Closed jackiechensuper closed 10 years ago
Fixed in latest commit. Thanks for pointing this out.
Dear Dr.Nitish, I have implemented an pretrained Auto-eocoder neural network based on your code, When I done the training, I got the trained weight and bias, but how can I get the predictions when testing on a different new image using the above weights? (just one feed forward calculation and got the prediction of final layer) Do you have a sample example? (sorry for my naive question since there are so many parameters and a explaining document would help a lot !) Many thanks Hao
Got it, many thanks!
Hi nitish, This is the error that when I ran the ae met, could you help me with that, many thanks!
Autoencoder 1 Train Step: 0Traceback (most recent call last): File "../../trainer.py", line 60, in
main()
File "../../trainer.py", line 54, in main
model.Train()
File "/home/hchen/deepnet/deepnet/neuralnet.py", line 632, in Train
losses = self.TrainOneBatch(step)
File "/home/hchen/deepnet/deepnet/neuralnet.py", line 330, in TrainOneBatch
losses2 = self.BackwardPropagate(step)
File "/home/hchen/deepnet/deepnet/neuralnet.py", line 316, in BackwardPropagate
loss = self.ComputeDown(node, step)
File "/home/hchen/deepnet/deepnet/neuralnet.py", line 234, in ComputeDown
self.UpdateLayerParams(layer, step)
File "/home/hchen/deepnet/deepnet/neuralnet.py", line 291, in UpdateLayerParams
layer.Update('bias', step, no_reg=True) # By default, do not regularize bias.
File "/home/hchen/deepnet/deepnet/parameter.py", line 84, in Update
w = self.params[param_name] # Parameter to be updated.
KeyError: 'bias'