HttpError

[YounZGrace]

• Project Type:
• Operating System & Browser: - MAC OS - google chrome
• Project Universe Link or Workspace/Project ID: - fnl_labeling

Objective: I am trying to export the JSON dictionaries of my frame predictions using code in python. I found this script on the roboflow forum from a couple years back.

Error: I was successful at obtaining the predictions for a couple frames, but then I ran into an http error. My video is around 2min~

Looking at the other forums, it seems as though I may need to pay more for this function to work, but I wanted to confirm before doing so.

roboflow.login()

rf = roboflow.Roboflow()

rf = Roboflow(api_key="xxx")
project = rf.workspace("caitlyn-lee-gr-dartmouth-edu").project("xxx")
version = project.version(1)


# run inference
model = version.model

# Video capture
f = cv2.VideoCapture(video_file)

rf = Roboflow(api_key="f06RVtgEWRnqjdc52Ujc")
project = rf.workspace("fnlidentitylabels").project("fnl-character-labeling")
model = project.version(5).model
dataset = version.download("yolov4pytorch")

while(f.isOpened()):
  # f.read() methods returns a tuple, first element is a bool 
  # and the second is frame
    ret, frame = f.read()
    if ret == True:
        # save frame as a “temporary” jpeg file
        cv2.imwrite('temp.jpg', frame)
        # run inference on “temporary” jpeg file (the frame)
        predictions = model.predict('temp.jpg')
        predictions_json = predictions.json()
        # printing all detection results from the image
        print(predictions_json)

        # accessing individual predicted boxes on each image
        for bounding_box in predictions:
            # x0 = bounding_box['x'] - bounding_box['width'] / 2#start_column
            # x1 = bounding_box['x'] + bounding_box['width'] / 2#end_column
            # y0 = bounding_box['y'] - bounding_box['height'] / 2#start row
            # y1 = bounding_box['y'] + bounding_box['height'] / 2#end_row
            class_name = bounding_box['class']
            confidence_score = bounding_box['confidence']
        
            detection_results = bounding_box
            class_and_confidence = (class_name, confidence_score)
            print(class_and_confidence, '\n')

    elif cv.waitKey(1) == ord('q'):
        break
    else:
        break

f.release()
cv2.destroyAllWindows()

[Cahse_Pahm]

This is my exact issue too! I hope you get a solution. I think it’s a bug, as I copied it exactly from the example.

Urgent: Remove your API Key from the code snippet. You removed it once but forgot the other one.

[leo]

Hey @YounZGrace @Cahse_Pahm

It’s likely that you passed your monthly hosted inference limit. You can check your hosted inference limit in the Usage tab of your settings and enable overages if you would like.

@YounZGrace I have revoked your API key since you published it publicly here on the forum. You can create a new one by going to the Roboflow API page of the settings.