Uploaded app and requirements for embeddings app.

app.py

@@ -0,0 +1,87 @@
+import torch
+from PIL import Image
+from transformers import CLIPProcessor, CLIPModel
+from torch.utils.data import Dataset, DataLoader
+import os
+import numpy as np
+import pickle
+import gradio as gr
+
+class ImageDataset(Dataset):
+    def __init__(self, image_dir, processor):
+        self.image_paths = [os.path.join(image_dir, f) for f in os.listdir(image_dir) if f.endswith(('.png', '.jpg', '.jpeg'))]
+        self.processor = processor
+
+    def __len__(self):
+        return len(self.image_paths)
+
+    def __getitem__(self, idx):
+        image = Image.open(self.image_paths[idx])
+        return self.processor(images=image, return_tensors="pt")['pixel_values'][0]
+
+def get_and_save_clip_embeddings(image_dir, output_file, batch_size=32, device='cuda'):
+    model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32").to(device)
+    processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
+
+    dataset = ImageDataset(image_dir, processor)
+    dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=False, num_workers=4)
+
+    all_embeddings = []
+    image_paths = []
+
+    model.eval()
+    with torch.no_grad():
+        for batch_idx, batch in enumerate(dataloader):
+            batch = batch.to(device)
+            embeddings = model.get_image_features(pixel_values=batch)
+            all_embeddings.append(embeddings.cpu().numpy())
+            start_idx = batch_idx * batch_size
+            end_idx = start_idx + len(batch)
+            image_paths.extend(dataset.image_paths[start_idx:end_idx])
+
+    all_embeddings = np.concatenate(all_embeddings)
+
+    with open(output_file, 'wb') as f:
+        pickle.dump({'embeddings': all_embeddings, 'image_paths': image_paths}, f)
+
+# image_dir = "dataset/"
+# output_file = "image_embeddings.pkl"
+# batch_size = 32
+# device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# get_and_save_clip_embeddings(image_dir, output_file, batch_size, device)
+
+
+# APP
+
+model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
+processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
+
+with open('image_embeddings.pkl', 'rb') as f:
+        f = pickle.load(f)
+        image_embeddings = f['embeddings']
+        image_names = f['image_paths']
+image_paths = 'dataset'
+
+def cosine_similarity(a, b):
+    a = a / np.linalg.norm(a, axis=-1, keepdims=True)
+    b = b / np.linalg.norm(b, axis=-1, keepdims=True)
+    return np.dot(a, b.T)
+
+def find_similar_images(text):
+    inputs = processor(text=[text], return_tensors="pt", padding=True)
+    with torch.no_grad():
+        text_embedding = model.get_text_features(**inputs).cpu().numpy()
+
+    similarities = cosine_similarity(text_embedding, image_embeddings)
+    top_indices = np.argsort(similarities[0])[::-1][:4]
+    top_images = [image_names[i] for i in top_indices]
+    
+    return top_images
+
+text_input = gr.Textbox(label="Input text", placeholder="Enter the images description")
+imgs_output = gr.Gallery(label="Top 4 most similar images")
+
+intf = gr.Interface(fn=find_similar_images, inputs=text_input, outputs=imgs_output)
+
+intf.launch(share=True)

requirements.txt

@@ -0,0 +1,204 @@
+absl-py==2.1.0
+aiofiles==23.2.1
+aiohappyeyeballs==2.4.3
+aiohttp==3.10.8
+aiosignal==1.3.1
+annotated-types==0.7.0
+anyio==4.6.0
+argon2-cffi==23.1.0
+argon2-cffi-bindings==21.2.0
+arrow==1.3.0
+asttokens==2.4.1
+async-lru==2.0.4
+async-timeout==4.0.3
+attrs==24.2.0
+babel==2.16.0
+backoff==2.2.1
+beautifulsoup4==4.12.3
+bleach==6.1.0
+boto3==1.35.31
+botocore==1.35.31
+cachetools==5.5.0
+certifi==2024.8.30
+cffi==1.17.1
+charset-normalizer==3.3.2
+click==8.1.7
+comm==0.2.2
+contourpy==1.3.0
+cycler==0.12.1
+debugpy==1.8.6
+decorator==5.1.1
+defusedxml==0.7.1
+exceptiongroup==1.2.2
+executing==2.1.0
+-e git+https://github.com/fastai/fastai@80e032b0eb98860166f3ace7d2408ac210174b12#egg=fastai
+fastapi==0.115.0
+fastcore==1.7.11
+fastdownload==0.0.7
+fastjsonschema==2.20.0
+fastprogress==1.0.3
+ffmpy==0.4.0
+filelock==3.16.1
+fire==0.7.0
+fonttools==4.54.1
+fqdn==1.5.1
+frozenlist==1.4.1
+fsspec==2024.9.0
+google-auth==2.35.0
+google-auth-oauthlib==1.2.1
+gradio==4.44.1
+gradio_client==1.3.0
+grpcio==1.66.2
+h11==0.14.0
+httpcore==1.0.6
+httpx==0.27.2
+huggingface-hub==0.25.1
+idna==3.10
+importlib_resources==6.4.5
+ipykernel==6.26.0
+ipython==8.17.2
+ipywidgets==8.1.1
+isoduration==20.11.0
+jedi==0.19.1
+Jinja2==3.1.4
+jmespath==1.0.1
+joblib==1.4.2
+json5==0.9.25
+jsonpointer==3.0.0
+jsonschema==4.23.0
+jsonschema-specifications==2023.12.1
+jupyter-events==0.10.0
+jupyter-lsp==2.2.5
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+jupyter_server==2.14.2
+jupyter_server_terminals==0.5.3
+jupyterlab==4.2.0
+jupyterlab_pygments==0.3.0
+jupyterlab_server==2.27.3
+jupyterlab_widgets==3.0.13
+kiwisolver==1.4.7
+lightning==2.4.0
+lightning-cloud==0.5.70
+lightning-utilities==0.11.7
+lightning_sdk==0.1.19
+litdata==0.2.19
+litserve==0.2.2
+Markdown==3.7
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.8.2
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+mistune==3.0.2
+mpmath==1.3.0
+multidict==6.1.0
+nbclient==0.10.0
+nbconvert==7.16.4
+nbformat==5.10.4
+nest-asyncio==1.6.0
+networkx==3.3
+notebook_shim==0.2.4
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.19.3
+nvidia-nvjitlink-cu12==12.6.77
+nvidia-nvtx-cu12==12.1.105
+oauthlib==3.2.2
+orjson==3.10.7
+overrides==7.7.0
+packaging==24.1
+pandas==2.1.4
+pandocfilters==1.5.1
+parso==0.8.4
+pexpect==4.9.0
+pillow==10.4.0
+platformdirs==4.3.6
+prometheus_client==0.21.0
+prompt_toolkit==3.0.48
+protobuf==4.23.4
+psutil==6.0.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pyasn1==0.6.1
+pyasn1_modules==0.4.1
+pycparser==2.22
+pydantic==2.9.2
+pydantic_core==2.23.4
+pydub==0.25.1
+Pygments==2.18.0
+PyJWT==2.9.0
+pyparsing==3.1.4
+python-dateutil==2.9.0.post0
+python-json-logger==2.0.7
+python-multipart==0.0.12
+pytorch-lightning==2.4.0
+pytz==2024.2
+PyYAML==6.0.2
+pyzmq==26.2.0
+referencing==0.35.1
+regex==2024.9.11
+requests==2.32.3
+requests-oauthlib==2.0.0
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rich==13.9.1
+rpds-py==0.20.0
+rsa==4.9
+ruff==0.6.9
+s3transfer==0.10.2
+safetensors==0.4.5
+scikit-learn==1.3.2
+scipy==1.11.4
+semantic-version==2.10.0
+Send2Trash==1.8.3
+shellingham==1.5.4
+simple-term-menu==1.6.4
+six==1.16.0
+sniffio==1.3.1
+soupsieve==2.6
+stack-data==0.6.3
+starlette==0.38.6
+sympy==1.13.3
+tensorboard==2.15.1
+tensorboard-data-server==0.7.2
+termcolor==2.4.0
+terminado==0.18.1
+threadpoolctl==3.5.0
+timm==1.0.9
+tinycss2==1.3.0
+tokenizers==0.20.1
+tomli==2.0.1
+tomlkit==0.12.0
+torch==2.2.1+cu121
+torchmetrics==1.3.1
+torchsummary==1.5.1
+torchvision==0.17.1+cu121
+tornado==6.4.1
+tqdm==4.66.5
+traitlets==5.14.3
+transformers==4.45.2
+triton==2.2.0
+typer==0.12.5
+types-python-dateutil==2.9.0.20240906
+typing_extensions==4.12.2
+tzdata==2024.2
+uri-template==1.3.0
+urllib3==2.2.3
+uvicorn==0.31.0
+wcwidth==0.2.13
+webcolors==24.8.0
+webencodings==0.5.1
+websocket-client==1.8.0
+websockets==12.0
+Werkzeug==3.0.4
+widgetsnbextension==4.0.13
+yarl==1.13.1