API call returns "detail": "Not Found" error when code used works in Jupyter Notebook

[eRuaro]

First Check

• I added a very descriptive title to this issue.
• I used the GitHub search to find a similar issue and didn't find it.
• I searched the FastAPI documentation, with the integrated search.
• I already searched in Google "How to X in FastAPI" and didn't find any information.
• I already read and followed all the tutorial in the docs and didn't find an answer.
• I already checked if it is not related to FastAPI but to Pydantic.
• I already checked if it is not related to FastAPI but to Swagger UI.
• I already checked if it is not related to FastAPI but to ReDoc.

Commit to Help

• I commit to help with one of those options 👆

Example Code

from fastapi import FastAPI
import tensorflow as tf
import numpy as np

app = FastAPI()
model_dir = "food-vision-model.h5"
model = tf.keras.models.load_model(model_dir)

class_predictions = [
    'apple_pie',
    'baby_back_ribs',
    'baklava',
    'beef_carpaccio',
    'beef_tartare',
    'beet_salad',
    'beignets',
    'bibimbap',
    'bread_pudding',
    'breakfast_burrito',
    'bruschetta',
    'caesar_salad',
    'cannoli',
    'caprese_salad',
    'carrot_cake',
    'ceviche',
    'cheesecake',
    'cheese_plate',
    'chicken_curry',
    'chicken_quesadilla',
    'chicken_wings',
    'chocolate_cake',
    'chocolate_mousse',
    'churros',
    'clam_chowder',
    'club_sandwich',
    'crab_cakes',
    'creme_brulee',
    'croque_madame',
    'cup_cakes',
    'deviled_eggs',
    'donuts',
    'dumplings',
    'edamame',
    'eggs_benedict',
    'escargots',
    'falafel',
    'filet_mignon',
    'fish_and_chips',
    'foie_gras',
    'french_fries',
    'french_onion_soup',
    'french_toast',
    'fried_calamari',
    'fried_rice',
    'frozen_yogurt',
    'garlic_bread',
    'gnocchi',
    'greek_salad',
    'grilled_cheese_sandwich',
    'grilled_salmon',
    'guacamole',
    'gyoza',
    'hamburger',
    'hot_and_sour_soup',
    'hot_dog',
    'huevos_rancheros',
    'hummus',
    'ice_cream',
    'lasagna',
    'lobster_bisque',
    'lobster_roll_sandwich',
    'macaroni_and_cheese',
    'macarons',
    'miso_soup',
    'mussels',
    'nachos',
    'omelette',
    'onion_rings',
    'oysters',
    'pad_thai',
    'paella',
    'pancakes',
    'panna_cotta',
    'peking_duck',
    'pho',
    'pizza',
    'pork_chop',
    'poutine',
    'prime_rib',
    'pulled_pork_sandwich',
    'ramen',
    'ravioli',
    'red_velvet_cake',
    'risotto',
    'samosa',
    'sashimi',
    'scallops',
    'seaweed_salad',
    'shrimp_and_grits',
    'spaghetti_bolognese',
    'spaghetti_carbonara',
    'spring_rolls',
    'steak',
    'strawberry_shortcake',
    'sushi',
    'tacos',
    'takoyaki',
    'tiramisu',
    'tuna_tartare',
    'waffles'
]

@app.post("/net/image/prediction/{image_link}")
async def get_net_image_prediction(image_link: str):
    img_path = tf.keras.utils.get_file(
        origin = image_link
    )
    img = tf.keras.utils.load_img(
        img_path, 
        target_size = (224, 224)
    )

    img_array = tf.keras.utils.img_to_array(img)
    img_array = tf.expand_dims(img_array, 0)

    pred = model.predict(img_array)
    score = tf.nn.softmax(pred[0])

    class_prediction = class_names[np.argmax(score)]
    model_score = round(np.max(score) * 100, 2)

    return {
        "model_prediction_class": class_prediction,
        "model_prediction_score": model_score
    }

Description

I'm trying to make a RESTful API for image classification, I got the code that makes the predictions to work on jupyter notebook but I'm getting the error below when running through the API.

For reference, here's the output on jupyter.

Operating System

Windows

Operating System Details

No response

FastAPI Version

0.73.0

Python Version

3.9.7

Additional Context

No response

[upeshjindal]

I assume you are sending the image URL as you are doing it in the Jupyter notebook. I don't think you can send a URL in your path params. Try putting it in as query parameter.

Something like: https://yourdomain.com/classification?imageUrl=https://cdn.fxyz.co/image.jpeg

[eRuaro]

I can't view the image you sent. But I looked into your suggestion of using query parameters, it now works. Thanks!

Here's the working implementation as reference for anyone who might run into this problem in the future.

from fastapi import FastAPI
import tensorflow as tf
import numpy as np

app = FastAPI()
model_dir = "food-vision-model.h5"
model = tf.keras.models.load_model(model_dir)

class_predictions = [
    'apple_pie',
    'baby_back_ribs',
    'baklava',
    'beef_carpaccio',
    'beef_tartare',
    'beet_salad',
    'beignets',
    'bibimbap',
    'bread_pudding',
    'breakfast_burrito',
    'bruschetta',
    'caesar_salad',
    'cannoli',
    'caprese_salad',
    'carrot_cake',
    'ceviche',
    'cheesecake',
    'cheese_plate',
    'chicken_curry',
    'chicken_quesadilla',
    'chicken_wings',
    'chocolate_cake',
    'chocolate_mousse',
    'churros',
    'clam_chowder',
    'club_sandwich',
    'crab_cakes',
    'creme_brulee',
    'croque_madame',
    'cup_cakes',
    'deviled_eggs',
    'donuts',
    'dumplings',
    'edamame',
    'eggs_benedict',
    'escargots',
    'falafel',
    'filet_mignon',
    'fish_and_chips',
    'foie_gras',
    'french_fries',
    'french_onion_soup',
    'french_toast',
    'fried_calamari',
    'fried_rice',
    'frozen_yogurt',
    'garlic_bread',
    'gnocchi',
    'greek_salad',
    'grilled_cheese_sandwich',
    'grilled_salmon',
    'guacamole',
    'gyoza',
    'hamburger',
    'hot_and_sour_soup',
    'hot_dog',
    'huevos_rancheros',
    'hummus',
    'ice_cream',
    'lasagna',
    'lobster_bisque',
    'lobster_roll_sandwich',
    'macaroni_and_cheese',
    'macarons',
    'miso_soup',
    'mussels',
    'nachos',
    'omelette',
    'onion_rings',
    'oysters',
    'pad_thai',
    'paella',
    'pancakes',
    'panna_cotta',
    'peking_duck',
    'pho',
    'pizza',
    'pork_chop',
    'poutine',
    'prime_rib',
    'pulled_pork_sandwich',
    'ramen',
    'ravioli',
    'red_velvet_cake',
    'risotto',
    'samosa',
    'sashimi',
    'scallops',
    'seaweed_salad',
    'shrimp_and_grits',
    'spaghetti_bolognese',
    'spaghetti_carbonara',
    'spring_rolls',
    'steak',
    'strawberry_shortcake',
    'sushi',
    'tacos',
    'takoyaki',
    'tiramisu',
    'tuna_tartare',
    'waffles'
]

@app.post("/net/image/prediction/")
async def get_net_image_prediction(image_link: str = ""):
    if image_link == "":
        return {"message": "No image link provided"}
    
    img_path = tf.keras.utils.get_file(
        origin = image_link
    )
    img = tf.keras.utils.load_img(
        img_path, 
        target_size = (224, 224)
    )

    img_array = tf.keras.utils.img_to_array(img)
    img_array = tf.expand_dims(img_array, 0)

    pred = model.predict(img_array)
    score = tf.nn.softmax(pred[0])

    class_prediction = class_predictions[np.argmax(score)]
    model_score = round(np.max(score) * 100, 2)

    return {
        "model_prediction_class": class_prediction,
        "model_prediction_score": model_score
    }