search

mintanwei / Cycle-IR

This is a Tensorflow implementation of Cycle-IR approach for content-aware image retargeting.
20 stars 3 forks source link

Not able to reproduce results #8

Open AlverGant opened 2 years ago

AlverGant commented 2 years ago

As far as I know this is the only project to do image retargeting with deep-learning. Really interested to see it working.. Done with all requirements Donwloaded vgg16.npy and vgg16.py from https://github.com/machrisaa/tensorflow-vgg in VGG_MODEL folder commented out all assert instructions from vgg16.py Now stuck with this error

ubuntu@vega:~/Cycle-IR$ python3 CycleIR.py npy file loaded build model started Traceback (most recent call last): File "CycleIR.py", line 204, in tf.app.run() File "/home/ubuntu/.local/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 126, in run _sys.exit(main(argv)) File "CycleIR.py", line 190, in main opt_g, aspect_ratio, images, CycleLoss, images_LR, AttentionMap, input_size, Sh, Sw = build_graph() File "CycleIR.py", line 93, in build_graph Sh, Sw, AttentionMap = CycleIR(images, reuse=False) File "CycleIR.py", line 27, in CycleIR vgg.build(images) File "/home/ubuntu/Cycle-IR/VGG_MODEL/vgg16.py", line 69, in build self.fc6 = self.fc_layer(self.pool5, "fc6") File "/home/ubuntu/Cycle-IR/VGG_MODEL/vgg16.py", line 106, in fc_layer dim = d TypeError: unsupported operand type(s) for =: 'int' and 'NoneType'

givkashi commented 2 years ago

Can you solve your problem? @AlverGant

AlverGant commented 2 years ago

@givkashi unfortunately no

kiashann commented 2 years ago

As far as I know this is the only project to do image retargeting with deep-learning. Really interested to see it working.. Done with all requirements Donwloaded vgg16.npy and vgg16.py from https://github.com/machrisaa/tensorflow-vgg in VGG_MODEL folder commented out all assert instructions from vgg16.py Now stuck with this error

ubuntu@vega:~/Cycle-IR$ python3 CycleIR.py npy file loaded build model started Traceback (most recent call last): File "CycleIR.py", line 204, in tf.app.run() File "/home/ubuntu/.local/lib/python3.6/site-packages/tensorflow/python/platform/app.py", line 126, in run _sys.exit(main(argv)) File "CycleIR.py", line 190, in main opt_g, aspect_ratio, images, CycleLoss, images_LR, AttentionMap, input_size, Sh, Sw = build_graph() File "CycleIR.py", line 93, in build_graph Sh, Sw, AttentionMap = CycleIR(images, reuse=False) File "CycleIR.py", line 27, in CycleIR vgg.build(images) File "/home/ubuntu/Cycle-IR/VGG_MODEL/vgg16.py", line 69, in build self.fc6 = self.fc_layer(self.pool5, "fc6") File "/home/ubuntu/Cycle-IR/VGG_MODEL/vgg16.py", line 106, in fc_layer dim = d TypeError: unsupported operand type(s) for =: 'int' and 'NoneType'

Did you find any solution for train this code? I can't find train_CycleIR.py file in this repository