CS231
CS231 copied to clipboard
cthorey
My corrections for the Standford class assingments CS231n - Convolutional Neural Networks for Visual Recognition
Hey @cthorey , I recently went through your batch normalization tutorial here: [What does gradient flowing through ...](http://cthorey.github.io./backpropagation/) . First of, thank you so much for such an amazing post...
The functions `compute_distances_two_loops` `compute_distances_one_loops` `compute_distances_no_loops` all are required to compute the L2 distance so the dists matrix should be prepended by `np.sqrt` in all the cases
If you change it to key you will see significantly slower conversion. Looks like this typo comes from the original class though. https://github.com/cthorey/CS231/blob/11f0521c4f7865a0005f21bb24ec29c8b00c2712/assignment2/cs231n/classifiers/cnn.py#L143 Should be: bn_param['mode'] = mode
in function compute_distances_no_loops(self, X) T = np.sum(X**2,axis = 1) F = np.sum(self.X_train**2,axis = 1).T F = np.tile(F,(500,5000)) FT = X.dot(self.X_train.T) print T.shape,F.shape,FT.shape,X.shape,self.X_train.shape dists = T+F-2*FT` the code `F = np.tile(F,(500,5000))`...
In order to predict labels. Just simple use like y_predict[i]=np.argmax(np.bincount(closest_y))
When full connected net has more than 3 layers, the backporp gradient and numerical gradient show significant difference. This issue could be reproduced in the `Dropout.ipynb` (in the cell `Fully-connected...
