def test18(self):
# Gradient check batchnorm backward pass
N, D = 2, 3
x = 5 * np.random.randn(N, D) + 12
gamma = np.random.randn(D)
beta = np.random.randn(D)
dout = np.random.randn(N, D)
bn_param = {'mode': 'train'}
fx = lambda x: batchnorm_forward(x, gamma, beta, bn_param)[0]
fg = lambda a: batchnorm_forward(x, gamma, beta, bn_param)[0]
fb = lambda b: batchnorm_forward(x, gamma, beta, bn_param)[0]
dx_num = eval_numerical_gradient_array(fx, x, dout)
da_num = eval_numerical_gradient_array(fg, gamma, dout)
db_num = eval_numerical_gradient_array(fb, beta, dout)
dmean_num = np.sum(dx_num, axis=0) * N
_, cache = batchnorm_forward(x, gamma, beta, bn_param)
dx, dgamma, dbeta = batchnorm_backward(dout, cache)
# print('dmean error: ', rel_error(dmean_num, dmean), dmean, dmean_num)
print('dx error: ', rel_error(dx_num, dx))
print('dgamma error: ', rel_error(da_num, dgamma))
print('dbeta error: ', rel_error(db_num, dbeta))
def test8(self):
np.random.seed(231)
x = np.random.randn(2, 3, 8, 8)
w = np.random.randn(3, 3, 3, 3)
b = np.random.randn(3, )
dout = np.random.randn(2, 3, 8, 8)
conv_param = {'stride': 1, 'pad': 1}
out, cache = conv_relu_forward(x, w, b, conv_param)
dx, dw, db = conv_relu_backward(dout, cache)
dx_num = eval_numerical_gradient_array(lambda x: conv_relu_forward(x, w, b, conv_param)[0], x, dout)
dw_num = eval_numerical_gradient_array(lambda w: conv_relu_forward(x, w, b, conv_param)[0], w, dout)
db_num = eval_numerical_gradient_array(lambda b: conv_relu_forward(x, w, b, conv_param)[0], b, dout)
print('Testing conv_relu:')
print('dx error: ', rel_error(dx_num, dx))
print('dw error: ', rel_error(dw_num, dw))
print('db error: ', rel_error(db_num, db))
def test2(self):
np.random.seed(231)
x = np.random.randn(4, 3, 5, 5)
w = np.random.randn(2, 3, 3, 3)
b = np.random.randn(2, )
dout = np.random.randn(4, 2, 5, 5)
conv_param = {'stride': 1, 'pad': 1}
dx_num = eval_numerical_gradient_array(lambda x: conv_forward_naive(x, w, b, conv_param)[0], x, dout)
dw_num = eval_numerical_gradient_array(lambda w: conv_forward_naive(x, w, b, conv_param)[0], w, dout)
db_num = eval_numerical_gradient_array(lambda b: conv_forward_naive(x, w, b, conv_param)[0], b, dout)
out, cache = conv_forward_naive(x, w, b, conv_param)
dx, dw, db = conv_backward_naive(dout, cache)
# Your errors should be around 1e-8'
print('Testing conv_backward_naive function')
print('dx error: ', rel_error(dx, dx_num))
print('dw error: ', rel_error(dw, dw_num))
print('db error: ', rel_error(db, db_num))
def test2(self):
np.random.seed(231)
x = np.random.randn(10, 2, 3)
w = np.random.randn(6, 5)
b = np.random.randn(5)
dout = np.random.randn(10, 5)
dx_num = eval_numerical_gradient_array(
lambda x: fc_forward(x, w, b)[0], x, dout)
dw_num = eval_numerical_gradient_array(
lambda w: fc_forward(x, w, b)[0], w, dout)
db_num = eval_numerical_gradient_array(
lambda b: fc_forward(x, w, b)[0], b, dout)
_, cache = fc_forward(x, w, b)
dx, dw, db = fc_backward(dout, cache)
# The error should be around 1e-10
print('Testing fc_backward function:')
print('dx error: ', rel_error(dx_num, dx))
print('dw error: ', rel_error(dw_num, dw))
print('db error: ', rel_error(db_num, db))
def test4(self):
np.random.seed(231)
x = np.random.randn(3, 2, 8, 8)
dout = np.random.randn(3, 2, 4, 4)
pool_param = {'pool_height': 2, 'pool_width': 2, 'stride': 2}
dx_num = eval_numerical_gradient_array(lambda x: max_pool_forward_naive(x, pool_param)[0], x, dout)
out, cache = max_pool_forward_naive(x, pool_param)
dx = max_pool_backward_naive(dout, cache)
# Your error should be around 1e-12
print('Testing max_pool_backward_naive function:')
print('dx error: ', rel_error(dx, dx_num))
def test5(self):
from stats232a.layer_utils import fc_relu_forward, fc_relu_backward
np.random.seed(231)
x = np.random.randn(2, 3, 4)
w = np.random.randn(12, 10)
b = np.random.randn(10)
dout = np.random.randn(2, 10)
out, cache = fc_relu_forward(x, w, b)
dx, dw, db = fc_relu_backward(dout, cache)
dx_num = eval_numerical_gradient_array(
lambda x: fc_relu_forward(x, w, b)[0], x, dout)
dw_num = eval_numerical_gradient_array(
lambda w: fc_relu_forward(x, w, b)[0], w, dout)
db_num = eval_numerical_gradient_array(
lambda b: fc_relu_forward(x, w, b)[0], b, dout)
print('Testing affine_relu_forward:')
print('dx error: ', rel_error(dx_num, dx))
print('dw error: ', rel_error(dw_num, dw))
print('db error: ', rel_error(db_num, db))
def test4(self):
np.random.seed(231)
x = np.random.randn(10, 10)
dout = np.random.randn(*x.shape)
dx_num = eval_numerical_gradient_array(lambda x: relu_forward(x)[0], x,
dout)
_, cache = relu_forward(x)
dx = relu_backward(dout, cache)
# The error should be around 3e-12
print('Testing relu_backward function:')
print('dx error: ', rel_error(dx_num, dx))
correct_out = np.array([[ 1.49834967, 1.70660132, 1.91485297],
[ 3.25553199, 3.5141327, 3.77273342]])
# Compare your output with ours. The error should be around 1e-9.
print('Testing fc_forward function:')
print('difference: ', rel_error(out, correct_out))
# Test the fc_backward function
np.random.seed(231)
x = np.random.randn(10, 2, 3)
w = np.random.randn(6, 5)
b = np.random.randn(5)
dout = np.random.randn(10, 5)
dx_num = eval_numerical_gradient_array(lambda x: fc_forward(x, w, b)[0], x, dout)
dw_num = eval_numerical_gradient_array(lambda w: fc_forward(x, w, b)[0], w, dout)
db_num = eval_numerical_gradient_array(lambda b: fc_forward(x, w, b)[0], b, dout)
_, cache = fc_forward(x, w, b)
dx, dw, db = fc_backward(dout, cache)
# The error should be around 1e-10
print('Testing fc_backward function:')
print('dx error: ', rel_error(dx_num, dx))
print('dw error: ', rel_error(dw_num, dw))
print('db error: ', rel_error(db_num, db))
# Test the relu_forward function
x = np.linspace(-0.5, 0.5, num=12).reshape(3, 4)