You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: doc/lenet.txt
+1-1Lines changed: 1 addition & 1 deletion
Original file line number
Diff line number
Diff line change
@@ -404,7 +404,7 @@ to be compatible with our previous MLP implementation.
404
404
Note that the term convolution could corresponds to different mathematical operations.
405
405
1. theano.tensor.nnet.conv2d which is the most common one in almost all of the recent published convolutional models. In this op for each output feature map, all the input feature maps are summed together after being convolved with the filter.
406
406
2. Original LeNet model: In this work for each output feature map, only subset of input feature maps were selected.
407
-
3. The convolution used in signal processing: theano.tensor.signal.conv.conv2d
407
+
3. The convolution used in signal processing: theano.tensor.signal.conv.conv2d which works only on single channel inputs.
0 commit comments