Muhib Ullah

icon indicating a website link www.linkedin.com/in/muhib-ullah-1449b7139

icon company University of Regina icon location Regina, Canada icon location Machine Learning, Computer Vision, Deep Learning, Speech Recognition

Results 3 comments of Muhib Ullah

While annotating Semantic Segmentation example with "labelme data_annotated --labels labels.txt --nodata --validatelabel exact --config '{shift_auto_shape_color: -2}' " command, it says UNRECOGNIZED AURGUMENTS: -2

any help in this regard would be greatly appreciated

What does the following code mean?img[0,:,:]=img[0,:,:]-92.8207477031

it seems he is taking mean pixel values across each channel (R, B, G) and then subtract them for the sake of normalization

WARNING: root: NaN or Inf found in input tensor.

> I'm having very small dataset of only 100 Images in Training and 10 Images in Val. > > My YML is: `project_name: technical_names train_set: train val_set: val num_gpus: 1...