:35

shijishiji

1

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  what's the result that you got?
  
  – gameon67
  Mar 26 at 4:19
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  @gameon67 something like this (1, 'Sunbear', 0.91407496) (1, 'Sunbear', 0.91407496) (1, 'Sunbear', 0.93277943) (1, 'Sunbear', 0.93277943) (1, 'Sunbear', 0.8578589) (1, 'Sunbear', 0.8578589) (2, 'Sunbear', 0.29979056) (2, 'Sunbear', 0.29979056) (1, 'Sunbear', 0.8787856) (1, 'Sunbear', 0.8787856) (2, 'Sunbear', 0.32679325) (2, 'Sunbear', 0.32679325) (1, 'Sunbear', 0.79356045) (1, 'Sunbear', 0.79356045) as you can see both inside and outside (loop) values are the same
  
  – shiji
  Mar 26 at 7:26
  
  

  
  
  
  

add a comment | 

Good day, I am new to python and currently I am trying to work with my object detection assignment. What I am currently working with is to do filtering and do counting for objects that have been detected. For e.g , I have 3 return variables such as boxes (bounding boxes that appeared, to do counting), classId and confidence (to determine the object classes and its probability) with

print (len(boxes),classId,confidence)

and i got values like this (1 sec for 50+ values)

(1, 'Sunbear', 0.91407496)

(1, 'Sunbear', 0.93277943)

(1, 'Sunbear', 0.8578589)

(2, 'Sunbear', 0.29979056)

(1, 'Sunbear', 0.8787856)

(2, 'Sunbear', 0.32679325)

(1, 'Sunbear', 0.79356045)

Here is what i wanted to do:

To take the majority values that appeared for every 10 ( or more) returned values for boxes, classId and confidence (average value for this), to eliminate random fluctuation. Here are part of my codes,

 classIds = []
 confidences = []
 boxes = []
 for out in outs:
 for detection in out:
 scores = detection[5:]
 classId = np.argmax(scores)
 confidence = scores[classId]
 if confidence > confThreshold:
 center_x = int(detection[0] * frameWidth)
 center_y = int(detection[1] * frameHeight)
 width = int(detection[2] * frameWidth)
 height = int(detection[3] * frameHeight)
 left = int(center_x - width / 2)
 top = int(center_y - height / 2)
 classIds.append(classId)
 confidences.append(float(confidence))
 boxes.append([left, top, width, height])
 if classId ==0:
 classId = 'Asian_elephant'
 elif classId ==1:
 classId = 'Sunbear'
 elif classId ==2:
 classId = 'Tapir'
 #print ()
 #logging.debug('%s %s %s', len(boxes), confidence,classId)
 #logging.debug(boxes)
 print ((len(boxes),classId,confidence))

Here is what I am trying to do:

If classId of 'Sunbear' appeared 5 times or more continuously , it will print the returned values and the count will reset back to 0 or else it will keep resetting to zero till the condition is met.

 count=0
 while classId=='Sunbear': 
 count+=1
 if count>=5:
 print ((len(boxes),classId,confidence))
 break

but somehow the returned values are the same in or outside the loop. Is this the right way of doing this, or there is some more efficient ways to do it. Please bear with me, I am new to programming, thanks in advance.

python object-detection

share|improve this question

edited Mar 26 at 6:39

gameon67

1,47199 silver badges2828 bronze badges

asked Mar 26 at 2:35

shijishiji

1

print (len(boxes),classId,confidence)

(1, 'Sunbear', 0.91407496)

(1, 'Sunbear', 0.93277943)

(1, 'Sunbear', 0.8578589)

(2, 'Sunbear', 0.29979056)

(1, 'Sunbear', 0.8787856)

(2, 'Sunbear', 0.32679325)

(1, 'Sunbear', 0.79356045)

 classIds = []
 confidences = []
 boxes = []
 for out in outs:
 for detection in out:
 scores = detection[5:]
 classId = np.argmax(scores)
 confidence = scores[classId]
 if confidence > confThreshold:
 center_x = int(detection[0] * frameWidth)
 center_y = int(detection[1] * frameHeight)
 width = int(detection[2] * frameWidth)
 height = int(detection[3] * frameHeight)
 left = int(center_x - width / 2)
 top = int(center_y - height / 2)
 classIds.append(classId)
 confidences.append(float(confidence))
 boxes.append([left, top, width, height])
 if classId ==0:
 classId = 'Asian_elephant'
 elif classId ==1:
 classId = 'Sunbear'
 elif classId ==2:
 classId = 'Tapir'
 #print ()
 #logging.debug('%s %s %s', len(boxes), confidence,classId)
 #logging.debug(boxes)
 print ((len(boxes),classId,confidence))

 count=0
 while classId=='Sunbear': 
 count+=1
 if count>=5:
 print ((len(boxes),classId,confidence))
 break

share|improve this question

edited Mar 26 at 6:39

gameon67

1,47199 silver badges2828 bronze badges

asked Mar 26 at 2:35

shijishiji

1

share|improve this question

edited Mar 26 at 6:39

gameon67

1,47199 silver badges2828 bronze badges

asked Mar 26 at 2:35

shijishiji

1

edited Mar 26 at 6:39

gameon67

1,47199 silver badges2828 bronze badges

edited Mar 26 at 6:39

gameon67

1,47199 silver badges2828 bronze badges

asked Mar 26 at 2:35

shijishiji

1

asked Mar 26 at 2:35

shijishiji

1