def test_forward1(self):
x = np.random.randn(1, 3, 224, 224).astype('f')
_model = chainer.links.VGG16Layers(None)
_model.to_gpu()
with chainer.using_config('train', False):
with chainer.using_config('enable_backprop', False):
out_layer_name = 'fc8'
_y = _model.forward(x, [out_layer_name])[out_layer_name]
model = VGG16()
layers = _model.available_layers
for l in layers:
if "conv" in l or "fc" in l:
m1 = getattr(model, l)
m2 = getattr(_model, l)
m1.W.data = m2.W.data
m1.b.data = m2.b.data
if "fc" in l:
m1.W.data = m1.W.data.T
model.to_gpu()
with dezero.test_mode():
y = model(x)
self.assertTrue(array_allclose(y.data, _y.data))
def test_forward4(self):
N, C, H, W = 20, 10, 5, 5
x, gamma, beta, mean, var = get_params(N, C, H, W)
cy = CF.fixed_batch_normalization(x, gamma, beta, mean, var)
with dezero.test_mode():
y = F.batch_nrom(x, gamma, beta, mean, var)
self.assertTrue(array_allclose(y.data, cy.data))
def generate_image():
with dezero.test_mode():
fake_images = gen(test_z)
img = dezero.cuda.as_numpy(fake_images.data)
plt.figure()
for i in range(0, 25):
ax = plt.subplot(5, 5, i + 1)
ax.axis('off')
plt.imshow(img[i][0], 'gray')
plt.show()
def test_forward2(self):
N, C = 8, 3
cl = chainer.links.BatchNormalization(C)
l = dezero.layers.BatchNorm()
for i in range(10):
x, gamma, beta, mean, var = get_params(N, C)
cy = cl(x)
y = l(x)
self.assertTrue(array_allclose(cl.avg_mean, l.avg_mean.data))
self.assertTrue(array_allclose(cl.avg_var, l.avg_var.data))
with dezero.test_mode():
y = l(x)
with chainer.using_config('train', False):
cy = cl(x)
self.assertTrue(array_allclose(cy.data, y.data))
def test_backward1(self):
x = np.random.randn(2, 3, 224, 224).astype('f')
_model = chainer.links.VGG16Layers(None)
with chainer.using_config('train', False):
out_layer_name = 'fc8'
_y = _model.forward(x, [out_layer_name])[out_layer_name]
_y.grad = np.ones_like(_y.data)
_y.backward()
model = VGG16()
layers = _model.available_layers
for l in layers:
if "conv" in l or "fc" in l:
m1 = getattr(model, l)
m2 = getattr(_model, l)
m1.W.data = m2.W.data
m1.b.data = m2.b.data
if "fc" in l:
m1.W.data = m1.W.data.T
with dezero.test_mode():
y = model(x)
y.backward()
layers = _model.available_layers
for l in layers:
if "conv" in l:
m1 = getattr(model, l)
m2 = getattr(_model, l)
self.assertTrue(array_allclose(m1.W.data, m2.W.data))
self.assertTrue(array_allclose(m1.b.data, m2.b.data))
elif "fc" in l:
m1 = getattr(model, l)
m2 = getattr(_model, l)
self.assertTrue(array_allclose(m1.W.data, m2.W.data.T))
self.assertTrue(array_allclose(m1.b.data, m2.b.data))
if '__file__' in globals():
import os, sys
sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
import numpy as np
from PIL import Image
import dezero
from dezero.models import VGG16
url = 'https://github.com/oreilly-japan/deep-learning-from-scratch-3/raw/images/zebra.jpg'
img_path = dezero.utils.get_file(url)
img = Image.open(img_path)
x = VGG16.preprocess(img)
x = x[np.newaxis]
model = VGG16(pretrained=True)
with dezero.test_mode():
y = model(x)
predict_id = np.argmax(y.data)
model.plot(x, to_file='vgg.pdf')
labels = dezero.datasets.ImageNet.labels()
print(labels[predict_id])
def test_type1(self):
N, C = 8, 3
x, gamma, beta, mean, var = get_params(N, C)
with dezero.test_mode():
y = F.batch_nrom(x, gamma, beta, mean, var)
self.assertTrue(y.data.dtype == np.float32)
if "__file__" in globals():
import os, sys
sys.path.append(os.path.join(os.path.dirname(__file__), ".."))
import numpy as np
from dezero import test_mode
import dezero.functions as F
x = np.ones(5)
print(x)
# When training
y = F.dropout(x)
print(y)
# When testing (predicting)
with test_mode():
y = F.dropout(x)
print(y)
def test_forward2(self):
x = np.random.randn(100, 100)
with dezero.test_mode():
y = F.dropout(x)
res = array_equal(y.data, x)
self.assertTrue(res)