更新算法

chatgpt_detector_model_predict.py

@@ -34,7 +34,7 @@ batch_size = 32
 # model_name = "drop_aigc_model_2"
 # model_name = "drop_aigc_model_3"
 # model_name = "/home/majiahui/project/models-llm/aigc_check_10"
-model_name_sentence = "/home/majiahui/project/models-llm/weipu_aigc_512_11"
+model_name_sentence = "/home/majiahui/project/models-llm/weipu_aigc_512_8"
 model_name_short = "/home/majiahui/project/models-llm/weipu_aigc_512_5"
 pantten_biaoti_0 = '^[1-9一二三四五六七八九ⅠⅡⅢⅣⅤⅥⅦⅧⅨ][、.]\s{0,}?[\u4e00-\u9fa5a-zA-Z]+'
 pantten_biaoti_1 = '^第[一二三四五六七八九]章\s{0,}?[\u4e00-\u9fa5a-zA-Z]+'
@@ -109,21 +109,21 @@ def model_preidct(model, text):
     output = torch.sigmoid(output[0]).tolist()
     print(output)
 
-    if model_name_sentence == "drop_aigc_model_2":
-        return_list = {
-            "humen": output[0][1],
-            "robot": output[0][0]
-        }
-    elif model_name_sentence == "AIGC_detector_zhv2":
-        return_list = {
-            "humen": output[0][0],
-            "robot": output[0][1]
-        }
-    else:
-        return_list = {
-            "humen": output[0][0],
-            "robot": output[0][1]
-        }
+    # if model_name_sentence == "drop_aigc_model_2":
+    #     return_list = {
+    #         "humen": output[0][1],
+    #         "robot": output[0][0]
+    #     }
+    # elif model_name_sentence == "AIGC_detector_zhv2":
+    #     return_list = {
+    #         "humen": output[0][0],
+    #         "robot": output[0][1]
+    #     }
+    # else:
+    return_list = {
+        "humen": output[0][0],
+        "robot": output[0][1]
+    }
 
     return return_list
 
@@ -179,20 +179,20 @@ def main(content_list: list):
         reference_bool = is_reference_sentence(sentence)
 
         if reference_bool == False:
-            if res["robot"] > 0.9:
+            if res["robot"] > 0.87:
                 for _ in range(len(sentence)):
                     gpt_score_list.append(res["robot"])
                 gpt_score_sentence_list.append(res["robot"])
                 sim_word += len(sentence)
                 gpt_content.append(
                     "<em class=\"similar\" id='score_{}'>".format(str(i)) + sentence + "\n" + "</em>")
-            elif 0.9 >= res["robot"] > 0.5:
-                for _ in range(len(sentence)):
-                    gpt_score_list.append(res["robot"])
-                gpt_score_sentence_list.append(res["robot"])
-                sim_word_5_9 += len(sentence)
-                gpt_content.append(
-                    "<em class=\"color-gold\" id='score_{}'>".format(str(i)) + sentence + "\n" + "</em>")
+            # elif 0.9 >= res["robot"] > 0.5:
+            #     for _ in range(len(sentence)):
+            #         gpt_score_list.append(res["robot"])
+            #     gpt_score_sentence_list.append(res["robot"])
+            #     sim_word_5_9 += len(sentence)
+            #     gpt_content.append(
+            #         "<em class=\"color-gold\" id='score_{}'>".format(str(i)) + sentence + "\n" + "</em>")
             else:
                 for _ in range(len(sentence)):
                     gpt_score_list.append(0)
@@ -287,4 +287,4 @@ def classify():  # 调用模型，设置最大batch_size
 
 if __name__ == '__main__':
     t = Thread(target=classify)
-    t.start()
+    t.start()