marcellacornia
commented
6 years ago Hi @MartaCollPol, thanks for downloading our code.
Which Keras version are you using? Our code is compatible with Keras 1.1.0 using Theano as backend. Be sure to have "image_dim_ordering": "th" and "backend": "theano" in your keras.json file.
MartaCollPol
Hello, I'm trying to use your model for testing a dataset but a strange error is raised when loading the model, do you have any idea on which could be the cause? Thank you in advance!
Traceback (most recent call last): File "main.py", line 43, in
model = ml_net_model(img_cols=shape_c, img_rows=shape_r, downsampling_factor_product=10)
File "/home/marta/Documents/Recerca_2017/TFG/MLNet/model.py", line 78, in ml_net_model
eltprod = EltWiseProduct(init='zero', W_regularizer=l2(1/(rows_eltcols_elt)))(pre_final_conv)
File "/home/marta/Documents/Recerca_2017/TFG/virualenv/MLNetenv/local/lib/python2.7/site-packages/keras/engine/topology.py", line 514, in call
self.add_inbound_node(inbound_layers, node_indices, tensor_indices)
File "/home/marta/Documents/Recerca_2017/TFG/virualenv/MLNetenv/local/lib/python2.7/site-packages/keras/engine/topology.py", line 572, in add_inbound_node
Node.create_node(self, inbound_layers, node_indices, tensor_indices)
File "/home/marta/Documents/Recerca_2017/TFG/virualenv/MLNetenv/local/lib/python2.7/site-packages/keras/engine/topology.py", line 149, in create_node
output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0]))
File "/home/marta/Documents/Recerca_2017/TFG/MLNet/eltwise_product.py", line 56, in call
output = xT.nnet.abstract_conv.bilinear_upsampling(K.expand_dims(K.expand_dims(1 + self.W, 0), 0), self.downsampling_factor, 1, 1)
File "/home/marta/Documents/Recerca_2017/TFG/virualenv/MLNetenv/local/lib/python2.7/site-packages/theano/tensor/nnet/abstract_conv.py", line 1900, in bilinear_upsampling
raise ValueError("can't use ratio and frac_ratio together")
ValueError: can't use ratio and frac_ratio together