When I first read about it was a little hard for me to believe that I could train a neural network with 7 lines of code. Like most people, I had a very natural reaction. “WTF!?! That’s impossible!” Practical Deep Learning For Coders Here I am, 10 minutes into the first lesson training , a convolutional neural network, to classify images of cats and dogs. That was insanely easy to do. Too easy in fact. VGG-16 Okay, maybe we are getting too far ahead of ourselves. With a 98% accuracy rate on the very first epoch, it was surprisingly accurate. “Aaron, you are a natural.” Yea thanks but I know that already. Did I really do anything extraordinary though? No. After taking a quick peek at the class that came with the rest of the code used for , it was apparent that was initializing an instance of a class that obfuscates the not so pretty parts of creating a neural net model. Vgg16 Practical Deep Learning For Coders vgg = Vgg16() For an example of what that looks like: def create(self):model = self.model = Sequential()model.add(Lambda(vgg_preprocess,input_shape=(3,224,224),output_shape=(3,224,224))) self.ConvBlock(2, 64) self.ConvBlock(2, 128) self.ConvBlock(3, 256) self.ConvBlock(3, 512) self.ConvBlock(3, 512) model.add(Flatten()) self.FCBlock() self.FCBlock() model.add(Dense(1000, activation='softmax')) fname = 'vgg16.h5' model.load\_weights(get\_file( fname, self.FILE\_PATH+fname, cache\_subdir='models' )) I am not going to pretend I know right now what 100% of this code means but from what I understand, it is initializing a and then defining the input, output, and hidden layers of that model. It is also loading pre-trained weights into the model. Keras Sequential model Okay so maybe I lied to myself about my so called natural talent when it comes to deep learning but I did fine tune and fit the model with the training and validation data. Okay so maybe I am lying about that too… That doesn’t take away from how awesome it feels to teach my computer how to differentiate between cats and dogs! vgg Out of curiosity, I decided to run this code on the data set from . Admittedly, my first submission didn’t do so well. Had I been three months earlier when this competition was still open, my score would have placed me at ~1100 out of the 1314 people already on the leader board. Seeing that my validation accuracy was 98%, I decided to investigate. Dogs vs. Cats Redux Kaggle After spending two hours ripping my hair out, I came upon this nasty little fellow: Log loss on kaggle. Kaggle uses this function to rank submissions. It turns out that when competing on Kaggle, it is a bad thing when a model is so confident about a picture being a cat that it labels it 0. This ends up breaking the LogLoss function on Kaggle leading to my abysmal score. So how can I make it better? Why not just force the extreme values of 0 and 1 to be 0.02 and 0.98 respectively? BAM. Just like that I go from ~1100 to ~500 putting me in the top 50% of the leader board. Okay you caught me. So maybe I had to rely on Jeremy (the guy teaching the course) to realize that my overconfident model was the problem. Details, details. Overall, training my first CNN was really fun. Can’t wait to begin lecture 2!
