Repeated API Errors

[willhy4]

Search before asking

• [X] I have searched the HUB issues and found no similar bug report.

HUB Component

Inference

Bug

---

HTTPError Traceback (most recent call last) Cell In[13], line 16 12 response = requests.post(url, headers=headers, data=data, files={"image": f}) 13 #if response.status_code == 429: 14 # time.sleep(int(response.headers["Retry-After"])) ---> 16 response.raise_for_status() 18 # Get predicted class and confidence from response 19 predicted_class = response.json()['data'][0]['class']

File ~/Python310-boto3/lib/python3.10/site-packages/requests/models.py:1021, in Response.raise_for_status(self) 1016 http_error_msg = ( 1017 f"{self.status_code} Server Error: {reason} for url: {self.url}" 1018 ) 1020 if http_error_msg: -> 1021 raise HTTPError(http_error_msg, response=self)

HTTPError: 502 Server Error: Bad Gateway for url: https://api.ultralytics.com/v1/predict/AFX0h0mvCLGtEDjTVvbJ

Environment

• Computer: MacBook Pro (13-inch) - but I get the same error on a 2022 Dell as well since I am calling from a jupyter hub environment
• processor 2.5 GHz, i5
• Memory: 16 GM 1600 MHz DDR3
• Disk: SSD

Minimal Reproducible Example

I am attempting to run inference on 100 images and I get this same error for every model (17 of them) that I have created.

Here's the code:

Iterate through items and store results in lists

for image_filename in os.listdir(image_folder_path): if image_filename.endswith(('.jpg', '.jpeg', '.png', '.gif')): image_path = os.path.join(image_folder_path, image_filename) label_filename = os.path.splitext(image_filename)[0] + '.txt' label_path = os.path.join(label_folder_path, label_filename)

    # Read the label file to get the actual class
    actual_class = read_label_file(label_path)

    with open(image_path, "rb") as f:
        response = requests.post(url, headers=headers, data=data, files={"image": f})
        #if response.status_code == 429:
        #    time.sleep(int(response.headers["Retry-After"]))

    response.raise_for_status()

    # Get predicted class and confidence from response
    predicted_class = response.json()['data'][0]['class']
    confidence = response.json()['data'][0]['confidence']

    # Store results in lists
    image_list.append(image_filename)
    actual_class_list.append(actual_class)
    predicted_class_list.append(predicted_class)
    confidence_list.append(confidence)
    #time.sleep(5)

Function to read label file and extract class information

def read_label_file(label_file_path): with open(label_file_path, 'r') as label_file:

Read the first line of the label file

    first_line = label_file.readline().strip()

    # Extract the class value from the first integer
    class_value = int(first_line.split()[0])

return class_value

Additional

The url, headers, and data values were copy/paste from the "Deploy" page for each model.

[github-actions[bot]]

👋 Hello @willhy4, thank you for raising an issue about Ultralytics HUB 🚀! Please visit our HUB Docs to learn more:

• Quickstart. Start training and deploying YOLO models with HUB in seconds.
• Datasets: Preparing and Uploading. Learn how to prepare and upload your datasets to HUB in YOLO format.
• Projects: Creating and Managing. Group your models into projects for improved organization.
• Models: Training and Exporting. Train YOLOv5 and YOLOv8 models on your custom datasets and export them to various formats for deployment.
• Integrations. Explore different integration options for your trained models, such as TensorFlow, ONNX, OpenVINO, CoreML, and PaddlePaddle.
• Ultralytics HUB App. Learn about the Ultralytics App for iOS and Android, which allows you to run models directly on your mobile device.
  • iOS. Learn about YOLO CoreML models accelerated on Apple's Neural Engine on iPhones and iPads.
  • Android. Explore TFLite acceleration on mobile devices.
• Inference API. Understand how to use the Inference API for running your trained models in the cloud to generate predictions.

If this is a 🐛 Bug Report, please provide screenshots and steps to reproduce your problem to help us get started working on a fix.

If this is a ❓ Question, please provide as much information as possible, including dataset, model, environment details etc. so that we might provide the most helpful response.

We try to respond to all issues as promptly as possible. Thank you for your patience!