Update app.py

app.py

@@ -32,7 +32,7 @@ def draw_results_ssd(detected, input_img, ad):
             confidence = detected[0, 0, i, 2]
 
             # filter out weak detections
-            if confidence > 0.5:
+            if confidence > 0.6:
                 # compute the (x, y)-coordinates of the bounding box for
                 # the face and extract the face ROI
                 (h0, w0) = input_img.shape[:2]
@@ -126,22 +126,26 @@ def face_detector(input_img):
     return cropped_list
 
 def predict(image):
-    print(type(image))
+    # print(type(image))
     cropped_list = face_detector(image)
-    print(cropped_list)
-    output = [None for _ in range(20)]
-    for i in range(len(cropped_list)):
-        predictions = pipe(Image.fromarray(cropped_list[i]))
-        output[int(i*2)] = Image.fromarray(cropped_list[i])
-        output[int(i*2+1)] = {p["label"]: p["score"] for p in predictions}
-        # return [output[0], output[1]]
-    return output
+    # print(cropped_list)
+    # output = [None for _ in range(20)]
+    output_img = Image.fromarray(cropped_list[i])
+    predictions = pipe(output_img)
+    return output_img, predictions
+    # for i in range(len(cropped_list)):
+    #     predictions = pipe(Image.fromarray(cropped_list[i]))
+    #     output[int(i*2)] = Image.fromarray(cropped_list[i])
+    #     output[int(i*2+1)] = {p["label"]: p["score"] for p in predictions}
+    #     # return [output[0], output[1]]
+    # return output
 
 # outputs=list(itertools.chain(*[[gr.outputs.Image(label="Image {}".format(ind)), gr.outputs.Label(num_top_classes=7, label="Result {}".format(ind))] for ind in range(10)])),
+# list(itertools.chain(*[["image", "label"] for _ in range(10)])), #Maximum number of face: 10
 gr.Interface(
     predict,
     inputs=gr.inputs.Image(label="Upload image"),
-    outputs=list(itertools.chain(*[["image", "label"] for _ in range(10)])), #Maximum number of face: 10
+    outputs=["image", "label"],
     examples=[["examples/9_peoples.jpg"], ["examples/sad.jpg"], ["examples/angry.jpg"], ["examples/surprise.jpg"]],
     title="FER trained on DiffusionFER dataset",
 ).launch()