pytorch-deeplab-xception

pytorch-deeplab-xception copied to clipboard

my data are images and its 0,255 masks,,the masks are 0 255 images, it is voc format?

1

how to train my data?

henbucuoshanghai

ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 256, 1, 1])

5

When I train my coco-style dataset by use : bash train_coco.sh then the errors as follows: Namespace(backbone='resnet', base_size=513, batch_size=4, checkname='deeplab-resnet', crop_size=513, cuda=True, dataset='coco', epochs=10, eval_interval=1, freeze_bn=False, ft=False, gpu_ids=[0], loss_type='ce', lr=0.01,...

YadongLau

Issue with Xception Backbone

2

I've tried both xception and resnet-101 backbone. The resent-101 backbone is working fine but when using xception backbone, results are very bad. And even, training for longer making the resulting...

Thunder003

refactoring code with var unpack which is more pythonic, concise, readable and efficient

idiomaticrefactoring

Overfitting when training on Cityscapes

3

I wonder about the overfitting problem when training on Cityscapes and why it happened. How can I solve this problem? Thanks! 

Liforam

Has anybody run the code efficient？

b762927

@stonessss yes, i write test code.

1

@stonessss yes, i write test code. 1. copy and overwrite. https://github.com/jaemin93/pytorch-deeplab-xception/blob/master/test.py https://github.com/jaemin93/pytorch-deeplab-xception/blob/master/dataloaders/__init__.py 2. add test.txt(you want to test img id) in VOC path /ImageSets/Segmentation test.txt is like val, train.txt 3....

ouyang11111

self = reduction.pickle.load(from_parent) error Ran out of input

1

File "E:\ProgramData\Anaconda3\envs\yolov5-master\lib\multiprocessing\popen_spawn_win32.py", line 89, in __init__ reduction.dump(process_obj, to_child) File "E:\ProgramData\Anaconda3\envs\yolov5-master\lib\multiprocessing\reduction.py", line 60, in dump ForkingPickler(file, protocol).dump(obj) TypeError: can't pickle module objects Traceback (most recent call last): File "E:\ProgramData\Anaconda3\envs\yolov5-master\lib\multiprocessing\spawn.py", line 115,...

xinyujituan

VOC 2012 TEST results

17

Hi, I took the liberty of submitting the resnet pre-trained model results on VOC2012 TEST to the evaluation server. These are the results on the TEST set: Competition | Category...

shaibagon

run inference.py success

2

ouyang11111