update

app.py

@@ -14,6 +14,7 @@ from huggingface_hub import HfApi
     
 def yolov7_inference(
     image: gr.inputs.Image = None,
+    video: gr.inputs.Video = None,
     model_path: gr.inputs.Dropdown = None,
     image_size: gr.inputs.Slider = 640,
     conf_threshold: gr.inputs.Slider = 0.25,
@@ -23,6 +24,7 @@ def yolov7_inference(
     YOLOv7 inference function
     Args:
         image: Input image
+        video: Input video
         model_path: Path to the model
         image_size: Image size
         conf_threshold: Confidence threshold
@@ -34,12 +36,13 @@ def yolov7_inference(
     model = yolov7.load(model_path, device="cpu", hf_model=True, trace=False)
     model.conf = conf_threshold
     model.iou = iou_threshold
-    results = model([image], size=image_size)
+    results = model([image], [video], size=image_size)
     return results.render()[0]
         
 
 inputs = [
     gr.inputs.Image(type="pil", label="Input Image"),
+    gr.inputs.Video(type="pil", label="Input Video"),
     gr.inputs.Dropdown(
         choices=[
             "alshimaa/model_baseline",
@@ -54,7 +57,7 @@ inputs = [
     #gr.inputs.Slider(minimum=0.0, maximum=1.0, default=0.45, step=0.05, label="IOU Threshold")
 ]
 
-outputs = gr.outputs.Image(type="filepath", label="Output Image")
+outputs = [gr.outputs.Image(type="filepath", label="Output Image"), gr.outputs.Video(type="filepath", label="Output Video")]
 title = "Smart Environmental Eye (SEE)"
 
 examples = [['image1.jpg', 'alshimaa/model_yolo7', 640, 0.25, 0.45], ['image2.jpg', 'alshimaa/model_yolo7', 640, 0.25, 0.45], ['image3.jpg', 'alshimaa/model_yolo7', 640, 0.25, 0.45]]