titu1994 / Image-Super-Resolution

Implementation of Super Resolution CNN in Keras.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

ValueError: Only tensors of same shape can be merged by layeradd_1 Got input shapes: [(None, 64, 8, 8), (None, 64, 8, 64)]

kankur opened this issue · comments

sr and esr are working fine. But when I ran python main.py "input_images/tt26.bmp" --model=dsr --save_intermediate=True , I am getting following error :
Traceback (most recent call last):
File "main.py", line 50, in
model.upscale(path, save_intermediate=save, mode=mode, patch_size=patch_size, suffix=suffix)
File "/home/ankurk/ML/Image Super Resolution/Image-Super-Resolution-master/models.py", line 182, in upscale
model = self.create_model(img_height, img_width, load_weights=True)
File "/home/ankurk/ML/Image Super Resolution/Image-Super-Resolution-master/models.py", line 565, in create_model
level2 = Add()([level2_1, level2_2])
File "/home/ankurk/anaconda3/lib/python3.5/site-packages/keras/engine/topology.py", line 530, in call
self.build(input_shapes)
File "/home/ankurk/anaconda3/lib/python3.5/site-packages/keras/layers/merge.py", line 39, in build
' Got input shapes: %s' % input_shape)
ValueError: Only tensors of same shape can be merged by layeradd_1 Got input shapes: [(None, 64, 8, 8), (None, 64, 8, 64)]