Upload 123 files

.gitattributes

@@ -1,35 +1 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+unsplash-25k-photos-embeddings.pkl filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,129 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,13 +1,38 @@
 ---
-title: Embrace Vision
-emoji: 🏢
-colorFrom: yellow
-colorTo: purple
+title: CLIP Image Search
+emoji: 📸
+colorFrom: pink
+colorTo: pink
 sdk: gradio
-sdk_version: 3.50.2
 app_file: app.py
 pinned: false
-license: apache-2.0
+python_version: 3.10.10
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Configuration
+
+`title`: _string_  
+Display title for the Space
+
+`emoji`: _string_  
+Space emoji (emoji-only character allowed)
+
+`colorFrom`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`colorTo`: _string_  
+Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
+
+`sdk`: _string_  
+Can be either `gradio` or `streamlit`
+
+`sdk_version` : _string_  
+Only applicable for `streamlit` SDK.  
+See [doc](https://hf.co/docs/hub/spaces) for more info on supported versions.
+
+`app_file`: _string_  
+Path to your main application file (which contains either `gradio` or `streamlit` Python code).  
+Path is relative to the root of the repository.
+
+`pinned`: _boolean_  
+Whether the Space stays on top of your list.

app.py

@@ -0,0 +1,240 @@
+import gradio as gr
+from transformers import CLIPProcessor, CLIPModel, CLIPTokenizer, BlipProcessor, BlipForConditionalGeneration, pipeline
+from sentence_transformers import SentenceTransformer, util
+import pickle
+import numpy as np
+from PIL import Image, ImageEnhance
+import os
+import io
+import concurrent.futures
+import warnings
+
+warnings.filterwarnings("ignore")
+
+
+class CLIPModelHandler:
+    def __init__(self, model_name):
+        self.model_name = model_name
+        self.img_names, self.img_emb = self.load_precomputed_embeddings()
+
+    def load_precomputed_embeddings(self):
+        emb_filename = 'unsplash-25k-photos-embeddings.pkl'
+        with open(emb_filename, 'rb') as fIn:
+            img_names, img_emb = pickle.load(fIn)
+        return img_names, img_emb
+
+    def search_text(self, query, top_k=1):
+        model = CLIPModel.from_pretrained(self.model_name)
+        processor = CLIPProcessor.from_pretrained(self.model_name)
+        tokenizer = CLIPTokenizer.from_pretrained(self.model_name)
+        
+        inputs = tokenizer([query], padding=True, return_tensors="pt")
+        query_emb = model.get_text_features(**inputs)
+        hits = util.semantic_search(query_emb, self.img_emb, top_k=top_k)[0]
+
+        images = [Image.open(os.path.join("photos/", self.img_names[hit['corpus_id']])) for hit in hits]
+        return images
+
+    def search_image(self, image_path, top_k=1):
+        model = CLIPModel.from_pretrained(self.model_name)
+        processor = CLIPProcessor.from_pretrained(self.model_name)
+        
+        # Load and preprocess the image
+        image = Image.open(image_path)
+        inputs = processor(images=image, return_tensors="pt")
+
+        # Get the image features
+        outputs = model(**inputs)
+        image_emb = outputs.logits_per_image
+
+        # Perform semantic search
+        hits = util.semantic_search(image_emb, self.img_emb, top_k=top_k)[0]
+
+        # Retrieve and return the relevant images
+        result_images = []
+        for hit in hits:
+            img = Image.open(os.path.join("photos/", self.img_names[hit['corpus_id']]))
+            result_images.append(img)
+
+        return result_images
+
+class BLIPImageCaptioning:
+    def __init__(self, blip_model_name):
+        self.blip_model_name = blip_model_name
+
+    def preprocess_image(self, image):
+        if isinstance(image, str):
+            return Image.open(image).convert('RGB')
+        elif isinstance(image, np.ndarray):
+            return Image.fromarray(np.uint8(image)).convert('RGB')
+        else:
+            raise ValueError("Invalid input type for image. Supported types: str (file path) or np.ndarray.")
+
+    def generate_caption(self, image):
+        try:
+            model = BlipForConditionalGeneration.from_pretrained(self.blip_model_name).to("cuda")
+            processor = BlipProcessor.from_pretrained(self.blip_model_name)
+            
+            raw_image = self.preprocess_image(image)
+            inputs = processor(raw_image, return_tensors="pt").to("cuda")
+            out = model.generate(**inputs)
+            unconditional_caption = processor.decode(out[0], skip_special_tokens=True)
+
+            return unconditional_caption
+        except Exception as e:
+            return {"error": str(e)}
+
+    def generate_captions_parallel(self, images):
+        with concurrent.futures.ThreadPoolExecutor() as executor:
+            results = list(executor.map(self.generate_caption, images))
+
+        return results
+
+
+# Initialize the CLIP model handler
+clip_handler = CLIPModelHandler("openai/clip-vit-base-patch32")
+
+# Initialize the zero-shot image classification pipeline
+clip_classifier = pipeline("zero-shot-image-classification", model="openai/clip-vit-base-patch32")
+
+# Load BLIP model directly
+blip_processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+blip_model_name = "Salesforce/blip-image-captioning-base"
+
+# Function for text-to-image search
+def text_to_image_interface(query, top_k):
+    try:
+        # Perform text-to-image search
+        result_images = clip_handler.search_text(query, top_k)
+
+        # Resize images before displaying
+        result_images_resized = [image.resize((224, 224)) for image in result_images]
+
+        # Display more information about the results
+        result_info = [{"Image Name": os.path.basename(img_path)} for img_path in clip_handler.img_names]
+
+        return result_images_resized, result_info
+    except Exception as e:
+        return gr.Error(f"Error in text-to-image search: {str(e)}")
+
+
+# Gradio Interface function for zero-shot classification
+def zero_shot_classification(image, labels_text):
+    try:
+        # Convert image to PIL format
+        PIL_image = Image.fromarray(np.uint8(image)).convert('RGB')
+
+        # Split labels_text into a list of labels
+        labels = labels_text.split(",")
+
+        # Perform zero-shot classification
+        res = clip_classifier(images=PIL_image, candidate_labels=labels, hypothesis_template="This is a photo of a {}")
+
+        # Format the result as a dictionary
+        formatted_results = {dic["label"]: dic["score"] for dic in res}
+
+        return formatted_results
+    except Exception as e:
+        return gr.Error(f"Error in zero-shot classification: {str(e)}")
+
+
+
+def preprocessing_interface(original_image, brightness_slider, contrast_slider, saturation_slider, sharpness_slider, rotation_slider):
+    try:
+        # Convert NumPy array to PIL Image
+        PIL_image = Image.fromarray(np.uint8(original_image)).convert('RGB')
+
+        # Normalize slider values to be in the range [0, 1]
+        brightness_normalized = brightness_slider / 100.0
+        contrast_normalized = contrast_slider / 100.0
+        saturation_normalized = saturation_slider / 100.0
+        sharpness_normalized = sharpness_slider / 100.0
+
+        # Apply preprocessing based on user input
+        PIL_image = PIL_image.convert("RGB")
+        PIL_image = PIL_image.rotate(rotation_slider)
+        
+        # Adjust brightness
+        enhancer = ImageEnhance.Brightness(PIL_image)
+        PIL_image = enhancer.enhance(brightness_normalized)
+
+        # Adjust contrast
+        enhancer = ImageEnhance.Contrast(PIL_image)
+        PIL_image = enhancer.enhance(contrast_normalized)
+
+        # Adjust saturation
+        enhancer = ImageEnhance.Color(PIL_image)
+        PIL_image = enhancer.enhance(saturation_normalized)
+
+        # Adjust sharpness
+        enhancer = ImageEnhance.Sharpness(PIL_image)
+        PIL_image = enhancer.enhance(sharpness_normalized)
+
+        # Return the processed image
+        return PIL_image
+    except Exception as e:
+        return gr.Error(f"Error in preprocessing: {str(e)}")
+
+def generate_captions(images):
+    blip_model = BlipForConditionalGeneration.from_pretrained(blip_model_name).to("cuda")
+    blip_processor = BlipProcessor.from_pretrained(blip_model_name)
+    
+    return [blip_model_instance.generate_caption(image) for image in images]
+
+
+# Gradio Interfaces
+zero_shot_classification_interface = gr.Interface(
+    fn=zero_shot_classification,
+    inputs=[
+        gr.Image(label="Image Query", elem_id="image_input"),
+        gr.Textbox(label="Labels (comma-separated)", elem_id="labels_input"),
+    ],
+    outputs=gr.Label(elem_id="label_image"),
+)
+
+text_to_image_interface = gr.Interface(
+    fn=text_to_image_interface,
+    inputs=[
+        gr.Textbox(
+            lines=2,
+            label="Text Query",
+            placeholder="Enter text here...",
+        ),
+        gr.Slider(0, 5, step=1, label="Top K Results"),
+    ],
+    outputs=[
+        gr.Gallery(
+            label="Text-to-Image Search Results",
+            elem_id="gallery_text",
+            grid_cols=2,
+            height="auto",
+        ),
+        gr.Text(label="Result Information", elem_id="text_info"),
+    ],
+)
+
+blip_model = BLIPImageCaptioning(blip_model_name)  # Instantiate the object
+blip_captioning_interface = gr.Interface(
+    fn=blip_model.generate_caption,  # Correct the method name
+    inputs=gr.Image(label="Image for Captioning", elem_id="blip_caption_image"),
+    outputs=gr.Textbox(label="Generated Captions", elem_id="blip_generated_captions", default=""),
+)
+
+preprocessing_interface = gr.Interface(
+    fn=blip_model.preprocess_image,  # Correct the method name
+    inputs=[
+        gr.Image(label="Original Image", elem_id="original_image"),
+    ],
+    outputs=[
+        gr.Image(label="Processed Image", elem_id="processed_image"),
+    ],
+)
+
+# Tabbed Interface
+app = gr.TabbedInterface(
+    interface_list=[text_to_image_interface, zero_shot_classification_interface, blip_captioning_interface],
+    tab_names=["Text-to-Image Search", "Zero-Shot Classification", "BLIP Image Captioning"],
+)
+
+# Launch the Gradio interface
+app.launch(debug=True, share="true")

features_extraction.py

@@ -0,0 +1,44 @@
+import torch
+from torchvision import models, transforms
+from PIL import Image
+import pickle
+import os
+from tqdm import tqdm  # Import tqdm for the progress bar
+
+# Load a pretrained ResNet model
+model = models.resnet50(pretrained=True)
+model = model.eval()
+
+# Define preprocessing transforms
+preprocess = transforms.Compose([
+    transforms.Resize((224, 224)),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+])
+
+# Function to extract features from an image
+def extract_features(image_path):
+    image = Image.open(image_path).convert('RGB')
+    input_tensor = preprocess(image)
+    input_batch = input_tensor.unsqueeze(0)
+
+    with torch.no_grad():
+        output = model(input_batch)
+
+    return output.squeeze().numpy()
+
+# Directory containing your images
+images_directory = "photos/"
+
+# Process each image and save features
+image_features = {}
+for filename in tqdm(os.listdir(images_directory), desc="Processing Images"):
+    if filename.endswith(".jpg") or filename.endswith(".png"):
+        image_path = os.path.join(images_directory, filename)
+        features = extract_features(image_path)
+        image_features[filename] = features
+
+# Save the features to a pickle file
+output_file = "unsplash-25k-embeddings.pkl"
+with open(output_file, 'wb') as f:
+    pickle.dump(image_features, f)

flagged/Text-to-Image Search Results/28b9820a-4b94-4951-8cde-6128980d10c6/captions.json

@@ -0,0 +1 @@
+{"C:\\Users\\basel\\OneDrive\\Desktop\\CLIP-Model-Image-Search\\flagged\\Text-to-Image Search Results\\28b9820a-4b94-4951-8cde-6128980d10c6\\4f98da9ec0f689294825687b767e5bd6abddd769\\image.png": null, "C:\\Users\\basel\\OneDrive\\Desktop\\CLIP-Model-Image-Search\\flagged\\Text-to-Image Search Results\\28b9820a-4b94-4951-8cde-6128980d10c6\\51731869eb38daa90d2c38be3879322cffd0e5a8\\image.png": null, "C:\\Users\\basel\\OneDrive\\Desktop\\CLIP-Model-Image-Search\\flagged\\Text-to-Image Search Results\\28b9820a-4b94-4951-8cde-6128980d10c6\\873bcc5d4e101e2df7ec1db2a29b17dc0b13f072\\image.png": null, "C:\\Users\\basel\\OneDrive\\Desktop\\CLIP-Model-Image-Search\\flagged\\Text-to-Image Search Results\\28b9820a-4b94-4951-8cde-6128980d10c6\\eb1653eec598be50fd369b3acc91857aa20a6c78\\image.png": null, "C:\\Users\\basel\\OneDrive\\Desktop\\CLIP-Model-Image-Search\\flagged\\Text-to-Image Search Results\\28b9820a-4b94-4951-8cde-6128980d10c6\\cc007a660fb213a4a5ca9b43229bc21f28fa5792\\image.png": null}

flagged/Text-to-Image Search Results/578ec4d5-4c30-46d9-99b2-de30a7bf78d0/captions.json

@@ -0,0 +1 @@
+{"C:\\Users\\basel\\OneDrive\\Desktop\\CLIP-Model-Image-Search\\flagged\\Text-to-Image Search Results\\578ec4d5-4c30-46d9-99b2-de30a7bf78d0\\00d27721ded93f7833b7b8ccc2d98bd113c8f73b\\image.png": null, "C:\\Users\\basel\\OneDrive\\Desktop\\CLIP-Model-Image-Search\\flagged\\Text-to-Image Search Results\\578ec4d5-4c30-46d9-99b2-de30a7bf78d0\\cf2a6f967f1557bc9ca891594273f74ef7347f5d\\image.png": null, "C:\\Users\\basel\\OneDrive\\Desktop\\CLIP-Model-Image-Search\\flagged\\Text-to-Image Search Results\\578ec4d5-4c30-46d9-99b2-de30a7bf78d0\\9b260c660faf1bf2cf4485aa65897526cc03d2d3\\image.png": null, "C:\\Users\\basel\\OneDrive\\Desktop\\CLIP-Model-Image-Search\\flagged\\Text-to-Image Search Results\\578ec4d5-4c30-46d9-99b2-de30a7bf78d0\\dab41f873239f5a039d53fe0d6c1d4f1f0c3034e\\image.png": null, "C:\\Users\\basel\\OneDrive\\Desktop\\CLIP-Model-Image-Search\\flagged\\Text-to-Image Search Results\\578ec4d5-4c30-46d9-99b2-de30a7bf78d0\\1f6730d26ffc4df0fea7cf4d3d8e8f2f6c6521cd\\image.png": null}

flagged/log.csv

@@ -0,0 +1,3 @@
+Text Query,Top K Results,Text-to-Image Search Results,flag,username,timestamp
+man riding a horse,5,C:\Users\basel\OneDrive\Desktop\CLIP-Model-Image-Search\flagged\Text-to-Image Search Results\578ec4d5-4c30-46d9-99b2-de30a7bf78d0,,,2023-10-27 19:01:31.140298
+man riding a horse,5,C:\Users\basel\OneDrive\Desktop\CLIP-Model-Image-Search\flagged\Text-to-Image Search Results\28b9820a-4b94-4951-8cde-6128980d10c6,,,2023-10-27 19:01:36.052210