🌘w🌖

app.py

@@ -1,6 +1,36 @@
 import gradio as gr
+import spaces
+import torch
+from transformers import AutoProcessor, AutoModelForZeroShotImageClassification
+from datasets import load_dataset
 
-def search(img):
-  return img
-      
-demo = gr.Interface(search, inputs="image",outputs=["image"])
+dataset = load_dataset("not-lain/embedded-pokemon", split="train")
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+processor = AutoProcessor.from_pretrained("openai/clip-vit-large-patch14")
+model = AutoModelForZeroShotImageClassification.from_pretrained(
+    "openai/clip-vit-large-patch14", device_map=device
+)
+
+
+@spaces.GPU
+def search(query: str, k: int = 4 ):
+    """a function that embeds a new image and returns the most probable results"""
+
+    pixel_values = processor(images = query, return_tensors="pt")['pixel_values'] # embed new image
+    pixel_values = pixel_values.to(device)
+    img_emb = model.get_image_features(pixel_values)[0] # because 1 element
+    img_emb = img_emb.cpu().detach().numpy() # because datasets only works with numpy
+
+    scores, retrieved_examples = dataset.get_nearest_examples( # retrieve results
+        "embeddings", img_emb, # compare our new embedded query with the dataset embeddings
+        k=k # get only top k results
+    )
+
+    return retrieved_examples["image"]
+
+
+demo = gr.Interface(search, inputs="image", outputs=["gallery"])
+
+demo.launch(debug=True)

requirements.txt

@@ -0,0 +1,5 @@
+datasets 
+torch
+spaces
+accelerate 
+faiss-cpu