def test_maxout(): network = N.Network() network.setInput(N.RawInput((1, 28, 28))) network.append(N.Conv2d(filter_size=(3, 3), feature_map_multiplier=128)) network.append(N.FeaturePooling(4)) network.append(N.Pooling((2, 2))) network.append(N.Conv2d(filter_size=(3, 3), feature_map_multiplier=8)) network.append(N.FeaturePooling(4)) network.append(N.Pooling((2, 2))) network.append(N.Conv2d(filter_size=(3, 3), feature_map_multiplier=8)) network.append(N.FeaturePooling(4)) network.append(N.GlobalPooling()) network.append(N.FullConn(input_feature=128, output_feature=10)) network.append(N.SoftMax()) network.build() trX, trY, teX, teY = l.load_mnist() for i in range(5000): print(i) network.train(trX, trY) print(1 - np.mean( np.argmax(teY, axis=1) == np.argmax(network.predict(teX), axis=1)))
def test1(): network = N.Network() network.debug = True network.setInput((28, 28)) network.append(N.Conv2d(filter=(3, 3), input_feature=1, output_feature=32)) network.append(N.Relu()) network.append(N.Conv2d(filter=(3, 3), input_feature=32, output_feature=32)) network.append(N.Relu()) network.append(N.Conv2d(filter=(3, 3), input_feature=32, output_feature=32)) network.append(N.Relu()) network.append(N.Pooling((2, 2))) network.append(N.Conv2d(filter=(3, 3), input_feature=32, output_feature=64)) network.append(N.Relu()) network.append(N.Conv2d(filter=(3, 3), input_feature=64, output_feature=64)) network.append(N.Relu()) network.append(N.Conv2d(filter=(3, 3), input_feature=64, output_feature=64)) network.append(N.Relu()) network.append(N.Pooling((2, 2))) network.append( N.Conv2d(filter=(3, 3), input_feature=64, output_feature=128)) network.append(N.Relu()) network.append( N.Conv2d(filter=(3, 3), input_feature=128, output_feature=128)) network.append(N.Relu()) network.append( N.Conv2d(filter=(3, 3), input_feature=128, output_feature=128)) network.append(N.Relu()) network.append(N.Pooling((2, 2))) network.append(N.Flatten()) network.append(N.FullConn(input_feature=1152, output_feature=1152 * 2)) network.append(N.Relu()) network.append(N.FullConn(input_feature=1152 * 2, output_feature=10)) network.append(N.SoftMax()) #network.setCost(N.CategoryCrossEntropy) network.build() f = h5py.File('/hdd/home/yueguan/workspace/data/mnist/mnist.hdf5', 'r') trX = f['x_train'][:, :].reshape(-1, 1, 28, 28) teX = f['x_test'][:, :].reshape(-1, 1, 28, 28) trY = np.zeros((f['t_train'].shape[0], 10)) trY[np.arange(len(f['t_train'])), f['t_train']] = 1 teY = np.zeros((f['t_test'].shape[0], 10)) teY[np.arange(len(f['t_test'])), f['t_test']] = 1 for i in range(5000): print(i) network.train(trX, trY) print(1 - np.mean(np.argmax(teY, axis=1) == network.predict(teX)))
def test_pooling_forward(self): x = np.asarray(rng.uniform(low=-1, high=1, size=(500, 20, 28, 28))) x = theano.shared(x, borrow=True) pooling = N.Pooling() y = pooling.forward([x]) y_shape = y[0].eval().shape self.assertEqual(y_shape, (500, 20, 14, 14))
def test(): network = N.Network() network.debug = True network.setInput(N.RawInput((1, 28,28))) network.append(N.Conv2d(feature_map_multiplier=32)) network.append(N.Relu()) network.append(N.Pooling()) network.append(N.Conv2d(feature_map_multiplier=2)) network.append(N.Relu()) network.append(N.Pooling()) network.append(UpConv2d(feature_map_multiplier=2)) network.append(N.Relu()) network.append(UpConv2d(feature_map_multiplier=32)) network.append(N.Relu()) #network.append(N.Flatten()) #network.append(N.FullConn(input_feature=1152, output_feature=1152*2)) #network.append(N.Relu()) #network.append(N.FullConn(input_feature=1152*2, output_feature=10)) #network.append(N.SoftMax()) network.costFunction = cost.ImageSSE network.inputOutputType = (T.tensor4(), T.tensor4(),) network.build() f = h5py.File('/hdd/home/yueguan/workspace/data/mnist/mnist.hdf5', 'r') trX = f['x_train'][:,:].reshape(-1, 1, 28, 28) teX = f['x_test'][:,:].reshape(-1, 1, 28, 28) trY = np.zeros((f['t_train'].shape[0], 10)) trY[np.arange(len(f['t_train'])), f['t_train']] = 1 teY = np.zeros((f['t_test'].shape[0], 10)) teY[np.arange(len(f['t_test'])), f['t_test']] = 1 for i in range(5000): print(i) #network.train(trX, trY) #print(1 - np.mean(np.argmax(teY, axis=1) == np.argmax(network.predict(teX), axis=1))) network.train(trX, trX) print(np.sum((teX - network.predict(teX)) * (teX - network.predict(teX))))
def test_binaryweight(): network = N.Network() network.debug = True network.setInput(N.RawInput((1, 28,28))) network.append(N.Conv2d(feature_map_multiplier=32)) network.append(N.Relu()) network.append(N.Pooling((2,2))) network.append(Binarize()) network.append(N.Conv2d(feature_map_multiplier=2)) network.append(N.Relu()) network.append(N.Pooling((2,2))) network.append(Binarize()) network.append(BinaryConv2d(feature_map_multiplier=2)) network.append(N.Relu()) network.append(N.Pooling((2,2))) network.append(N.Flatten()) network.append(N.FullConn(input_feature=1152, output_feature=1152*2)) network.append(N.Relu()) network.append(N.FullConn(input_feature=1152*2, output_feature=10)) network.append(N.SoftMax()) network.build() f = h5py.File('/hdd/home/yueguan/workspace/data/mnist/mnist.hdf5', 'r') trX = f['x_train'][:,:].reshape(-1, 1, 28, 28) teX = f['x_test'][:,:].reshape(-1, 1, 28, 28) trY = np.zeros((f['t_train'].shape[0], 10)) trY[np.arange(len(f['t_train'])), f['t_train']] = 1 teY = np.zeros((f['t_test'].shape[0], 10)) teY[np.arange(len(f['t_test'])), f['t_test']] = 1 for i in range(5000): print(i) network.train(trX, trY) print(1 - np.mean(np.argmax(teY, axis=1) == np.argmax(network.predict(teX), axis=1)))
def test_pooling_forwardSize(self): x = [(100, 1, 28, 28)] pool = N.Pooling() y = pool.forwardSize(x) self.assertEqual(y, [(100, 1, 14, 14)])