yolo nas 抛出错误“ImageDetectionPrediction”对象不可迭代

Question

我在 yolo nas 检测代码上绑定了运行预测，但它抛出了错误。在 Colab 之前，它工作正常，没有给出错误，但第二天它给出了一个错误，我不明白我运行此代码的任何内容，与每个 yolo nas github 文档相同。不知道什么

img_url='/content/Retail-Store-1/valid/images/-10_jpg.rf.d5119996f5715cf1105b1e5bf01c0ced.jpg'
# best_model.predict(img_url).show()
# images_predictions.show(box_thickness=2, show_confidence=True)

images_predictions = best_model.predict(img_url)
for image_prediction in images_predictions:
    class_names = image_prediction.class_names
    labels = image_prediction.prediction.labels
    confidence = image_prediction.prediction.confidence
    bboxes = image_prediction.prediction.bboxes_xyxy

    for i, (label, conf, bbox) in enumerate(zip(labels, confidence, bboxes)):
        print("prediction: ", i)
        print("label_id: ", label)
        print("label_name: ", class_names[int(label)])
        print("confidence: ", conf)
        print("bbox: ", bbox)
        print("--" * 10)


---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-24-7b64588141eb> in <cell line: 1>()
----> 1 for image_prediction in images_predictions:
      2     class_names = image_prediction.class_names
      3     labels = image_prediction.prediction.labels
      4     confidence = image_prediction.prediction.confidence
      5     bboxes = image_prediction.prediction.bboxes_xyxy

TypeError: 'ImageDetectionPrediction' object is not iterable

Answer 1

之前工作时您可能使用的是 3.5 版本，因为从 3.6 版本开始，如果输入是单个图像，预测结果不再是可迭代对象。

另请参阅 GitHub 问题那里。