rm (#62)

* rm

* Delete demo.py

experiments/segmentation/demo.py

-import torch
-import encoding
-
-# Get the model
-model = encoding.models.get_model('fcn_resnet50_ade', pretrained=True).cuda()
-model.eval()
-
-# Prepare the image
-url = 'https://github.com/zhanghang1989/image-data/blob/master/' + \
-      'encoding/segmentation/ade20k/ADE_val_00001142.jpg?raw=true'
-filename = 'example.jpg'
-img = encoding.utils.load_image(
-    encoding.utils.download(url, filename)).cuda().unsqueeze(0)
-
-# Make prediction
-output = model.evaluate(img)
-predict = torch.max(output, 1)[1].cpu().numpy() + 1
-
-# Get color pallete for visualization
-mask = encoding.utils.get_mask_pallete(predict, 'ade20k')
-mask.save('output.png')

experiments/segmentation/test_models.py

-import importlib
-import torch
-import encoding
-from option import Options
-from torch.autograd import Variable
-
-if __name__ == "__main__":
-    args = Options().parse()
-    model = encoding.models.get_segmentation_model(args.model, dataset=args.dataset, aux=args.aux,
-                                                   se_loss=args.se_loss, norm_layer=torch.nn.BatchNorm2d)
-    print('Creating the model:')
-    
-    print(model)
-    model.cuda()
-    x = Variable(torch.Tensor(4, 3, 480, 480)).cuda()
-    with torch.no_grad():
-        out = model(x)
-    for y in out:
-        print(y.size())