Update README.md

README.md

@@ -7,8 +7,6 @@ tags:
 - computer-vision
 - object-detection
 - pytorch
-- object detection
-- distance-estimation
 library_name: ultralytics
 library_version: 8.0.43
 inference: true
@@ -20,9 +18,8 @@ model-index:
     metrics:
     - type: precision
       value: 0.50setup environment python setup.py
-
 datasets:
-- foddu/kitti_vehicle_distance_estimation
+- keremberke/nfl-object-detection
 language:
 - en
 metrics:
@@ -30,26 +27,26 @@ metrics:
 pipeline_tag: object-detection
 ---
 
-# Model Card for YOLOv5 distance estimation
+# Model Card for YOLOv5 object detection
 
 ## Model Summary
 
-The YOLOv5 Tobject Detection and distance estimation model is an object detection and distance estimation model based on the YOLO (You Only Look Once) framework. It is designed to detect object and distance estimate, whether they are object detect, in images and video. The model has been fine-tuned on a vast dataset and achieved high accuracy in detecting tables and distinguishing between object detect and distance estimation ones.
+The YOLOv5  object Detection model is an object detection model based on the YOLO (You Only Look Once) framework. It is designed to detect object, whether they are object detect, in images. The model has been fine-tuned on a vast dataset and achieved high accuracy in detecting tables and distinguishing between object detect ones.
 
 ## Model Details
 
 ### Model Description
-The YOLOv5 Object Detection and distance estimation model serves as a versatile solution for precisely identifying object and distance within images and video, whether they exhibit a object detect and distance. Notably, this model's capabilities extend beyond mere detection – it plays a crucial role for object detection and distance estimation. By employing advanced techniques such as object detection.
+The YOLOv5 Object Detection model serves as a versatile solution for precisely identifying object detect within images, whether they exhibit a object detect. Notably, this model's capabilities extend beyond mere detection – it plays a crucial role for object detection. By employing advanced techniques such as object detection.
 
 
-We invite you to explore the potential of this model and its object detection capabilities. For those interested in harnessing its power or seeking further collaboration, we encourage you to reach out to us at [email protected]. Whether you require assistance, customization, or have innovative ideas, our collaborative approach is geared towards addressing your unique challenges. Additionally, you can actively engage with our vibrant community section for valuable insights and collective problem-solving. Your input drives our continuous improvement, as we collectively pave the way towards enhanced object detection and distance estimation.
+We invite you to explore the potential of this model and its object detection capabilities. For those interested in harnessing its power or seeking further collaboration, we encourage you to reach out to us at [email protected]. Whether you require assistance, customization, or have innovative ideas, our collaborative approach is geared towards addressing your unique challenges. Additionally, you can actively engage with our vibrant community section for valuable insights and collective problem-solving. Your input drives our continuous improvement, as we collectively pave the way towards enhanced object detection.
 
 - **Developed by:** FODUU AI
 - **Model type:** Object Detection
-- **Task:** Object Detection (object detection and distance estimation)
+- **Task:** Object Detection (object detection)
 
 Furthermore, the YOLOv5  Detection model is limited to object detectionsetup environment python setup.py
- and opencv distance estimation model alone. It is a versatile tool that contributes to the processing of structured image data. By utilizing advanced box techniques, the model empowers users to isolate object within the image visual data. What sets this model apart is its seamless integration with object detection technology. The combination of box information and distance estimation allows for precise object detection from the data. This comprehensive approach streamlines the process of information retrieval from image data.
+yolov5 object detection model alone. It is a versatile tool that contributes to the processing of structured image data. By utilizing advanced box techniques, the model empowers users to isolate object within the image visual data. What sets this model apart is its seamless integration with object detection technology. The combination of box information allows for precise object detection from the data. This comprehensive approach streamlines the process of information retrieval from image data.
 
 User collaboration is actively encouraged to enrich the model's capabilities. By contributing table images of different designs and types, users play a pivotal role in enhancing the model's ability to detect a diverse range of object accurately. Community participation can be facilitated through our platform or by reaching out to us at [email protected]. We value collaborative efforts that drive continuous improvement and innovation in object detection.
 
@@ -63,26 +60,24 @@ User collaboration is actively encouraged to enrich the model's capabilities. By
 
 ### Direct Use
 
-The YOLOv5 and opencv for object Detection and distance estimation model can be directly used for detecting object from images, whether they are bordered box.
+The YOLOv5 and opencv for object Detection  model can be directly used for detecting object from images, whether they are bordered box.
 
 ### Downstream Use
 
-The model can also be fine-tuned for specific object detection and distance estimation tasks or integrated into larger applications for distance measure, image-based object detection, and other related fields.
+The model can also be fine-tuned for specific object detection tasks or integrated into larger applications for distance measure, image-based object detection, and other related fields.
 
 ### Limitations:
 Performance Dependence on Training Data: The model's performance heavily relies on the quality, quantity, and diversity of the training data. Inaccuracies in object detection and distance estimation may arise when encountering object types, lighting conditions, or environments that significantly differ from the training data.
 
 Complex Object Arrangements: The model's accuracy may decrease when detecting objects within cluttered or complex scenes. It might struggle to accurately estimate distances for objects that are partially occluded or located behind other objects.
 
-Size and Distance Constraints: Accurate distance estimation requires objects with well-defined dimensions and significant visibility. The model's distance estimation accuracy may diminish for very small objects or those located at extreme distances from the camera.
-
 ### Biases:
 Training Data Bias: Biases present in the training data, such as object type distribution, camera viewpoints, and lighting conditions, could lead to differential performance across various scenarios. For instance, the model might exhibit better accuracy for object types more heavily represented in the training data.
 
 ### Risks:
 Privacy Concerns: The model processes images, potentially capturing sensitive or private information. Deploying the model in contexts where privacy is a concern may inadvertently expose sensitive data, raising ethical and legal issues.
 
-Safety Considerations: Users should exercise caution when relying solely on the model's outputs for critical decision-making. The model may not account for all safety hazards, obstacles, or dynamic environmental changes that could impact real-time distance estimation.
+Safety Considerations: Users should exercise caution when relying solely on the model's outputs for critical decision-making. The model may not account for all safety hazards, obstacles, or dynamic environmental changes that could impact real-time object detect.
 
 ### Recommendations
 
@@ -105,7 +100,7 @@ pip install -U yolov5
 import yolov5
 
 # load model
-model = yolov5.load('foduucom/object_distance_estimation')
+model = yolov5.load('foduucom/object_detection')
   
 # set model parameters
 model.conf = 0.25  # NMS confidence threshold
@@ -139,7 +134,7 @@ results.save(save_dir='results/')
 - Finetune the model on your custom dataset:
 
 ```bash
-yolov5 train --data dataset.yaml --img 640 --batch -1 --weights foduucom/object_distance_estimation --epochs 10
+yolov5 train --data dataset.yaml --img 640 --batch -1 --weights foduucom/object_detection--epochs 10
 ```
 
 
@@ -163,8 +158,7 @@ For inquiries and contributions, please contact us at [email protected].
 @ModelCard{
   author    = {Nehul Agrawal and
                Rahul parihar},
-  title     = {YOLOv5 object Detection and distance estimation},
+  title     = {YOLOv5 object Detection},
   year      = {2023}
 }
-``` YOLOv5
-
+``` YOLOv5