v03 update

app.py

@@ -12,6 +12,7 @@ import argparse
 import csv
 import json
 import sys
+from collections import Counter
 from pathlib import Path
 import pandas as pd
 
@@ -175,6 +176,8 @@ def yolo_det(img, device, model_name, inference_size, conf, iou, max_num, model_
     s_obj, m_obj, l_obj = 0, 0, 0
     # object area list
     area_obj_all = []
+    # cls num stat
+    cls_det_stat = []
 
     if model_name_tmp != model_name:
         # Model judgment to avoid repeated loading
@@ -189,13 +192,14 @@ def yolo_det(img, device, model_name, inference_size, conf, iou, max_num, model_
     model.iou = iou # NMS IoU threshold
     model.max_det = int(max_num) # Maximum number of detection frames
     model.classes = model_cls # model classes
+    
+    img_size = img.size # frame size
 
     results = model(img, size=inference_size) # detection
     
+    # Data Frame
     dataframe = results.pandas().xyxy[0].round(2)
 
-    img_size = img.size # frame size
-
     # ----------------Load fonts----------------
     yaml_index = cls_name.index(".yaml")
     cls_name_lang = cls_name[yaml_index - 2:yaml_index]
@@ -271,7 +275,16 @@ def yolo_det(img, device, model_name, inference_size, conf, iou, max_num, model_
 
     objSize_dict = {obj_style[i]: [s_obj, m_obj, l_obj][i] / sml_obj_total for i in range(3)}
 
-    return det_img, objSize_dict, det_json, report, dataframe
+    # ------------cls stat------------
+    clsRatio_dict = {}
+    clsDet_dict = Counter(cls_det_stat)
+    clsDet_dict_sum = sum(clsDet_dict.values())
+
+    for k, v in clsDet_dict.items():
+        clsRatio_dict[k] = v / clsDet_dict_sum
+
+
+    return det_img, objSize_dict, clsRatio_dict, det_json, report, dataframe
 
 
 def main(args):
@@ -336,8 +349,9 @@ def main(args):
     outputs_pdf = gr.outputs.File(label="Download test report")
     outputs_df = gr.outputs.Dataframe(max_rows=5, overflow_row_behaviour="paginate", type="pandas", label="List of detection information")
     outputs_objSize = gr.outputs.Label(label="Object size ratio statistics")
+    outputs_clsSize = gr.outputs.Label(label="Category detection proportion statistics")
 
-    outputs = [outputs_img, outputs_objSize, outputs_json, outputs_pdf, outputs_df]
+    outputs = [outputs_img, outputs_objSize, outputs_clsSize, outputs_json, outputs_pdf, outputs_df]
 
     # title
     title = "Gradio YOLOv5 Det v0.3"