From 112aace08718ad0ead624286fe09e4bf941dee5a Mon Sep 17 00:00:00 2001
From: zhm <839713154@qq.com>
Date: 星期五, 25 七月 2025 14:16:33 +0800
Subject: [PATCH] 预警跟图片描述修改--修改检测内容
---
qwen_thread.py | 296 ++++++++--------------------------------------------------
1 files changed, 43 insertions(+), 253 deletions(-)
diff --git a/qwen_thread.py b/qwen_thread.py
index 3673dcd..4c3a1d6 100644
--- a/qwen_thread.py
+++ b/qwen_thread.py
@@ -1,18 +1,16 @@
+import logging
import time
from concurrent.futures import ThreadPoolExecutor
import threading
-
import torch
from PIL import Image
from pymilvus import connections, Collection
from datetime import datetime
-import os
import requests
import asyncio
-import logging
import re
-from logging.handlers import RotatingFileHandler
+from qwen_vl_utils import process_vision_info
from transformers import AutoModelForVision2Seq, AutoProcessor
@@ -29,18 +27,22 @@
# 鍔犺浇闆嗗悎
self.collection = Collection(name="smartobject")
self.collection.load()
-
+ if config.get('cuda') is None or config.get('cuda') == '0':
+ self.device = f"cuda"
+ else:
+ self.device = f"cuda:{config.get('cuda')}"
self.model_pool = []
- self.lock_pool = [threading.Lock() for _ in range(int(config.get("threadnum")))]
- for i in range(int(config.get("threadnum"))):
+ self.lock_pool = [threading.Lock() for _ in range(int(config.get("qwenwarning")))]
+ for i in range(int(config.get("qwenwarning"))):
model = AutoModelForVision2Seq.from_pretrained(
config.get("qwenaddr"),
- device_map=f"cuda:{config.get('cuda')}",
+ device_map=self.device,
trust_remote_code=True,
use_safetensors=True,
torch_dtype=torch.float16
).eval()
+ model = model.to(self.device)
self.model_pool.append(model)
# 鍏变韩鐨勫鐞嗗櫒 (绾跨▼瀹夊叏)
@@ -69,44 +71,24 @@
def tark_do(self,res,ragurl,rag_mode,max_tokens):
try:
- # 1. 浠庨泦鍚圓鑾峰彇鍚戦噺鍜屽厓鏁版嵁
- is_waning = 0
- is_desc = 2
-
# 鐢熸垚鍥剧墖鎻忚堪
ks_time = datetime.now()
- desc = self.image_desc(res)
- desc_time = datetime.now() - ks_time
- current_time = datetime.now()
+
risk_description = ""
suggestion = ""
- # 鍥剧墖鎻忚堪鐢熸垚鎴愬姛
- if desc:
- is_desc = 2
- # 璋冪敤瑙勫垯鍖归厤鏂规硶,鍒ゆ柇鏄惁棰勮
- is_waning = self.image_rule_chat(desc, res['waning_value'], ragurl,rag_mode,max_tokens)
- # 濡傛灉棰勮,鍒欑敓鎴愰殣鎮ｆ弿杩板拰澶勭悊寤鸿
- if is_waning == 1:
- # 鑾峰彇瑙勭珷鍒跺害鏁版嵁
- filedata = self.get_filedata(res['waning_value'],res['suggestion'], ragurl)
- # 鐢熸垚闅愭偅鎻忚堪
- risk_description = self.image_rule_chat_with_detail(filedata, res['waning_value'], ragurl,rag_mode,max_tokens)
- # 鐢熸垚澶勭悊寤鸿
- suggestion = self.image_rule_chat_suggestion(filedata, res['waning_value'], ragurl,rag_mode,max_tokens)
- else:
- is_desc = 3
-
- # 鏁版嵁缁�
+ # 璋冪敤瑙勫垯鍖归厤鏂规硶,鍒ゆ柇鏄惁棰勮
+ is_waning = self.image_rule(res)
+ self.logger.info(f"棰勮瑙勫垯瑙勫垯瑙勫垯is_waning锛歿is_waning}")
+ #鏇存柊鏁版嵁鐨勯璀︾粨鏋滀笌鏁版嵁棰勮鐘舵��
data = {
- "id": res['id'],
"event_level_id": res['event_level_id'], # event_level_id
"event_level_name": res['event_level_name'], # event_level_id
"rule_id": res["rule_id"],
"video_point_id": res['video_point_id'], # video_point_id
"video_point_name": res['video_point_name'],
"is_waning": is_waning,
- "is_desc": is_desc,
- "zh_desc_class": desc, # text_vector
+ "is_desc": 5, #鏀逛负宸茬粡棰勮
+ "zh_desc_class": res['zh_desc_class'], # text_vector
"bounding_box": res['bounding_box'], # bounding_box
"task_id": res['task_id'], # task_id
"task_name": res['task_name'], # task_id
@@ -122,234 +104,67 @@
"suggestion": suggestion,
"knowledge_id": res['knowledge_id']
}
-
+ self.collection.delete(f"id == {res['id']}")
# 淇濆瓨鍒癿ilvus
- image_id = self.collection.upsert(data).primary_keys
- data = {
- "id": str(image_id[0]),
- "video_point_id": res['video_point_id'],
- "video_path": res["video_point_name"],
- "zh_desc_class": desc,
- "detect_time": res['detect_time'],
- "image_path": f"{res['image_path']}",
- "task_name": res["task_name"],
- "event_level_name": res["event_level_name"],
- "rtsp_address": f"{res['video_path']}"
- }
- # 璋冪敤rag
- asyncio.run(self.insert_json_data(ragurl, data))
- rag_time = datetime.now() - current_time
- self.logger.info(f"{res['video_point_id']}鎵ц瀹屾瘯锛歿image_id}杩愯缁撴潫鎬讳綋鐢ㄦ椂:{datetime.now() - ks_time},鍥剧墖鎻忚堪鐢ㄦ椂{desc_time}锛孯AG鐢ㄦ椂{rag_time}")
+ image_id = self.collection.insert(data).primary_keys
+ res['id'] = image_id[0]
+ self.logger.info(f"{res['video_point_id']}棰勮鎵ц瀹屾瘯锛歿image_id}杩愯缁撴潫鎬讳綋鐢ㄦ椂:{datetime.now() - ks_time}")
+ return None
except Exception as e:
self.logger.info(f"绾跨▼锛氭墽琛屾ā鍨嬭В鏋愭椂鍑洪敊::{e}")
return 0
- def image_desc(self, res_data):
+ def image_rule(self, res_data):
+ self.logger.info(f"棰勮瑙勫垯瑙勫垯瑙勫垯绛夌骇鍒嗙被灏辨槸鎵撹缂濆灏戠Н鍒�")
try:
model, lock = self._acquire_model()
-
image = Image.open(res_data['image_desc_path']).convert("RGB").resize((600, 600), Image.Resampling.LANCZOS)
+
messages = [
{
"role": "user",
"content": [
- {
- "type": "image",
- },
- {"type": "text", "text": "璇疯缁嗘弿杩板浘鐗囦腑鐨勭洰鏍囦俊鎭強鐗瑰緛銆傝繑鍥炴牸寮忎负鏁存鏂囧瓧鎻忚堪"},
+ {"type": "image", "image": image},
+ {"type": "text", "text": f"璇锋娴嬪浘鐗囦腑鏄惁{res_data['waning_value']}?璇峰洖绛攜es鎴杗o"},
],
}
]
+
# Preparation for inference
text = self.processor.apply_chat_template(
- messages, add_generation_prompt=True
+ messages, tokenize=False, add_generation_prompt=True
)
+ image_inputs, video_inputs = process_vision_info(messages)
inputs = self.processor(
text=[text],
- images=[image],
+ images=image_inputs,
+ videos=video_inputs,
padding=True,
return_tensors="pt",
)
inputs = inputs.to(model.device)
- with torch.inference_mode():
- outputs = model.generate(**inputs,max_new_tokens=100)
+
+ with torch.no_grad():
+ outputs = model.generate(**inputs, max_new_tokens=10)
generated_ids = outputs[:, len(inputs.input_ids[0]):]
image_text = self.processor.batch_decode(
generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True
)
+
image_des = (image_text[0]).strip()
- return image_des
+ upper_text = image_des.upper()
+ self.logger.info(f"棰勮瑙勫垯瑙勫垯瑙勫垯锛歿upper_text}")
+ if "YES" in upper_text:
+ return 1
+ else:
+ return 0
except Exception as e:
self.logger.info(f"绾跨▼锛氭墽琛屽浘鐗囨弿杩版椂鍑洪敊:{e}")
+ return 0
finally:
# 4. 閲婃斁妯″瀷
self._release_model(model)
torch.cuda.empty_cache()
-
- def get_rule(self,ragurl):
- try:
- rule_text = None
- search_data = {
- "collection_name": "smart_rule",
- "query_text": "",
- "search_mode": "hybrid",
- "limit": 100,
- "weight_dense": 0.7,
- "weight_sparse": 0.3,
- "filter_expr": "",
- "output_fields": ["text"]
- }
- response = requests.post(ragurl + "/search", json=search_data)
- results = response.json().get('results')
- rule_text = ""
- ruleid = 1
- for rule in results:
- if rule['score'] >= 0:
- rule_text = rule_text + str(ruleid) + ". " + rule['entity'].get('text') + ";\n"
- ruleid = ruleid + 1
- # self.logger.info(len(rule_text))
- else:
- self.logger.info(f"绾跨▼锛氭墽琛岃幏鍙栬鍒欐椂鍑洪敊:{response}")
- return rule_text
- except Exception as e:
- self.logger.info(f"绾跨▼锛氭墽琛岃幏鍙栬鍒欐椂鍑洪敊:{e}")
- return None
-
- def image_rule_chat(self, image_des,rule_text, ragurl, rag_mode,max_tokens):
- try:
- content = (
- f"鍥剧墖鎻忚堪鍐呭涓猴細\n{image_des}\n瑙勫垯鍐呭锛歕n{rule_text}銆俓n璇烽獙璇佸浘鐗囨弿杩颁腑鏄惁鏈夌鍚堣鍒欑殑鍐呭锛屼笉杩涜鎺ㄧ悊鍜宼hink銆傝繑鍥炵粨鏋滄牸寮忎负[xxx绗﹀悎鐨勮鍒檌d]锛屽鏋滄病鏈夎繑鍥瀃]")
- #self.logger.info(len(content))
- search_data = {
- "prompt": "",
- "messages": [
- {
- "role": "user",
- "content": content
- }
- ],
- "llm_name": rag_mode,
- "stream": False,
- "gen_conf": {
- "temperature": 0.7,
- "max_tokens": max_tokens
- }
- }
- response = requests.post(ragurl + "/chat", json=search_data)
- results = response.json().get('data')
- # self.logger.info(results)
- ret = re.sub(r'<think>.*?</think>', '', results, flags=re.DOTALL)
- ret = ret.replace(" ", "").replace("\t", "").replace("\n", "")
- is_waning = 0
- if len(ret) > 2:
- is_waning = 1
- return is_waning
- except Exception as e:
- self.logger.info(f"绾跨▼锛氭墽琛岃鍒欏尮閰嶆椂鍑洪敊:{image_des, rule_text, ragurl, rag_mode,e}")
- return None
-
- # 闅愭偅鎻忚堪
- def image_rule_chat_with_detail(self,filedata, rule_text, ragurl, rag_mode,max_tokens):
- # API璋冪敤
- content = (
- f"瑙勭珷鍒跺害涓猴細[{filedata}]\n杩濆弽鍐呭涓猴細[{rule_text}]\n璇锋煡璇㈣繚鍙嶅唴瀹瑰湪瑙勭珷鍒跺害涓殑瀹夊叏闅愭偅锛屼笉杩涜鎺ㄧ悊鍜宼hink锛岃繑鍥炵畝鐭殑鏂囧瓧淇℃伅")
- # self.logger.info(len(content))
- search_data = {
- "prompt": "",
- "messages": [
- {
- "role": "user",
- "content": content
- }
- ],
- "llm_name": rag_mode,
- "stream": False,
- "gen_conf": {
- "temperature": 0.7,
- "max_tokens": max_tokens
- }
- }
- response = requests.post(ragurl + "/chat", json=search_data)
- # 浠巎son鎻愬彇data瀛楁鍐呭
- ret = response.json()["data"]
- # 绉婚櫎<think>鏍囩鍜屽唴瀹�
- ret = re.sub(r'<think>.*?</think>', '', ret, flags=re.DOTALL)
- # 瀛楃涓叉竻鐞�,绉婚櫎绌烘牸,鍒惰〃绗�,鎹㈣绗�,鏄熷彿
- ret = ret.replace(" ", "").replace("\t", "").replace("\n", "").replace("**","")
- #print(f"瀹夊叏闅愭偅:{ret}")
- return ret
- #澶勭悊寤鸿
- def image_rule_chat_suggestion(self,filedata, rule_text, ragurl, rag_mode,max_tokens):
- # 璇锋眰鍐呭
- content = (
- f"瑙勭珷鍒跺害涓猴細[{filedata}]\n杩濆弽鍐呭涓猴細[{rule_text}]\n璇锋煡璇㈣繚鍙嶅唴瀹瑰湪瑙勭珷鍒跺害涓殑澶勭悊寤鸿锛屼笉杩涜鎺ㄧ悊鍜宼hink锛岃繑鍥炵畝鐭殑鏂囧瓧淇℃伅")
- response = requests.post(
- # ollama鍦板潃
- url=f"{ragurl}/chat",
- json={
- # 鎸囧畾妯″瀷
- "llm_name": rag_mode,
- "messages": [
- {"role": "user", "content": content}
- ],
- "stream": False, # 鍏抽棴娴佸紡杈撳嚭
- "gen_conf": {
- "temperature": 0.7,
- "max_tokens": max_tokens
- }
- }
- )
- # 浠巎son鎻愬彇data瀛楁鍐呭
- ret = response.json()["data"]
- # 绉婚櫎<think>鏍囩鍜屽唴瀹�
- ret = re.sub(r'<think>.*?</think>', '', ret, flags=re.DOTALL)
- # 瀛楃涓叉竻鐞�,绉婚櫎绌烘牸,鍒惰〃绗�,鎹㈣绗�,鏄熷彿
- ret = ret.replace(" ", "").replace("\t", "").replace("\n", "").replace("**","")
- #print(f"澶勭悊寤鸿:{ret}")
- return ret
-
- # RAG鏈嶅姟鍙戦�佽姹�,鑾峰彇鐭ヨ瘑搴撳唴瀹�
- def get_filedata(self, searchtext,filter_expr, ragurl):
- search_data = {
- # 鐭ヨ瘑搴撻泦鍚�
- "collection_name": "smart_knowledge",
- # 鏌ヨ鏂囨湰
- "query_text": searchtext,
- # 鎼滅储妯″紡
- "search_mode": "hybrid",
- # 鏈�澶氳繑鍥炵粨鏋�
- "limit": 10,
- # 璋冨瘑鍚戦噺鎼滅储鏉冮噸
- "weight_dense": 0.9,
- # 绋�鐤忓悜閲忔悳绱㈡潈閲�
- "weight_sparse": 0.1,
- # 绌哄瓧绗︿覆
- "filter_expr": f"docnm_kwd in {filter_expr}",
- # 鍙繑鍥� text 瀛楁
- "output_fields": ["text"]
- }
- #print(search_data)
- # 鍚� ragurl + "/search" 绔偣鍙戦�丳OST璇锋眰
- response = requests.post(ragurl + "/search", json=search_data)
- # 浠庡搷搴斾腑鑾峰彇'results'瀛楁
- results = response.json().get('results')
- # 鍒濆鍖� text
- text = ""
- # 閬嶅巻鎵�鏈夌粨鏋滆鍒�(rule)锛屽皢姣忔潯瑙勫垯鐨�'entity'涓殑'text'瀛楁鍙栧嚭.
- for rule in results:
- text = text + rule['entity'].get('text') + ";\n"
- #print(text)
- return text
-
- async def insert_json_data(self, ragurl, data):
- try:
- data = {'collection_name': "smartrag", "data": data, "description": ""}
- requests.post(ragurl + "/insert_json_data", json=data, timeout=(0.3, 0.3))
- #self.logger.info(f"璋冪敤褰曞儚鏈嶅姟:{ragurl, data}")
- except Exception as e:
- #self.logger.info(f"{self._thread_name}绾跨▼锛氳皟鐢ㄥ綍鍍忔椂鍑洪敊:鍦板潃锛歿ragurl}锛歿e}")
- return
-
def _release_semaphore(self, future):
self.semaphore.release()
#self.logger.info(f"閲婃斁绾跨▼ (鍓╀綑绌洪棽: {self.semaphore._value}/{self.max_workers})")
@@ -376,29 +191,4 @@
self.lock_pool[i].release()
break
-
- def remove_duplicate_lines(self,text):
- seen = set()
- result = []
- for line in text.split('銆�'): # 鎸夊彞鍙峰垎鍓�
- if line.strip() and line not in seen:
- seen.add(line)
- result.append(line)
- return '銆�'.join(result)
- def remove_duplicate_lines_d(self,text):
- seen = set()
- result = []
- for line in text.split(','): # 鎸夊彞鍙峰垎鍓�
- if line.strip() and line not in seen:
- seen.add(line)
- result.append(line)
- return '銆�'.join(result)
- def remove_duplicate_lines_n(self,text):
- seen = set()
- result = []
- for line in text.split('\n'): # 鎸夊彞鍙峰垎鍓�
- if line.strip() and line not in seen:
- seen.add(line)
- result.append(line)
- return '銆�'.join(result)
--
Gitblit v1.8.0