algorithm/pytorch-tutorial
1
0
Fork 0
mirror of https://github.com/yunjey/pytorch-tutorial.git synced 2025-07-07 10:05:29 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fixed Test error when encoder(image).

Browse Source 
When we load an image for the sample, we have to make sure that the image has three color channel (RGB) because it might be grayscale. So we should convert it for sampling.
This commit is contained in:
Mohammad Hasan
2019-03-13 22:23:53 +06:00
committed by GitHub
parent 4896cefea1
commit b5793737c6
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tutorials/03-advanced/image_captioning/sample.py
View File

@ -14,7 +14,7 @@ from PIL import Image
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
def load_image(image_path, transform=None):
image = Image.open(image_path)
image = Image.open(image_path).convert('RGB')
image = image.resize([224, 224], Image.LANCZOS)
if transform is not None:
@ -78,4 +78,4 @@ if __name__ == '__main__':
parser.add_argument('--hidden_size', type=int , default=512, help='dimension of lstm hidden states')
parser.add_argument('--num_layers', type=int , default=1, help='number of layers in lstm')
args = parser.parse_args()
main(args)
main(args)