Upload app.py

app.py

@@ -0,0 +1,81 @@
+import gradio as gr
+import numpy as np
+import config
+from utils import *
+from pytorch_grad_cam.utils.image import show_cam_on_image
+from YoloV3Lightning import YOLOv3LightningModel
+
+examples = [[f'examples/100{i}.jpg'] for i in range(7)]
+scaled_anchors = config.scaled_anchors
+
+model = YOLOv3LightningModel()
+model.load_state_dict(torch.load("S13_model.pth", map_location="cpu"), strict=False)
+model.eval()
+
+@torch.inference_mode()
+def yolo_predict(image, iou_thresh=0.5, thresh=0.5):
+    transformed_image = config.transforms(image=image)["image"].unsqueeze(0)
+    output = model(transformed_image)
+    
+    bboxes = [[] for _ in range(1)]
+    for i in range(3):
+        batch_size, A, S, _, _ = output[i].shape
+        anchor = scaled_anchors[i]
+        boxes_scale_i = cells_to_bboxes(
+            output[i], anchor, S=S, is_preds=True
+        )
+        for idx, (box) in enumerate(boxes_scale_i):
+            bboxes[idx] += box
+
+    nms_boxes = non_max_suppression(
+        bboxes[0], iou_threshold=iou_thresh, threshold=thresh, box_format="midpoint",
+    )
+    plot_img = draw_bounding_boxes(image.copy(), nms_boxes, class_labels=config.PASCAL_CLASSES)
+
+    return plot_img
+
+
+
+tab1 = gr.Interface(
+    yolo_predict,
+    inputs=[
+        gr.Image(label="Input Image"),
+        gr.Slider(0, 1, value=0.5, step=0.1, label="IOU Threshold", info="Define IOU Threshold value"),
+        gr.Slider(0, 1, value=0.5, step=0.1, label="Threshold", info="Define Threshold value"),
+    ],
+    outputs=[
+        gr.Image(label="YoloV3 Object Detection"),
+    ],
+    examples=examples,
+)
+
+
+def GradCAM(image, target_layer=-5, transparency=0.5, show_cam=True):
+    if show_cam:
+        cam = YoloCAM(model=model, target_layers=[model.layers[target_layer]], use_cuda=False)
+        transformed_image = config.transforms(image=image)["image"].unsqueeze(0)
+        grayscale_cam = cam(transformed_image, scaled_anchors)[0, :, :]
+        img = cv2.resize(image, (416, 416))
+        img = np.float32(img) / 255
+        cam_image = show_cam_on_image(img, grayscale_cam, use_rgb=True, image_weight=transparency)
+    else:
+        cam_image = image
+        
+    return cam_image
+
+tab2 = gr.Interface(
+    GradCAM,
+    inputs=[
+        gr.Image(label="Input Image"),
+        gr.Slider(-5, -2, value=-3, step=-1, label="Network Layer", info="Which layer GRAD-CAM do you want to visualize?"),
+        gr.Slider(0, 1, value=0.5, step=0.1, label="Transparency", info="Define Transparency of GRAD-CAMs"), 
+        gr.Checkbox(label="GradCAM", value=True, info="Visualize Class Activation Maps?"), 
+    ],
+    outputs=[
+        gr.Image(label="GradCAM Visualization"),
+    ],
+    examples=examples,
+)
+
+demo = gr.TabbedInterface([tab1, tab2], ["YOLOV3 Detection", "GradCAM Visualization"])
+demo.launch()