I am using cv_samples_v1.3.0/unet as a guide to do transfer learning for a dataset comprised of color images and need to get a multiclass result using semantic segmentation. I fully ran the notebook unet_isbi to completion with the default values and test data. I changed the training specificatio…

Your last recommendation for hyperparameters didn’t work for binary semantic segmentation but it did work for multiclass semantic segmentation with my images, which is what I wanted. Thank you very much for all your support. By the way I am curious to know for the future if there is an option for …

Are your images .jpg or .png? Refer to Problems encountered in training unet and inference unet - #26 , you can have a try for below. Change the training image from jpg to png. $ for i in *.jpg ; do convert "$i" "${i%.*}.png" ; done

Thanks! I changed the images to be PNG and completely deleted the contents of folder isbi_experiment_unpruned, but same nan results on evaluate

Refer to Problems encountered in training unet and inference unet - #26 and Multiple classes not detected? - #11 by Morganh Please note that the pixel integer value should be equal to the value of the label_id provided in the spec. UNet expects the images and corresponding masks encoded as image…

I wrote a program to count the pixels per ID value, and they are all fine!! P1020007.png, 0: 448962, 10: 21025, 40: 496, 70: 3059, 100: 58, BAD: 0 P1020008.png, 0: 448504, 10: 21388, 40: 654, 70: 2952, 100: 102, BAD: 0 P1020009.png, 0: 439044, 10: 30354, 40: 845, 70: 3234, 100: 123, BAD: 0 P102001…

More, as mention in Problem in training unet - #21 by Morganh Please convert the mask images to gray images. After checking the public dataset you mentioned, the pixel value is either 0 or 128. Please map 128 to 1. For binary segmentation, the label_id should be 0 and 1. BTW, if there are 4 classe…

Thanks! The image is created as Grayscale as follows: Mat red (resized.rows, resized.cols, CV_8UC1); Also converted all labels to be contiguous 0, 1, 2, 3, and 4: P1020007.png, 0: 448962, 1: 21025, 2: 496, 3: 3059, 4: 58, BAD: 0 P1020008.png, 0: 448504, 1: 21388, 2: 654, 3: 2952, 4: 102, BAD:…

UPDATE I decided to go back to what works and do small steps from there. I went back to a working version of the original unmodified unet_isbi notebook. Then, I made by dataset have the same specs as the ISBI dataset: all images are grayscale 512X512, and the masks have label values of 0 for backg…

Because it is grayscale image in the notebook. Its “input_image_type” is not color. Only in the case of grayscale, the mask image will have 0 and 255 and the tao pipe will take care accordingly, mapping is not required. For input_image_type color and the mask having any value except 0 and 255 - we…

Right now I am trying to simplify by using the original unet_isbi all in grayscale, but with my images,converted to grayscale 512X512 it worked well with two classes (binary segmentation) with exactly the same original spec as for isbi. This means the masks were marked 0 and 255. Running the same mo…

Fail with Transfer Learning with Unet Multiclass, Color Images, Semantic Segmentation

Accelerated Computing Intelligent Video Analytics TAO Toolkit

Morganh January 17, 2022, 6:27am 13

As mentioned above, for the case of grayscale, mapping is not required.

Yes, please refer to another user’s topic Training multi-class UNet does not converge - #32 by laurim

Topic		Replies	Views
Problem in training unet TAO Toolkit	21	2200	August 30, 2021
Training multi-class UNet does not converge TAO Toolkit	30	3519	September 10, 2021
Problem in training Unet with multi class labels TAO Toolkit	10	1283	January 16, 2022
TAO unet producing nan values TAO Toolkit	4	1051	April 7, 2022
Multiple classes not detected? TAO Toolkit	18	1229	September 13, 2021
Problems encountered in training unet and inference unet TAO Toolkit inference-server-triton	26	3123	September 10, 2021
Segmentation with unet : shape error TAO Toolkit	7	1693	April 27, 2021
Transfer learning using the cityscapes dataset in unet-peopleSemSegNet causes poor generalization performance TAO Toolkit segmentation	11	1681	October 27, 2021
Migrating TAO3 unet model to segformer, Foreground has performance of 0.0 ! TAO Toolkit	27	1406	February 27, 2023
Cannot run tao unet dataset_convert because of docker mapping issue TAO Toolkit	5	912	March 24, 2023

Fail with Transfer Learning with Unet Multiclass, Color Images, Semantic Segmentation

Related topics