Update app.py

app.py

@@ -4,39 +4,41 @@ from transformers import YolosImageProcessor, YolosForObjectDetection, pipeline
 from PIL import Image
 import requests
 
-# st.title("Welcome to 🇷🇺 Translator App!🪆")
 
-# input = st.text_area("Your input here! 🇬🇧")
 
-# pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-ru-en")
+st.title("Welcome to 🇷🇺 Translator App!🪆")
 
-# st.write(pipe(input)[0]['translation_text'])
+input = st.text_area("Your input here! 🇬🇧")
 
-st.title("Imag")
+pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-ru-en")
 
-url = st.text_area("Put your URL here")
-if url:
-    image = Image.open(requests.get(url, stream=True).raw)
+st.write(pipe(input)[0]['translation_text'])
 
-    st.image(image)
 
-    model = YolosForObjectDetection.from_pretrained('hustvl/yolos-tiny')
-    image_processor = YolosImageProcessor.from_pretrained("hustvl/yolos-tiny")
+
+# url = st.text_area("Put your URL here")
+# if url:
+#     image = Image.open(requests.get(url, stream=True).raw)
+
+#     st.image(image)
+
+#     model = YolosForObjectDetection.from_pretrained('hustvl/yolos-tiny')
+#     image_processor = YolosImageProcessor.from_pretrained("hustvl/yolos-tiny")
     
-    inputs = image_processor(images=image, return_tensors="pt")
-    outputs = model(**inputs)
+#     inputs = image_processor(images=image, return_tensors="pt")
+#     outputs = model(**inputs)
     
-    # model predicts bounding boxes and corresponding COCO classes
-    logits = outputs.logits
-    bboxes = outputs.pred_boxes
-    st.image(bboxes)
-
-    # print results
-    target_sizes = torch.tensor([image.size[::-1]])
-    results = image_processor.post_process_object_detection(outputs, threshold=0.9, target_sizes=target_sizes)[0]
-    for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
-        box = [round(i, 2) for i in box.tolist()]
-        st.write(
-            f"Detected {model.config.id2label[label.item()]} with confidence "
-            f"{round(score.item(), 3)} at location {box}"
-        )
+#     # model predicts bounding boxes and corresponding COCO classes
+#     logits = outputs.logits
+#     bboxes = outputs.pred_boxes
+#     st.image(bboxes)
+
+#     # print results
+#     target_sizes = torch.tensor([image.size[::-1]])
+#     results = image_processor.post_process_object_detection(outputs, threshold=0.9, target_sizes=target_sizes)[0]
+#     for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
+#         box = [round(i, 2) for i in box.tolist()]
+#         st.write(
+#             f"Detected {model.config.id2label[label.item()]} with confidence "
+#             f"{round(score.item(), 3)} at location {box}"
+#         )