From c6715f570345f36ff930ebd4747bb4bb0e611073 Mon Sep 17 00:00:00 2001 From: Niels Rogge Date: Fri, 16 Dec 2022 20:05:33 +0000 Subject: [PATCH] Update to image processor --- README.md | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index ace50ba..20393b6 100644 --- a/README.md +++ b/README.md @@ -37,7 +37,7 @@ You can use the raw model for object detection. See the [model hub](https://hugg Here is how to use this model: ```python -from transformers import DetrFeatureExtractor, DetrForObjectDetection +from transformers import DetrImageProcessor, DetrForObjectDetection import torch from PIL import Image import requests @@ -45,24 +45,23 @@ import requests url = "http://images.cocodataset.org/val2017/000000039769.jpg" image = Image.open(requests.get(url, stream=True).raw) -feature_extractor = DetrFeatureExtractor.from_pretrained("facebook/detr-resnet-101") +processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-101") model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-101") -inputs = feature_extractor(images=image, return_tensors="pt") +inputs = processor(images=image, return_tensors="pt") outputs = model(**inputs) # convert outputs (bounding boxes and class logits) to COCO API +# let's only keep detections with score > 0.9 target_sizes = torch.tensor([image.size[::-1]]) -results = feature_extractor.post_process(outputs, target_sizes=target_sizes)[0] +results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0] for score, label, box in zip(results["scores"], results["labels"], results["boxes"]): box = [round(i, 2) for i in box.tolist()] - # let's only keep detections with score > 0.9 - if score > 0.9: - print( + print( f"Detected {model.config.id2label[label.item()]} with confidence " f"{round(score.item(), 3)} at location {box}" - ) + ) ``` This should output (something along the lines of): ```