search

YuhuiMa / DFN-tensorflow

This repo is the tensorflow implementation of Discriminative Feature Network (DFN)
Apache License 2.0
100 stars 26 forks source link

assert img.ndim == 3 and img.shape[2] == 3 #1

Open speakstone opened 6 years ago

speakstone commented 6 years ago

Did you encounter any of the following problems during the training?

File "main.py", line 159, in tf.app.run() File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/platform/app.py", line 124, in run _sys.exit(main(argv)) File "main.py", line 142, in main train(result, model, cfg.logdir, cfg.train_sum_freq, cfg.val_sum_freq, cfg.save_freq, cfg.models, fd) File "main.py", line 34, in train trX, trY = get_batch_of_trainval(result, "train", model.batch_size) File "/home/zw/deeplab_change/DFN-tensorflow-master/utils.py", line 79, in get_batch_of_trainval assert img.ndim == 3 and img.shape[2] == 3 AssertionError

This problem is in Training for iter 1050/139900: Training for iter 162/279800:

YuhuiMa commented 6 years ago

Please make sure all your images have three channels. The code is not perfect. If there are any bugs, please give me more advice.