zhmiao
commented
2 months ago Hello @ThomasLuypaert, thanks for reporting! And we have addressed the same issue in https://github.com/microsoft/CameraTraps/issues/523 and are closing this issue. Please update the package and let us know if the issue still persist and we can reopen it. Thanks!
Search before asking
Bug
Hi all,
I am trying to run the Megadetector in Pytorch-Wildlife to detect animals in videos. I have been following the online notebook provided here.
However, following the steps in this notebook results in the following error:
I realize that the classification step is not appropriate for my type of data, since I am not working with possums - but I am just testing the functionality.
Environment
No response
Minimal Reproducible Example
My code looks as follows: ` from PIL import Image import numpy as np import supervision as sv import torch from PytorchWildlife.models import detection as pw_detection from PytorchWildlife.models import classification as pw_classification from PytorchWildlife.data import transforms as pw_trans from PytorchWildlife import utils as pw_utils import os
DEVICE = "cuda" if torch.cuda.is_available() else "cpu" SOURCE_VIDEO_PATH = "/mnt/path_here/Videos/brocket_deer/58386bb1-3b61-4c5c-8d26-a8505e68e827.mp4" TARGET_VIDEO_PATH = "/mnt/path_here/Videos/brocket_deer/58386bb1-3b61-4c5c-8d26-a8505e68e827_processed.mp4" detection_model = pw_detection.MegaDetectorV5(device=DEVICE, pretrained=True) classification_model = pw_classification.AI4GOpossum(device=DEVICE, pretrained=True)
trans_det = pw_trans.MegaDetector_v5_Transform(target_size=detection_model.IMAGE_SIZE, stride=detection_model.STRIDE) trans_clf = pw_trans.Classification_Inference_Transform(target_size=224)
box_annotator = sv.BoxAnnotator(thickness=4)
def callback(frame: np.ndarray, index: int) -> np.ndarray: results_det = detection_model.single_image_detection(trans_det(frame), frame.shape, index) labels = [] for xyxy in results_det["detections"].xyxy: cropped_image = sv.crop_image(image=frame, xyxy=xyxy) results_clf = classification_model.single_image_classification(trans_clf(Image.fromarray(cropped_image))) labels.append("{} {:.2f}".format(results_clf["prediction"], results_clf["confidence"])) annotated_frame = box_annotator.annotate(scene=frame, detections=results_det["detections"], labels=labels) return annotated_frame
pw_utils.process_video(source_path=SOURCE_VIDEO_PATH, target_path=TARGET_VIDEO_PATH, callback=callback, target_fps=5) `
Additional
No response
Are you willing to submit a PR?