Using one convolutional-layer and two fully-connected-layers cost too much memory and also have bad performance for training, therefore I modify the model to two convolutional-layers and two narrow fully-connected-layers:
data = mx.sym.Variable('data')
conv1 = mx.sym.Convolution(data=data, kernel=(10, 10), stride=(2,2), num_filter=8)
bn1 = mx.sym.BatchNorm(data=conv1, fix_gamma=False, eps=2e-5, momentum=0.9, name="bn1")
tanh1 = mx.sym.Activation(data=bn1, act_type="relu")
conv2 = mx.sym.Convolution(data=tanh1, kernel=(10, 10), stride=(2,2), num_filter=8)
bn2 = mx.sym.BatchNorm(data=conv2, fix_gamma=False, eps=2e-5, momentum=0.9, name="bn2")
tanh2 = mx.sym.Activation(data=bn2, act_type="relu")
flatten = mx.sym.Flatten(data=tanh2)
fc1 = mx.sym.FullyConnected(data=flatten, num_hidden=100)
tanh3 = mx.sym.Activation(data=fc1, act_type="relu")
fc2 = mx.sym.FullyConnected(data=tanh3, num_hidden=3)
return mx.sym.SoftmaxOutput(data=fc2, name='softmax')
and training it by using learning rate “0.1” instead of “0.01” which may cause “overfit” in neural network.
Finally, the model occupied only 6MB disk space (It was more than 200MB before).
Now I could build a web site on a virtual machine of AliCloud (which is sponsored by Allen Mei, my old colleague) to let users uploading birds’ image and classifying it freely. To thank my sponsor, I named the web site “Allen’s bird” 🙂
In this web, I use angularjs and ngImgCrop plugin from “Alex Kaul”. They are powerful and convenient.
The append() operation of np.array() is very slow.
After replacing np.array() by normal python array, the training script could run much faster now.