How can i move line to y axis from x axis?which command do this operation?

When i use tflite model which is converted from darknet yolov4 weights i get this error,its quantized float16 tflite model,and i use only one class for my model
How can i fix this?
thanks in advance

C:\Users\Erkin\Desktop\tf yolov4\Tensorflow-2-Object-Counting>python tflite_cumulative_object_counting.py -m model.tflite -l labelmap.txt -v video.mp4 -a
Traceback (most recent call last):
  File "tflite_cumulative_object_counting.py", line 228, in <module>
    main()
  File "tflite_cumulative_object_counting.py", line 137, in main
    results = detect_objects(interpreter, image_pred, args.threshold)
  File "tflite_cumulative_object_counting.py", line 49, in detect_objects
    scores = get_output_tensor(interpreter, 2)
  File "tflite_cumulative_object_counting.py", line 36, in get_output_tensor
    output_details = interpreter.get_output_details()[index]
IndexError: list index out of range

Could you please provide a link to the video, model and label map that you used to generate examples? I would like to reproduce your results

I've a video of 3 minutes, and in that video I have 10-15 different object that can be detected using my model.

I can get the total of the object in one frame, but I would like to increment each time a new object detect.

for example in the first 30 seconds 3 persons detect, and then after 15 seconds another 2 persons detect, I would like to sum up this into totalcount = 5 persons and save into csv files etc.

those few lines of the code would count the detect object continuously but i would like to increment each object that counted.
final_count = [] filescore = np.squeeze(scores) count = 0 for i in range(100): if scores is None or filescore[i] > 0.5: count = count + 1 final_count.append(count) ymin = int(max(1,(boxes[i][0] * imH))) xmin = int(max(1,(boxes[i][1] * imW))) ymax = int(min(imH,(boxes[i][2] * imH))) xmax = int(min(imW,(boxes[i][3] * imW)))

            cv2.rectangle(frame, (xmin,ymin), (xmax,ymax), (10, 255, 0), 2)
            # Draw label                
            object_name = category_index[int(classes[i])]['name'] # Look up object name from "labels" array using class index
            label = '%s: %d%%' % (object_name, int(scores[i]*100)) # Example: 'person: 72%'

            labelSize, baseLine = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.7, 2) # Get font size
            label_ymin = max(ymin, labelSize[1] + 10) # Make sure not to draw label too close to top of window
            cv2.rectangle(frame, (xmin, label_ymin-labelSize[1]-10), (xmin+labelSize[0], label_ymin+baseLine-10), (255, 255, 255), cv2.FILLED) # Draw white box to put label text in
            cv2.putText(frame, label, (xmin, label_ymin-7), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 0), 2) # Draw label text
            
    
    if(len(new_name)> 0):     
        cv2.putText (frame,'Total Detections : ' + str(count),(10,25),cv2.FONT_HERSHEY_SIMPLEX,1,(70,235,52),2,cv2.LINE_AA)
     
    cv2.imshow("loading videos", frame)
    #print('These are total', total_object)

    if cv2.waitKey(1) & 0xFF == ord('q'):
        break`
        
      I tried both way. but I didnt get how I can increment each object that has been detect it. 

I tried using this one too ahmetozlu real time counting mode as well, but i just to increate all detect object into one total. let me know if you have tried this method.

Hello, I hope it's not to late to ask you about something. I am an absolute beginner and I try to follow your great tutorial.
Everything went well running the code on tensorflow but when I tried to use tensorflow lite version these error appears :
ImportError: generic_type: type "InterpreterWrapper" is already registered!

I am working with tensorflow 2.5.1 and I didn't find any solution on web, sorry to disturb you maybe you experiment this?
Maybe it's about dependencies for tflite?

Thank you for your time

I am an absolute beginner, follow your tutorial (https://www.youtube.com/watch?v=cvyDYdI2nEI&ab_channel=GilbertTanner) and successfully create a custom model but when trying the model with this TensorFlow-2-Object-Counting its doesn't work.
can please help on how to link your object detection tutorial to the abject counting tutorial.

Hello Tanner,

I have tested saved_model (created by exporter_main_v2.py file), works very nice. And I created a new saved_model in order to create tflite model with export_tflite_graph_tf2.py (when I converted tflite from the previously saved model gives error: tflight Didn't find op for builtin opcode 'STRIDED_SLICE' version '6')

So far tflite model loaded with succes but this time bellow error gives at count:

File "tflite_cumulative_object_counting.py", line 83, in detect_objects
    count = int(get_output_tensor(interpreter, 3))
TypeError: only size-1 arrays can be converted to Python scalars

the returning value at line 83 is an array. ([0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]) so, giving error is int([0. 0. 0. 0. 0. 0. 0. 0. 0. 0.])

Actually, it is a Python error apart from TF. But I just wanted to get your opinion on how to solve this in a clever way.

Thanks in advance.

When changing the flag to False, the line does not change. Could you please provide the exact command you used to produce the first video where you use the y axis?

ERROR: Could not find a version that satisfies the requirement tflite_runtime==2.5.0 (from -r requirements.txt (line 5)) (from versions: none)
ERROR: No matching distribution found for tflite_runtime==2.5.0 (from -r requirements.txt (line 5))

Can not install this package for some reason. Does anyone know how to solve this?
My python version is 3.8.5