Update README.md

README.md

@@ -1,17 +1,17 @@
 
 # Model Description
-This model detects dogs in images and catorgizes them into small, medium, and large based on average weight of an adult of that breed. The weight classes generall follow: less than 30lbs for small doges, between 30lbs and 50lbs for medium and greater than 50lbs for large dogs.
-Training was done by fine tunning the yolov11 model. Due to the large physical differences between dog breed, this model is intended to be used to determine counts of each type in order to better meet the needs to the group in the area.  
+This model detects dogs in images and categorizes them into small, medium, and large based on the average weight of an adult of that breed. The weight classes generally follow: less than 30lbs for small dogs, between 30 lbs and 50lbs for medium dogs, and greater than 50lbs for large dogs.
+Training was done by fine-tuning the YOLOv11 model. Due to the large physical differences between dog breeds, this model is intended to be used to determine counts of each type to better meet the needs of the group in the area.  
 ***
 # Training Data
-This model is trained using the follow roboflow dataset: [Link](https://universe.roboflow.com/igor-romanica-gmail-com/stanford-dogs-0pff9).
-The roboflow page is using a subset of the [Standford Dogs Dataset](http://vision.stanford.edu/aditya86/ImageNetDogs/). The subset consits of images of 60 breeds across 9884 images, about half the breed and image count of the orginal dataset.  
-Annotations included manually sorting each of the 60 breeds into a catagory based on weight(as detailed above). Additionally, some classes were deleted due to the large wieght ranges of the breed. For example, [Xoloitzcuintle](https://en.wikipedia.org/wiki/Xoloitzcuintle) are usually broken into three sub-breeds with different sizes but they are labeled in the dataset under one cateogry.
+This model is trained using the following Roboflow dataset: [Link](https://universe.roboflow.com/igor-romanica-gmail-com/stanford-dogs-0pff9).
+The Roboflow page is using a subset of the [Stanford Dogs Dataset](http://vision.stanford.edu/aditya86/ImageNetDogs/). The subset consists of images of 60 breeds across 9884 images, about half the breed and image count of the original dataset.  
+Annotations included manually sorting each of the 60 breeds into a category based on weight (as detailed above). Additionally, some classes were deleted due to the large weight ranges of the breed. For example, [Xoloitzcuintles](https://en.wikipedia.org/wiki/Xoloitzcuintle) are usually broken into three sub-breeds with different sizes, but they are labeled in the dataset under one category.
 
 ### *Class Breakdown*
 | Metric | Small  | Medium   | Large |
 |--------|--------|----------|------ |
-| Percent|   39%  |   37%    |   24% |
+| Percent |  39%  |   37%    |   24% |
 | Count  | 4,058  | 3,860    | 2,524 |
 
 ### *Training Split*
@@ -25,7 +25,7 @@ Annotations included manually sorting each of the 60 breeds into a catagory base
 * Trained on Google Collab using A100
 * Limited to 200 epochs and 100 patience
 * Ran for 73 epochs, best at 63
-* 4.9 Hours training on ~24k images
+* 4.9 hours of training on ~24k images
   * 10k base
   * 14k augmented on exposure and blur 
 ***
@@ -47,13 +47,14 @@ Less than a .04 difference between classes for each metric.
 ### *Visualizations*
 <img alt="Confusion Matrix" src="https://huggingface.co/cvtechniques/DogTypeDetection/resolve/main/confusion_matrix_normalized.png" width="700"></img>
 <img alt="F1-Confidence Graph" src="https://huggingface.co/cvtechniques/DogTypeDetection/resolve/main/BoxF1_curve.png" width="700"></img>
-<img alt="Precsiosn-Confidence Graph" src="https://huggingface.co/cvtechniques/DogTypeDetection/resolve/main/BoxP_curve.png"></img>
+<img alt="Precsiosn-Confidence Graph" src="https://huggingface.co/cvtechniques/DogTypeDetection/resolve/main/BoxP_curve.png" width="700"></img>
 ### *Performance Analysis*
 
-This model had high metrics across each of the classes, meeting the success threshold in precision, recall and F1 score. The confusion matrics shows some slight over guessing, as each of the classes had a 25% to 40% rates of being prediceted when that area was actual background. The model also predicted small dogs as large dogs 10% of the time, which was right at the limit set before training. That being said, the matrix still has high values of 80%-85% along the true postive diagonal. The 100% precioson peak at 
+This model had high metrics across each of the classes, meeting the success threshold in precision, recall, and F1 score. The confusion matrix shows some slight overguessing, as each of the classes had a 25% to 40% rate of being predicted when that area was actual background. The model also predicted small dogs as large dogs 10% of the time, which was right at the limit set before training. That being said, the matrix still has high values of 80%-85% along the true positive diagonal. The 100% precision peak at 100% confidence does raise some red flags. This is addressed in the *Known failure cases* section.
 ***
 # Limitations and Biases
 ### *Known failure cases*
+
 ### *Poor performing classes*
 ### *Data biases*
 ### *Environmental/contextual limitations*