import ast import json import spaces import requests import numpy as np import gradio as gr from PIL import Image from io import BytesIO from turtle import title from openai import OpenAI from collections import Counter from transformers import pipeline client = OpenAI() pipe = pipeline("zero-shot-image-classification", model="patrickjohncyh/fashion-clip") color_file_path = 'color_config.json' attributes_file_path = 'attributes_config.json' import os OPENAIKEY = os.getenv("OPENAI_KEY") # Open and read the COLOR JSON file with open(color_file_path, 'r') as file: color_data = json.load(file) # Open and read the ATTRIBUTES JSON file with open(attributes_file_path, 'r') as file: attributes_data = json.load(file) COLOURS_DICT = color_data['color_mapping'] ATTRIBUTES_DICT = attributes_data['attribute_mapping'] def shot(input, category): subColour,mainColour,score = get_colour(ast.literal_eval(str(input)),category) common_result = get_predicted_attributes(ast.literal_eval(str(input)),category) return { "colors":{ "main":mainColour, "sub":subColour, "score":round(score*100,2) }, "attributes":common_result, "image_mapping":openai_parsed_response } @spaces.GPU def get_colour(image_urls, category): colourLabels = list(COLOURS_DICT.keys()) for i in range(len(colourLabels)): colourLabels[i] = colourLabels[i] + " clothing: " + category responses = pipe(image_urls, candidate_labels=colourLabels) # Get the most common colour mainColour = responses[0][0]['label'].split(" clothing:")[0] if mainColour not in COLOURS_DICT: return None, None, None # Add category to the end of each label labels = COLOURS_DICT[mainColour] for i in range(len(labels)): labels[i] = labels[i] + " clothing: " + category # Run pipeline in one go responses = pipe(image_urls, candidate_labels=labels) subColour = responses[0][0]['label'].split(" clothing:")[0] return subColour, mainColour, responses[0][0]['score'] @spaces.GPU def get_predicted_attributes(image_urls, category): # Get the predicted attributes for the image # attributes = get_category_attributes(category) attributes = list(ATTRIBUTES_DICT.get(category,{}).keys()) # Mapping of possible values per attribute common_result = [] for attribute in attributes: # values = get_attribute_values(attribute, category) values = ATTRIBUTES_DICT.get(category,{}).get(attribute,[]) if len(values) == 0: continue # Adjust labels for the pipeline to be in format: "{attr}: {value}, clothing: {category}" attribute = attribute.replace("colartype", "collar").replace("sleevelength", "sleeve length").replace("fabricstyle", "fabric") values = [f"{attribute}: {value}, clothing: {category}" for value in values] # Get the predicted values for the attribute responses = pipe(image_urls, candidate_labels=values) result = [response[0]['label'].split(", clothing:")[0] for response in responses] # If attribute is details, then get the top 2 most common labels if attribute == "details": result += [response[1]['label'].split(", clothing:")[0] for response in responses] common_result.append(Counter(result).most_common(2)) else: common_result.append(Counter(result).most_common(1)) # Clean up the results into one long string for i, result in enumerate(common_result): common_result[i] = ", ".join([f"{x[0]}" for x in result]) result = {} # Iterate through the list and split each item into key and value for item in common_result: # Split by ': ' to separate the key and value key, value = item.split(': ', 1) # Add to the dictionary result[key] = value return result def get_openAI_tags(image_urls): # Create list containing JSONs of each image URL imageList = [] for image in image_urls: imageList.append({"type": "image_url", "image_url": {"url": image}}) openai_response = client.chat.completions.create( model="gpt-4o", messages=[ { "role": "system", "content": [ { "type": "text", "text": "You're a tagging assistant, you will help label and tag product pictures for my online e-commerce platform. Your tasks will be to return which angle the product images were taken from. You will have to choose from 'full-body', 'half-body', 'side', 'back', or 'zoomed' angles. You should label each of the images with one of these labels depending on which you think fits best (ideally, every label should be used at least once, but only if there are 5 or more images), and should respond with nothing but the labels separated by a comma in the order of the images without any other text. You should label every picture, no more, no less." } ] }, { "role": "user", "content": imageList }, ], temperature=1, max_tokens=500, top_p=1, frequency_penalty=0, presence_penalty=0 ) response= json.loads(openai_response.choices[0].message.content) return response # Define the Gradio interface with the updated components iface = gr.Interface( fn=shot, inputs=[ gr.Textbox(label="Image URLs (starting with http/https) comma seperated "), gr.Textbox(label="Category") ], outputs="text" , examples=[ [['https://d2q1sfov6ca7my.cloudfront.net/eyJidWNrZXQiOiAiaGljY3VwLWltYWdlLWhvc3RpbmciLCAia2V5IjogIlc4MDAwMDAwMTM0LU9SL1c4MDAwMDAwMTM0LU9SLTEuanBnIiwgImVkaXRzIjogeyJyZXNpemUiOiB7IndpZHRoIjogODAwLCAiaGVpZ2h0IjogMTIwMC4wLCAiZml0IjogIm91dHNpZGUifX19', 'https://d2q1sfov6ca7my.cloudfront.net/eyJidWNrZXQiOiAiaGljY3VwLWltYWdlLWhvc3RpbmciLCAia2V5IjogIlc4MDAwMDAwMTM0LU9SL1c4MDAwMDAwMTM0LU9SLTIuanBnIiwgImVkaXRzIjogeyJyZXNpemUiOiB7IndpZHRoIjogODAwLCAiaGVpZ2h0IjogMTIwMC4wLCAiZml0IjogIm91dHNpZGUifX19', 'https://d2q1sfov6ca7my.cloudfront.net/eyJidWNrZXQiOiAiaGljY3VwLWltYWdlLWhvc3RpbmciLCAia2V5IjogIlc4MDAwMDAwMTM0LU9SL1c4MDAwMDAwMTM0LU9SLTMuanBnIiwgImVkaXRzIjogeyJyZXNpemUiOiB7IndpZHRoIjogODAwLCAiaGVpZ2h0IjogMTIwMC4wLCAiZml0IjogIm91dHNpZGUifX19'], "women-top-shirt"]], description="Add an image URL (starting with http/https) or upload a picture, and provide a list of labels separated by commas.", title="Full product flow" ) # Launch the interface iface.launch()