添加models.py文件

models.py

@@ -0,0 +1,109 @@
+
+import requests
+import torch
+from PIL import Image
+from transformers import pipeline
+from paddleocr import PaddleOCR
+from transformers import BlipProcessor, BlipForConditionalGeneration
+
+
+class translate_models:
+    @staticmethod
+    def translate_models(file_path, flag, pairs):
+
+        # pairs = 1  # 默认为英转中
+        # flag = 2  # flag：判断是进行文字识别还是图片理解  1:文字识别  2:图片理解
+        # image_path_identify = 'D:\\py\\pythonProject\\image\\00056221.jpg'  # 用来文字识别的图片所在的文件路径
+        # image_path_understand = r"C:\Users\16173\Desktop\ccf_cv\blue-throat-7077261__340.jpg"  # 用来进行图片理解的文件路径
+
+        """事实证明除中文外，英语转成其他语言更难"""
+        language_pairs = {
+            "en-zh": "Helsinki-NLP/opus-mt-en-zh",  # 1:英语到中文
+            "zh-en": "Helsinki-NLP/opus-mt-zh-en",  # 2:中文到英语
+            "en-fr": "Helsinki-NLP/opus-mt-en-fr",  # 3:英语到法语
+            "fr-en": "Helsinki-NLP/opus-mt-fr-en",  # 4:法语到英语
+            "en-es": "Helsinki-NLP/opus-mt-en-es",  # 5:英语到西班牙语
+            "es-en": "Helsinki-NLP/opus-mt-es-en",  # 6:西班牙语到英语
+            "en-de": "Helsinki-NLP/opus-mt-en-de",  # 7:英语到德语
+            "de-en": "Helsinki-NLP/opus-mt-de-en",  # 8:德语到英语
+            "en-ru": "Helsinki-NLP/opus-mt-en-ru",  # 9:英语到俄语
+            "ru-en": "Helsinki-NLP/opus-mt-ru-en",  # 10:俄语到英语
+            "zh-fr": "Helsinki-NLP/opus-mt-zh-fr",  # 11:中文到法语
+            "fr-zh": "Helsinki-NLP/opus-mt-fr-zh",  # 12:法语到中文
+        }
+
+        if flag == 1:
+            image_path_identify = file_path# 用来文字识别的图片所在的文件路径
+
+            if torch.cuda.is_available():
+                # 使用 GPU
+                ocr = PaddleOCR(use_angle_cls=True, lang='ch', use_gpu=True)
+                print("使用 GPU 进行 OCR")
+            else:
+                # 使用 CPU
+                ocr = PaddleOCR(use_angle_cls=True, lang='ch', use_gpu=False)
+                print("使用 CPU 进行 OCR")
+            flag = 0
+            result = ocr.ocr(image_path_identify, cls=True)
+
+            # 提取纯文字内容
+            extracted_text = [res[1][0] for res in result[0]]
+
+            """-----------------------------------------这是文字识别的输出--------------------------------------------------"""
+            print("文字识别结果如下：")
+            for text in extracted_text:
+                print(text)
+
+        if flag == 2:
+            # 图片理解模块
+            image_path_understand = file_path  # 用来进行图片理解的文件路径
+
+            processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+            model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
+
+            image_path = image_path_understand  # 本地图片路径
+            image = Image.open(image_path)
+
+            # 处理图片
+            inputs = processor(images=image, return_tensors="pt")
+            output = model.generate(**inputs)
+
+            # 解码生成的描述
+            description = processor.decode(output[0], skip_special_tokens=True)
+            print(description)
+
+            if pairs == 1:
+                language_pair = "en-zh"
+            if pairs == 2:
+                language_pair = "zh-en"
+            if pairs == 3:
+                language_pair = "en-fr"
+            if pairs == 4:
+                language_pair = "fr-en"
+            if pairs == 5:
+                language_pair = "en-es"
+            if pairs == 6:
+                language_pair = "es-en"
+            if pairs == 7:
+                language_pair = "en-de"
+            if pairs == 8:
+                language_pair = "de-en"
+            if pairs == 9:
+                language_pair = "en-ru"
+            if pairs == 10:
+                language_pair = "ru-en"
+            if pairs == 11:
+                language_pair = "zh-fr"
+            if pairs == 12:
+                language_pair = "fr-zh"
+            translator = pipeline("translation", model=language_pairs[language_pair])
+
+            # 翻译文本
+            result = translator(description, max_length=40)
+            translation_text = result[0]['translation_text']
+
+            # 要把这里的translation_text传给前端/////
+            print(translation_text)
+            return translation_text
+
+