Issam H. Laradji

this is expected, because the model is trained on trancos. The dataset only has around 400 images and look very different from the images above. The model needs to be...

Is there a way you can make the TIF image have 3 channels in the first dimension without having to convert it to JPG?

run `trainval.py`

Hi Natasha, sorry about the late reply. Last week was graduation week, and it was exciting and hectic :P hehe. I have made a clean version of the code (it's...

Hiya @yassineAlouini , what you suggested should work! It might be a bit slow, and the learning rate might need to be adjusted. LCFCN does not work natively with batch...

Blobs are computed in two steps (as shown in line 33-46 in `models.py`): 1. First we compute`pred_mask = self(images).data.max(1)[1].squeeze().cpu().numpy()`, which gets the argmax over the probability of each pixel over...

`[None]` just adds a dimension, if `blobs` is `K x H x W`, then `blobs[None]` is `1 x K x H x W`

The segmentation part you showed is the upsampling path which combines different features from VGG16 to output a `K x H x W` matrix where `K` is the number of...

1) The 5, 9, and 31 are there to take care of the shifting due to the max-pooling layers of VGG16. 2) Once you get the `output` above (which is...

1. i. `blob_uniques` corresponds to all the unique blobs that intersect with the point-annotations. The false positive blobs are those that do not intersect with the point-annotations, which is what...