def test_convolution_layer(input_data):
W = np.random.randn(1, 3, 2, 2)
b = np.random.randn(1)
myconv = Convolution(W, b)
myresult = myconv.forward(input_data)
bookconv = book_layers.Convolution(W, b)
bookconvresult = bookconv.forward(input_data)
print(f"test result of test_convolution_layer: {(myresult==bookconvresult).all()}")
def test_convolution_backward(input_data):
W = np.random.randn(1, 3, 2, 2)
b = np.random.randn(1)
myconv = Convolution(W, b)
myresult = myconv.forward(input_data)
bookconv = book_layers.Convolution(W, b)
bookconvresult = bookconv.forward(input_data)
dx = np.random.randn(*myresult.shape)
dx2 = dx.copy()
my_b_r = myconv.backward(dx)
book_b_r = bookconv.backward(dx2)
#print(my_b_r)
#print(book_b_r)
different = (my_b_r-book_b_r)
print(f"test result of test_pooling_layer: {different.max()<1e-10}")
network = SimpleConvNet(input_dim=(1,28,28),
conv_param = {'filter_num':30, 'filter_size':5, 'pad':0, 'stride':1},
hidden_size=100, output_size=10, weight_init_std=0.01)
# 学習後の重み
network.load_params("params.pkl")
filter_show(network.params['W1'], 16)
img = imread('../data/lena_gray.png')
img = img.reshape(1, 1, *img.shape)
fig = plt.figure()
w_idx = 1
for i in range(16):
w = network.params['W1'][i]
b = 0 # network.params['b1'][i]
w = w.reshape(1, *w.shape)
#b = b.reshape(1, *b.shape)
conv_layer = Convolution(w, b)
out = conv_layer.forward(img)
out = out.reshape(out.shape[2], out.shape[3])
ax = fig.add_subplot(4, 4, i+1, xticks=[], yticks=[])
ax.imshow(out, cmap=plt.cm.gray_r, interpolation='nearest')
plt.show()
from keras import backend as K
import warnings
warnings.filterwarnings('ignore')
inputs = np.random.uniform(size=(10, 3, 30, 30))
params = {
'kernel_h': 5,
'kernel_w': 5,
'pad': 0,
'stride': 2,
'in_channel': inputs.shape[1],
'out_channel': 64,
}
layer = Convolution(params)
out = layer.forward(inputs)
keras_model = keras.Sequential()
keras_layer = layers.Conv2D(filters=params['out_channel'],
kernel_size=(params['kernel_h'],
params['kernel_w']),
strides=(params['stride'], params['stride']),
padding='valid',
data_format='channels_first',
input_shape=inputs.shape[1:])
keras_model.add(keras_layer)
sgd = optimizers.SGD(lr=0.01)
keras_model.compile(loss='mean_squared_error', optimizer='sgd')
weights = np.transpose(layer.weights, (2, 3, 1, 0))
keras_layer.set_weights([weights, layer.bias])
keras_out = keras_model.predict(inputs, batch_size=inputs.shape[0])