detect cleanup

.gitignore

@@ -1,2 +1,3 @@
 __pycache__/
-*.sh
+*.sh
+*.pt

app.py

@@ -1,9 +1,9 @@
 import gradio as gr
 from PIL import Image,ImageDraw, ImageFont
 import sys
-import os
 import torch
 from util import Detection
+import os
 
 face_model = os.environ.get('FACE_MODEL')
 age_model = os.environ.get('AGE_MODEL')
@@ -24,7 +24,7 @@ roboto_font = ImageFont.truetype("Roboto-Regular.ttf")
 
 def run_yolo(img):
 
-    img_path = img.name # ["name"]
+    img_path = img.name
     img0 = Image.open(img_path).convert("RGB")
     draw = ImageDraw.Draw(img0)
 
@@ -56,7 +56,8 @@ def run_yolo(img):
 
     return img0
 
-inputs = gr.inputs.Image(type='file', label="Input Image")
+
+inputs = gr.inputs.Image(type='filepath', label="Input Image")
 outputs = gr.outputs.Image(type="pil", label="Output Image")
 
 title = "AgeGuesser"

yolov5/detect.py

@@ -251,7 +251,7 @@ def predict(
         augment=False,  # augmented inference
         visualize=False,  # visualize features
         update=False,  # update all models
-        project=ROOT / 'runs/detect',  # save results to project/name
+        project=None,  # save results to project/name
         name='exp',  # save results to project/name
         exist_ok=False,  # existing project/name ok, do not increment
         line_thickness=3,  # bounding box thickness (pixels)
@@ -267,20 +267,9 @@ def predict(
 
     save_dir = None
     save_path = None
-    # save_img = not nosave and not source.endswith('.txt')  # save inference images
-    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
-    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
-    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
-    
-    # Directories
-    if project is not None:
-        save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
-        (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
 
     dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
-    #bs = 1  # batch_size
-    #vid_path, vid_writer = [None] * bs, [None] * bs
-
+    
     # Run inference
 
     dt, seen = [0.0, 0.0, 0.0], 0
@@ -299,7 +288,7 @@ def predict(
         dt[0] += t2 - t1
 
         # Inference
-        visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
+        visualize = False
         pred = model(im, augment=augment, visualize=visualize)
         t3 = time_sync()
         dt[1] += t3 - t2
@@ -308,34 +297,16 @@ def predict(
         pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
         dt[2] += time_sync() - t3
 
-        # Second-stage classifier (optional)
-        # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
-
         # Process predictions
         preds = []
         for i, det in enumerate(pred):  # per image
-            seen += 1
-            if webcam:  # batch_size >= 1
-                p, im0, frame = path[i], im0s[i].copy(), dataset.count
-                s += f'{i}: '
-            else:
-                p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
-
-            p = Path(p)  # to Path
             
-            #s += '%gx%g ' % im.shape[2:]  # print string
-            # gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
-            #imc = im0.copy() if save_crop else im0  # for save_crop
-            #annotator = Annotator(im0, line_width=line_thickness, example=str(names))
+            p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
+            
             if len(det):
                 # Rescale boxes from img_size to im0 size
                 det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
 
-                # Print results
-                """ for c in det[:, -1].unique():
-                    n = (det[:, -1] == c).sum()  # detections per class
-                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string """
-
                 for *xyxy, conf, cls in reversed(det):
                     face = im0[int(xyxy[1]):int(xyxy[3]),int(xyxy[0]):int(xyxy[2])]
                     face_img = cv2.cvtColor(face, cv2.COLOR_BGR2RGB)
@@ -344,8 +315,7 @@ def predict(
                         y = age_model(im)
                     
                     age = y[0]
-                    print(age)
-                    # xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
+
                     preds.append({"class": str(int(age)), "xmin": int(xyxy[0]), "ymin": int(xyxy[1]), "xmax": int(xyxy[2]),"ymax": int(xyxy[3]), "conf": float(conf)})
                     
         yield preds, save_path