Added object detection using coco dataset with yolo v5 advanced deep learning model

Object Detection using COCO dataset with YOLO_v5 model/README.md

@@ -0,0 +1,32 @@
+# Project Title: Object Detection with YOLOv5
+
+Project Description:
+--------------------
+This project implements an object detection system using the YOLOv5 (You Only Look Once) model. YOLOv5 is a state-of-the-art, real-time object detection algorithm that is both fast and accurate. This system can detect multiple objects in images or video streams and can be further fine-tuned for custom datasets. It includes training the YOLOv5 model, evaluating it on a test dataset, and running real-time inference.
+
+Features:
+---------
+Real-time object detection on images and video streams.
+Training the YOLOv5 model on custom datasets.
+Evaluation using key metrics such as Precision, Recall, Intersection over Union (IoU), and Mean Average Precision (mAP).
+Deployment for detecting objects in images and video streams (GPU requirements for this case is much preferrable)
+Model robustness testing with image augmentations.
+
+Requirements:
+--------------
+Python 3.7+
+PyTorch 1.7+
+YOLOv5 (via the ultralytics/yolov5 repository)
+Common libraries:
+numpy
+opencv-python
+torch
+pillow
+matplotlib
+albumentations
+
+Result Demo:
+-------------
+
+![result-demo-obj-det](https://github.com/user-attachments/assets/0c5020e1-d3e7-4789-a16a-16b44f1b85af)
+

Object Detection using COCO dataset with YOLO_v5 model/gitignore.txt

@@ -0,0 +1,38 @@
+__pycache__/
+*.py[cod]
+*.so
+
+.ipynb_checkpoints/
+
+# Python virtual environments
+env/
+venv/
+
+# YOLOv5 Weights
+*.pt
+runs/
+weights/
+
+
+*.log
+
+
+*.o
+*.a
+*.out
+*.exe
+
+# Data files
+data/
+*.csv
+*.json
+
+# System files
+.DS_Store
+Thumbs.db
+
+# PyCharm/IDEA
+.idea/
+
+# Visual Studio Code
+.vscode/

Object Detection using COCO dataset with YOLO_v5 model/requirements.txt

@@ -0,0 +1,16 @@
+torch>=1.7.0
+torchvision>=0.8.0
+matplotlib>=3.2.2
+numpy>=1.18.5
+opencv-python>=4.1.2
+pillow>=7.1.2
+PyYAML>=5.3.1
+tqdm>=4.64.0
+scipy>=1.4.1
+tensorboard>=2.4.1
+seaborn>=0.11.0
+pandas>=1.1.4
+albumentations>=0.5.2
+ipython>=7.16.1
+jupyterlab>=2.1.5
+requests>=2.23.0

app (3).py

@@ -0,0 +1,22 @@
+from flask import Flask, render_template, request, jsonify
+from chat import chatbot
+
+app = Flask(__name__)
+
+
+@app.route("/")
+def hello():
+    return render_template('chat.html')
+
+@app.route("/ask", methods=['POST'])
+def ask():
+
+    message = str(request.form['messageText'])
+
+    bot_response = chatbot(message) 
+
+    return jsonify({'status':'OK','answer':bot_response})
+
+
+if __name__ == "__main__":
+    app.run()

chat (1).py

@@ -0,0 +1,26 @@
+from peft import AutoPeftModelForCausalLM
+from transformers import GenerationConfig
+from transformers import AutoTokenizer
+import torch
+tokenizer = AutoTokenizer.from_pretrained("Vasanth/mistral-finetuned-alpaca")
+
+model = AutoPeftModelForCausalLM.from_pretrained(
+    "Vasanth/mistral-finetuned-alpaca",
+    low_cpu_mem_usage=True,
+    return_dict=True,
+    torch_dtype=torch.float16,
+    device_map="cuda")
+
+generation_config = GenerationConfig(
+    do_sample=True,
+    top_k=1,
+    temperature=0.1,
+    max_new_tokens=100,
+    pad_token_id=tokenizer.eos_token_id
+)
+
+def chatbot(message):
+    input_str = "###Human: " + message + " ###Assistant: "
+    inputs = tokenizer(input_str, return_tensors="pt").to("cuda")
+    outputs = model.generate(**inputs, generation_config=generation_config)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True).replace(input_str, '')

config (1).py

@@ -0,0 +1,2 @@
+##OPEN API STUFF
+OPENAI_API_KEY = "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"