search

pietrocarbo / deep-transfer

PyTorch implementation of "Universal Style Transfer via Feature Trasforms"
Apache License 2.0
87 stars 19 forks source link

TypeError: <lambda>() got an unexpected keyword argument 'dtype' #8

Open athulvingt opened 4 years ago

athulvingt commented 4 years ago

File "stylize.py", line 126, in main() File "stylize.py", line 51, in main ss_stride=args.ss_stride) File "/media/katomaran/512GB SSD/WCT-TF-master/wct.py", line 34, in init ss_patch_size=self.ss_patch_size, ss_stride=self.ss_stride) File "/media/katomaran/512GB SSD/WCT-TF-master/model.py", line 62, in init self.vgg_model = vgg_from_t7(vgg_path, target_layer=deepest_target) File "/media/katomaran/512GB SSD/WCT-TF-master/vgg_normalised.py", line 38, in vgg_from_t7 trainable=False)(x) File "/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py", line 463, in call self.build(unpack_singleton(input_shapes)) File "/usr/local/lib/python3.6/dist-packages/keras/layers/convolutional.py", line 141, in build constraint=self.kernel_constraint) File "/usr/local/lib/python3.6/dist-packages/keras/engine/base_layer.py", line 279, in add_weight weight = K.variable(initializer(shape, dtype=dtype), TypeError: () got an unexpected keyword argument 'dtype'

christianjcc commented 4 years ago

Hi athulvingt, I seem to be running into the same issue has you had experience, ever figure out how to resolve the problem? Any suggestions would be great, thanks.