fix random_flip setting

[mathfinder]

parser.add_argument('--random_flip', default=True, type=bool,
help='if horizontally flip images when training')
random_flip will always be True, although we run 'python train.py --random_flip False'

[wudonghao]

I CAN'T RUN IT FOR
File "train.py", line 314, in
main(args)
File "train.py", line 200, in main
train(segmentation_module, iterator_train, optimizers, history, epoch, args)
File "train.py", line 37, in train
loss, acc = segmentation_module(batch_data)
File "/home/wdh/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/wdh/PycharmProjects/Semantic Segmentation/pytorch-semantic-segmentation-master by hangzhaomit/models/models.py", line 34, in forward
pred = self.decoder(self.encoder(feed_dict['img_data'], return_feature_maps=True))
TypeError: list indices must be integers or slices, not str

[shlykov2]

I CAN'T RUN IT FOR
File "train.py", line 314, in
main(args)
File "train.py", line 200, in main
train(segmentation_module, iterator_train, optimizers, history, epoch, args)
File "train.py", line 37, in train
loss, acc = segmentation_module(batch_data)
File "/home/wdh/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/wdh/PycharmProjects/Semantic Segmentation/pytorch-semantic-segmentation-master by hangzhaomit/models/models.py", line 34, in forward
pred = self.decoder(self.encoder(feed_dict['img_data'], return_feature_maps=True))
TypeError: list indices must be integers or slices, not str

had the same issue, fixed with adding "feed_dict = feed_dict[0]" at the start of forward function in SegmentationModule class in models.py. Could please some1 tell me whether it spoils the training?

[wjqqy]

i also meet the problem,but i fix the feed_dict['img_data'] to feed_dict[0]['img_data']