search

jmiller656 / EDSR-Tensorflow

Tensorflow implementation of Enhanced Deep Residual Networks for Single Image Super-Resolution
MIT License
330 stars 107 forks source link

An error occurred when scale was 3 #12

Closed Ivan-Zhao closed 5 years ago

Ivan-Zhao commented 6 years ago

An error occurred when scale was 3.How to solve it? 0%| | 0/1000 [00:00<?, ?it/s] Traceback (most recent call last): File "/home/ivanz/workspace/tensor_sr/EDSR-Tensorflow-master/train.py", line 18, in network.train(args.iterations,args.savedir) File "/home/ivanz/workspace/tensorsr/EDSR-Tensorflow-master/model.py", line 188, in train summary, = sess.run([merged,train_op],feed) File "/home/ivanz/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 895, in run run_metadata_ptr) File "/home/ivanz/anaconda2/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1100, in _run % (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape()))) ValueError: Cannot feed value of shape (10, 100, 100, 3) for Tensor u'Placeholder_1:0', which has shape '(?, 99, 99, 3)'

jmiller656 commented 6 years ago

Hey, sorry about that. I'll be looking at this today. Looks like a small division error on my part

lihka1 commented 6 years ago

is it solved? .. I am too getting the same error now?...any suggestions for the fixes?

jmiller656 commented 5 years ago

I've fixed this with my most recent change