semantic-segmentation-pytorch

semantic-segmentation-pytorch copied to clipboard

hello author, i have implemented similar fcn vgg like yours. But my fcn32 gives better results than fcn 16 and 8. why is this. Can you please check my code....

soans1994

Hi, originally it work well with num_class=256... but when I edited `img = img.astype('float32') / 255.0, seg = seg.astype('float32') / 255.0` in segmentation_dataset.py, and ` target = target//255` in trainer.py...

zhou-rui1

how to output the gray image without random.randint?

5

Hi, I want to output the gray image for the binary classfication, how should I edit it? I try to edit this part but failed: `random.seed(0) class_colors = [(random.randint(0, 255),...

zhou-rui1

Skip layer connections from the second layer

3

Hi, when I try to edit the unet to unet++, it seems that the horizontal connections are only added from the second layer, and the last output layer is up-sampled...

zhou-rui1

Dear sir, I study your code for a long time, thanks for your contribution. Nearly, I find pspnet's encoder (resnet50) need dilation, however, I didn't find it.Do you write it...

LeeNannaner

Using on high channel image dataset

1

I want to try e.g. FCN8 on a custom dataset of high channel images(100ch+) but I'm not used to image segmentation with pretrained encoders. Are the models w/ corresponding encoders...

torjusn

HI, @IanTaehoonYoo How can I get the location coordinates of detected objects at inference time ? Thanks. Best, @bemoregt.

bemoregt

Scaling Error when training using different ratio size of image in batch_size > 1

3

Error in `Trainer.train() ` `RuntimeError: stack expects each tensor to be equal size, but got [3, 200, 257] at entry 0 and [3, 200, 341] at entry 2` When using...

leocd91

I tested with several model configurations, with and without pretrained weights, but am only getting black images for prediction outputs. Is this library not suitable for binary classification (background =...

bc-bytes