object detection

.gitignore

@@ -0,0 +1,80 @@
+# 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
+
+# Interpreter
+.env
+
+# Unit test / coverage reports
+.coverage
+.tox
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+
+# 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
+Pipfile.lock
+
+# PyCharm
+.idea/
+.idea/*
+/object-detection/flagged/log.csv
+/object-detection/flagged/

Pipfile

@@ -0,0 +1,32 @@
+[[source]]
+url = "https://pypi.org/simple"
+verify_ssl = true
+name = "pypi"
+
+[packages]
+requests = "*"
+langchain = "*"
+black = "*"
+openai = "*"
+install = "*"
+google-search-results = "*"
+tweepy = "*"
+flask = "*"
+langchain-openai = "*"
+python-dotenv = "*"
+langchain-community = "*"
+pydantic = "==v1.10.13"
+langchain-core = "*"
+langchainhub = "*"
+pinecone-client = "*"
+gradio = "*"
+timm = "*"
+inflect = "*"
+phonemizer = "*"
+py-espeak-ng = "*"
+transformers = "*"
+
+[dev-packages]
+
+[requires]
+python_version = "3.11"

object-detection/object_detection.py

@@ -0,0 +1,68 @@
+from transformers import DetrImageProcessor, DetrForObjectDetection
+import torch
+from PIL import Image, ImageDraw, ImageFont
+import gradio as gr
+
+
+def render_result_in_image(image):
+    """
+    Render detected objects in the input image.
+
+    Args:
+        image (PIL.Image): Input image.
+
+    Returns:
+        PIL.Image: Image with bounding boxes and labels drawn.
+    """
+    processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
+    model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
+
+    inputs = processor(images=image, return_tensors="pt")
+    outputs = model(**inputs)
+
+    # convert outputs (bounding boxes and class logits) to COCO API
+    # let's only keep detections with score > 0.9
+    target_sizes = torch.tensor([image.size[::-1]])
+    results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0]
+
+    # Create id to label mapping
+    id2label = {idx: model.config.id2label[idx] for idx in range(len(model.config.id2label))}
+
+    # Render results in the image
+    rendered_image = render_result_in_image_helper(image.copy(), results, id2label)
+    return rendered_image
+
+
+def render_result_in_image_helper(image, results, id2label):
+    """
+    Helper function to render detected objects in the input image.
+
+    Args:
+        image (PIL.Image): Input image.
+        results (dict): Detection results containing 'scores', 'labels', and 'boxes'.
+        id2label (dict): Mapping from class indices to class labels.
+
+    Returns:
+        PIL.Image: Image with bounding boxes and labels drawn.
+    """
+    draw = ImageDraw.Draw(image)
+    font = ImageFont.load_default()
+
+    for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
+        # Draw bounding box
+        draw.rectangle(box.tolist(), outline="red", width=20)
+
+        # Draw label
+        label_text = f"{id2label[label.item()]}: {score:.4f}"
+        draw.text((box[0], box[1]), label_text, fill="white", font=font)
+
+    return image
+
+
+demo = gr.Interface(
+    fn=render_result_in_image,
+    inputs=gr.inputs.Image(type="pil", label="Upload Image"),
+    outputs=gr.outputs.Image(type="pil", label="Output Image with Predicted Instances")
+)
+
+demo.launch()