small update to readme about downloading the image from remote

README.md

@@ -9,11 +9,11 @@ datasets:
 
 # DETR (End-to-End Object Detection) model with ResNet-50 backbone trained on SKU110K Dataset with 400 num_queries
 
-DEtection TRansformer (DETR) model trained end-to-end on SKU110K object detection (8k annotated images). Main difference between the model is it having **400** num_queries and it being pretrained on SKU110K dataset.
+DEtection TRansformer (DETR) model trained end-to-end on SKU110K object detection (8k annotated images). Main difference compared to the original model is it having **400** num_queries and it being pretrained on SKU110K dataset.
 
 ### How to use
 
-Here is how to use this model. You can download the **IMG_3507.jpg** from HuggingFace files
+Here is how to use this model:
 
 ```python
 from transformers import DetrImageProcessor, DetrForObjectDetection
@@ -21,9 +21,9 @@ import torch
 from PIL import Image, ImageOps
 import requests
 
-url = "IMG_3507.jpg" # You can download this image from HF files
-image = Image.open(url)
-ImageOps.exif_transpose(image)
+url = "https://github.com/Isalia20/DETR-finetune/blob/main/IMG_3507.jpg?raw=true"
+image = Image.open(requests.get(url, stream=True).raw)
+image = ImageOps.exif_transpose(image)
 
 # you can specify the revision tag if you don't want the timm dependency
 processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
@@ -38,11 +38,11 @@ target_sizes = torch.tensor([image.size[::-1]])
 results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.8)[0]
 
 for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
-    box = [round(i, 2) for i in box.tolist()]
-    print(
-            f"Detected {model.config.id2label[label.item()]} with confidence "
-            f"{round(score.item(), 3)} at location {box}"
-    )
+        box = [round(i, 2) for i in box.tolist()]
+        print(
+                f"Detected {model.config.id2label[label.item()]} with confidence "
+                f"{round(score.item(), 3)} at location {box}"
+        )
 ```
 This should output:
 ```