Updated readme and other optimization

README.md

@@ -1,5 +1,32 @@
 ---
-license: mit
 title: Shirt Detection
+colorFrom: red
+colorTo: gray
+app_file: app.py
+pinned: false
+license: mit
 sdk: gradio
----
+---
+
+# App for shirt/tshirt detection using YOLOv9
+
+## Features
+- Image input/output: Upload image and check predictions
+- Confidence Thresold: Confidence Thresold from NMS
+- IoU Thresold: IoU thresold to remove overlapping detection boxes
+
+## Usage
+- Upload an image
+- Change settings as requied
+- Hit submit and view results
+
+## Features
+- GradCAM: To understand what models has actully learned. Adjust opacity and model layer for grad-cam.
+- Miss classified images: Plot of images missclassified by model
+- Image input/output: Upload image and check predictions
+- Top classes: Show top n classes with high prediction confidence. 
+
+## Usage
+- Upload an image
+- Change settings as requied
+- Hit submit and view results

app.py

@@ -10,6 +10,9 @@ from utils.general import check_img_size, Profile, non_max_suppression, scale_bo
 
 weights = "runs/train/best_striped.pt"
 data = "data.yaml"
+# Load model
+device = select_device('cpu')
+model = DetectMultiBackend(weights, device=device, dnn=False, data=data, fp16=False)
 
 def resize_image_pil(image, new_width, new_height):
 
@@ -34,9 +37,6 @@ def resize_image_pil(image, new_width, new_height):
 
 def inference(input_img, conf_thres, iou_thres):
     im0 = input_img.copy()
-    # Load model
-    device = select_device('cpu')
-    model = DetectMultiBackend(weights, device=device, dnn=False, data=data, fp16=False)
     stride, names, pt = model.stride, model.names, model.pt
     imgsz = check_img_size((640, 640), s=stride)  # check image size
 
@@ -89,7 +89,7 @@ examples = [["image_1.jpg", 0.25, 0.45], ["image_2.jpg", 0.25, 0.45],
 
 demo = gr.Interface(inference, 
                     inputs = [gr.Image(width=320, height=320, label="Input Image"), 
-                              gr.Slider(0, 1, 0.25, label="Confidance Thresold"),
+                              gr.Slider(0, 1, 0.25, label="Confidence Threshold"),
                               gr.Slider(0, 1, 0.45, label="IoU Thresold")],
                     outputs= [gr.Image(width=640, height=640, label="Output")],
                     title=title,