From 77ccbf7c7ced63b6f656e70378b0d8386e4b92c5 Mon Sep 17 00:00:00 2001
From: shidong <shidong@jhsoft.cc>
Date: 星期二, 22 七月 2025 14:05:14 +0800
Subject: [PATCH] #2025/7/22 #修正图片描述的赋值
---
qwen_thread.py | 343 ++++++++++++++++++++++++++++++++++++++++++--------------
1 files changed, 254 insertions(+), 89 deletions(-)
diff --git a/qwen_thread.py b/qwen_thread.py
index 56ba944..f1cb6e0 100644
--- a/qwen_thread.py
+++ b/qwen_thread.py
@@ -1,71 +1,59 @@
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
class qwen_thread:
- def __init__(self, max_workers,config,model_path):
- self.executor = ThreadPoolExecutor(max_workers=max_workers)
- self.semaphore = threading.Semaphore(max_workers)
- self.max_workers = max_workers
+ def __init__(self, config,logger):
+ self.config = config
+ self.max_workers = int(config.get("threadnum"))
+ self.executor = ThreadPoolExecutor(max_workers=int(config.get("threadnum")))
+ self.semaphore = threading.Semaphore(int(config.get("threadnum")))
+ self.logger = logger
+
# 鍒濆鍖朚ilvus闆嗗悎
connections.connect("default", host=config.get("milvusurl"), port=config.get("milvusport"))
# 鍔犺浇闆嗗悎
self.collection = Collection(name="smartobject")
self.collection.load()
-
- self.config = config
+ if config.get('cuda') == 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(max_workers)]
- for i in range(max_workers):
+ self.lock_pool = [threading.Lock() for _ in range(int(config.get("threadnum")))]
+ for i in range(int(config.get("threadnum"))):
model = AutoModelForVision2Seq.from_pretrained(
- model_path,
- device_map="cuda:1",
+ config.get("qwenaddr"),
+ 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)
- self.processor = AutoProcessor.from_pretrained(model_path,use_fast=True)
+ self.processor = AutoProcessor.from_pretrained(config.get("qwenaddr"), use_fast=True)
-
- # 鍒涘缓瀹炰緥涓撳睘logger
- self.logger = logging.getLogger(f"{self.__class__}_{id(self)}")
- self.logger.setLevel(logging.INFO)
- # 閬垮厤閲嶅娣诲姞handler
- if not self.logger.handlers:
- handler = RotatingFileHandler(
- filename=os.path.join("logs", 'thread_log.log'),
- maxBytes=10 * 1024 * 1024,
- backupCount=3,
- encoding='utf-8'
- )
- formatter = logging.Formatter(
- '%(asctime)s - %(filename)s:%(lineno)d - %(funcName)s() - %(levelname)s: %(message)s'
- )
- handler.setFormatter(formatter)
- self.logger.addHandler(handler)
def submit(self,res_a):
# 灏濊瘯鑾峰彇淇″彿閲忥紙闈為樆濉烇級
acquired = self.semaphore.acquire(blocking=False)
if not acquired:
- self.logger.info(f"绾跨▼姹犲凡婊★紝绛夊緟绌洪棽绾跨▼... (褰撳墠娲昏穬: {self.max_workers - self.semaphore._value}/{self.max_workers})")
+ #self.logger.info(f"绾跨▼姹犲凡婊★紝绛夊緟绌洪棽绾跨▼... (褰撳墠娲昏穬: {self.max_workers - self.semaphore._value}/{self.max_workers})")
# 闃诲绛夊緟鐩村埌鏈夊彲鐢ㄧ嚎绋�
self.semaphore.acquire(blocking=True)
@@ -73,40 +61,45 @@
future.add_done_callback(self._release_semaphore)
return future
- def _wrap_task(self, res):
+ def _wrap_task(self, res_a):
try:
- #self.logger.info(f"澶勭悊: { res['id']}寮�濮�")
- current_time = datetime.now()
- image_id = self.tark_do(res, self.config.get("ragurl"), self.config.get("ragmode"), self.config.get("max_tokens"))
- self.logger.info(f"澶勭悊: { res['id']}瀹屾瘯{image_id}:{datetime.now() - current_time}")
- return image_id
+ self.tark_do(res_a, self.config.get("ragurl"), self.config.get("ragmode"), self.config.get("max_tokens"))
except Exception as e:
- self.logger.info(f"浠诲姟 { res['id']} 澶勭悊鍑洪敊: {e}")
+ self.logger.info(f"澶勭悊鍑洪敊: {e}")
raise
def tark_do(self,res,ragurl,rag_mode,max_tokens):
- try :
+ try:
# 1. 浠庨泦鍚圓鑾峰彇鍚戦噺鍜屽厓鏁版嵁
is_waning = 0
- image_des = self.image_desc(f"{res['image_desc_path']}")
- self.logger.info(image_des)
- if image_des:
- # rule_text = self.get_rule(ragurl)
- is_waning = self.image_rule_chat(image_des,res['waning_value'],ragurl,rag_mode,max_tokens)
- is_desc = 2
- else:
- is_waning = 0
- is_desc = 3
+ is_desc = 2
+ # 鐢熸垚鍥剧墖鎻忚堪
+ ks_time = datetime.now()
+ desc_time = datetime.now() - ks_time
+ current_time = datetime.now()
+ risk_description = ""
+ suggestion = ""
+ # 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)
+ # 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)
+ #self.logger.info(f"{res['video_point_id']}鎵ц瀹屾瘯锛歿res['id']}:鏄惁棰勮{is_waning},瀹夊叏闅愭偅锛歿risk_description}\n澶勭悊寤鸿锛歿suggestion}")
+ # 鏁版嵁缁�
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": image_des, # text_vector
+ "is_desc": 1,
+ "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
@@ -117,35 +110,75 @@
"image_path": res['image_path'], # image_path
"image_desc_path": res['image_desc_path'], # image_desc_path
"video_path": res['video_path'],
- "text_vector": res['text_vector']
+ "text_vector": res['text_vector'],
+ "risk_description": risk_description,
+ "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
- if is_desc == 2:
- data = {
- "id": str(image_id[0]),
- "video_point_id": res['video_point_id'],
- "video_path": res["video_point_name"],
- "zh_desc_class": image_des,
- "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))
- return image_id
+ image_id = self.collection.insert(data).primary_keys
+ res['id'] = image_id[0]
+ # 鍥剧墖鎻忚堪鐢熸垚鎴愬姛
+ desc = self.image_desc(res)
+ if desc:
+ is_desc = 2
+ else:
+ is_desc = 3
+ # 鏁版嵁缁�
+ data = {
+ "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
+ "bounding_box": res['bounding_box'], # bounding_box
+ "task_id": res['task_id'], # task_id
+ "task_name": res['task_name'], # task_id
+ "detect_id": res['detect_id'], # detect_id
+ "detect_time": res['detect_time'], # detect_time
+ "detect_num": res['detect_num'],
+ "waning_value": res['waning_value'],
+ "image_path": res['image_path'], # image_path
+ "image_desc_path": res['image_desc_path'], # image_desc_path
+ "video_path": res['video_path'],
+ "text_vector": res['text_vector'],
+ "risk_description": risk_description,
+ "suggestion": suggestion,
+ "knowledge_id": res['knowledge_id']
+ }
+ self.collection.delete(f"id == {res['id']}")
+ # 淇濆瓨鍒癿ilvus
+ image_id = self.collection.insert(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},RAG鐢ㄦ椂{rag_time}")
+ if is_waning == 1:
+ self.logger.info(f"{res['video_point_id']}鎵ц瀹屾瘯锛歿image_id},鍥剧墖鎻忚堪锛歿desc}\n闅愭偅锛歿risk_description}\n寤鸿锛歿suggestion}")
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:浠诲姟锛歿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, image_path):
+ def image_desc(self, res_data):
try:
model, lock = self._acquire_model()
- # 2. 澶勭悊鍥惧儚
- image = Image.open(image_path).convert("RGB") # 鏇挎崲涓烘偍鐨勫浘鐗囪矾寰�
- image = image.resize((600, 600), Image.Resampling.LANCZOS) # 楂樿川閲忕缉鏀�
+
+ image = Image.open(res_data['image_desc_path']).convert("RGB").resize((600, 600), Image.Resampling.LANCZOS)
messages = [
{
"role": "user",
@@ -167,19 +200,59 @@
padding=True,
return_tensors="pt",
)
- inputs = inputs.to("cuda:1")
- current_time = datetime.now()
- outputs = model.generate(**inputs,
- max_new_tokens=300,
- do_sample=True,
- temperature=0.7,
- renormalize_logits=True
- )
- print(f"澶勭悊瀹屾瘯:{datetime.now() - current_time}")
+ inputs = inputs.to(model.device)
+ with torch.inference_mode(), torch.amp.autocast(device_type=self.device, dtype=torch.float16):
+ outputs = model.generate(**inputs,max_new_tokens=200,do_sample=False,num_beams=1,temperature=None,top_p=None,top_k=1,use_cache=True,repetition_penalty=1.0)
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()
+ #self.logger.info(f"{res_data['video_point_id']}:{res_data['id']}:{res_data['detect_time']}:{image_des}")
+ return image_des
+ 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}")
+ finally:
+ # 4. 閲婃斁妯″瀷
+ self._release_model(model)
+ torch.cuda.empty_cache()
+
+ def image_rule(self, res_data):
+ 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", "image": image},
+ {"type": "text", "text": f"鍥剧墖涓槸鍚︽湁{res_data['waning_value']}?璇峰洖绛攜es鎴杗o"},
+ ],
+ }
+ ]
+
+ # Preparation for inference
+ text = self.processor.apply_chat_template(
+ messages, tokenize=False, add_generation_prompt=True
+ )
+ image_inputs, video_inputs = process_vision_info(messages)
+ inputs = self.processor(
+ text=[text],
+ images=image_inputs,
+ videos=video_inputs,
+ padding=True,
+ return_tensors="pt",
+ )
+ inputs = inputs.to(model.device)
+
+ 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
except Exception as e:
@@ -221,8 +294,7 @@
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(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変笉绗﹀悎瑙勫垯鐨勫唴瀹癸紝涓嶈繘琛屾帹鐞嗗拰think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": "",
@@ -241,10 +313,9 @@
}
response = requests.post(ragurl + "/chat", json=search_data)
results = response.json().get('data')
- #self.logger.info(len(results))
- # self.logger.info(results)
ret = re.sub(r'<think>.*?</think>', '', results, flags=re.DOTALL)
ret = ret.replace(" ", "").replace("\t", "").replace("\n", "")
+ #self.logger.info(f"{rule_text}:{ret}")
is_waning = 0
if len(ret) > 2:
is_waning = 1
@@ -252,6 +323,100 @@
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
+ }
+ }
+ #self.logger.info(content)
+ 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:
@@ -264,7 +429,7 @@
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})")
+ #self.logger.info(f"閲婃斁绾跨▼ (鍓╀綑绌洪棽: {self.semaphore._value}/{self.max_workers})")
def shutdown(self):
"""瀹夊叏鍏抽棴"""
--
Gitblit v1.8.0