People who code: we want your input. Take the Survey

New answers tagged

0

The correct way is to compute the DICE score per image and then find the mean, median and STD across all test images. It is good practice to report all three metrics to provide a clear intuition to the reader. For more details, please refer to this answer.


1

For this, you don't need to go through the pain of creating a model yourself. Use MTCNN to detect the face and get on with it. For posterity, compare face size and position w.r.t. to the image amd take optimal decision.


0

The best way is to use like Pre-trained transfer learning model with U-Net(Mobile Net). VGG-face with pre-defined-weights. Mobile net with U-Net def create_model(trainable=True): model = MobileNet(input_shape=(IMAGE_HEIGHT, IMAGE_WIDTH, 3), include_top=False, alpha=ALPHA, weights="imagenet") for layer in model.layers: layer....


0

Video has two information i.e. Images(Frames) and a temporal sense(moving Frame). To identify an object in each frame, treating each frame as separate image will work. To read the temporal sense of the video i.e. Running or Skipping, will need to treat the video as Sequence of images and work accordingly. This topic is pretty well covered in the online ...


0

Yes - individual frames can be used. See existing answers and links to docs as appropriate: https://stackoverflow.com/q/18954889/1928322 The following blog shows how to extract individual frames from a video (replicating your environment) before continuing: https://www.pyimagesearch.com/2017/02/06/faster-video-file-fps-with-cv2-videocapture-and-opencv/


0

I'm struggling with a similar problem myself. Could you please provide details about: What version of efficientDet you are using What preprocessing you are currently using on the images One solution is to divide the images into smaller images. At this years Nvidia GTC conference, ConservationAI did a talk where they mentioned that they split up 8k images ...


1

Instance segmentation: The combination annotation of target detection and semantic segmentation. The target detection comes first, and then each pixel is labeled (semantic segmentation). Compared to the image above, we take the person as the target objection for example: Semantic segmentation does not distinguish different instances in the same category (...


0

To be able to answer your question, firstly we should take into account the differences between Normalization and Standardization. Normalization: normalized_value=(raw_value-min)/(max-min) Standardization: standarized_value=(raw_value-μ)/σ Also, one additional famous method is there which is centering. Where you subtract the mean from the pixels. In general, ...


Top 50 recent answers are included