def __init__(self, dtype=np.float32, reshape_torch=False):
"""
Initializes a new LeNet inspired network
Args:
dtype: Datatype to be used
reshape_torch: set this, if the training parameters came from Pytorch which requires a custom reshape
"""
self.reshape_torch = reshape_torch
r1 = ReshapeLayer(newshape=[-1, 28, 28, 1])
cn1 = Conv2dLayer(in_channels=1, out_channels=16, kernel_size=3, activation='relu',
dtype=np.float32) # [? 28 28 16]
mp1 = MaxPool2dLayer(size=2) # [? 14 14 16]
cn2 = Conv2dLayer(in_channels=16, out_channels=32, kernel_size=3, activation='relu') # [? 14 14 32]
mp2 = MaxPool2dLayer(size=2) # [? 7 7 32]
if reshape_torch:
r2 = CustomReshapeLayer(custom_reshape_func=CustomReshapeLayer.reshape_for_torch)
else:
r2 = ReshapeLayer(newshape=[-1, 32 * 7 * 7])
fc1 = FullyConnectedLayer(input_size=32 * 7 * 7, output_size=32, activation='relu', dtype=np.float32)
fc2 = FullyConnectedLayer(input_size=32, output_size=10, activation='softmax')
# Store a reference to each layer
self.r1 = r1
self.cn1 = cn1
self.mp1 = mp1
self.cn2 = cn2
self.mp2 = mp2
self.r2 = r2
self.fc1 = fc1
self.fc2 = fc2
self.lenet_layers = [r1, cn1, mp1, cn2, mp2, r2, fc1, fc2]
super(LeNet, self).__init__(self.lenet_layers)
def test_conv(self):
cl = Conv2dLayer(in_channels=1, out_channels=3, kernel_size=5)
test_img = np.random.rand(4, 28, 28, 1) # create 4 test images
cl_out = cl.__call__(test_img)
# Check Shape
self.assertEqual(cl_out.shape, (4, 28, 28, 3))
def test_tf_compare2(self):
# kernel = test_kernel_gauss(size=5, sigma=1.6)
# kernel = kernel[..., np.newaxis, np.newaxis]
kernel = np.random.rand(5, 5, 8, 16)
b = np.zeros(16)
x = np.random.rand(5, 28, 28, 8) # create 4 test images
y_tf = conv2d(x, kernel, strides=1, padding='same')
y_tf = y_tf.numpy() # calculate numpy array
cl = Conv2dLayer(in_channels=8, out_channels=16, kernel_size=5)
cl.kernel = kernel
cl.b = b
y = cl(x)
self.assertEqual(y_tf.shape, y.shape)
self.assertTrue(np.allclose(y_tf, y))
for v1, v2 in zip(y_tf.flatten(), y.flatten()):
self.assertAlmostEqual(v1, v2, delta=0.001)
def test_tf_compare_zero(self):
kernel = np.zeros(shape=(5, 5, 8, 16))
b = np.zeros(16)
x = np.random.rand(5, 28, 28, 8) # create 4 test images
y_tf = conv2d(x, kernel, strides=1, padding='same')
y_tf = y_tf.numpy() # calculate numpy array
cl = Conv2dLayer(in_channels=1, out_channels=3, kernel_size=5)
cl.kernel = kernel
cl.b = b
y = cl(x)
self.assertEqual(y_tf.shape, y.shape)
self.assertTrue(np.allclose(y_tf, y))
for v1, v2 in zip(y_tf.flatten(), y.flatten()):
self.assertAlmostEqual(v1, 0, delta=0.0001)
self.assertAlmostEqual(v2, 0, delta=0.0001)
def test_blur(self):
k = make_gauss_kernel()
cl = Conv2dLayer(in_channels=1, out_channels=1, kernel_size=5)
loader = MnistDataDownloader("../../test/MNIST/")
path_img, path_lbl = loader.get_path(DataSetType.TRAIN)
reader = MnistDataReader(path_img, path_lbl)
for lbl, img in reader.get_next(4):
img = img.astype(np.float) / 255.0
img = np.reshape(img, newshape=[-1, 28, 28, 1])
k = np.reshape(k, newshape=[k.shape[0], k.shape[1], 1, 1])
cl.kernel = k
img_out = cl(img)
# Check the dimensions
self.assertEqual(img_out.shape, (4, 28, 28, 1))
# Uncomment to see the image
img_out = np.reshape(img_out, newshape=[1, 4 * 28, 28, 1])
img_out = np.squeeze(img_out)
plt.imshow(img_out, cmap='gray', vmin=0.0, vmax=1.0)
plt.show()
break
def test_tensorflow_parameter_0(self):
r1 = ReshapeLayer(newshape=[-1, 28, 28, 1])
cn1 = Conv2dLayer(in_channels=1,
out_channels=16,
kernel_size=3,
activation='relu') # [? 28 28 16]
checkpoint_path = "test/training_1/cp.ckpt"
checkpoint_dir = os.path.abspath(os.path.dirname(checkpoint_path))
os.path.join(checkpoint_dir, "model_config.json")
if not os.path.exists(checkpoint_dir):
raise RuntimeError("There is no trained model data!")
# Reload the model from the 2 files we saved
with open(os.path.join(checkpoint_dir,
"model_config.json")) as json_file:
json_config = json_file.read()
model = keras.models.model_from_json(json_config)
model.load_weights(os.path.join(checkpoint_dir, "weights.h5"))
# Print a summary
Ws = model.get_weights()
# See Keras Documentation
# https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv2D
#
# Default ordering of weights for Conv: (batch, height, width, channels)
# Default ordering of weights for Dense
self.assertEqual(cn1.kernel.shape, Ws[0].shape)
self.assertEqual(cn1.b.shape, Ws[1].shape)
# Assign values
cn1.kernel = Ws[0]
cn1.b = Ws[1]
layers = [
r1,
cn1,
]
interesting_layers = [1] # don't care about reshape layers
n = Network(layers)
loader = MnistDataDownloader("../../test/MNIST/")
path_img, path_lbl = loader.get_path(DataSetType.TRAIN)
reader = MnistDataReader(path_img, path_lbl)
for lbls, imgs in reader.get_next(10):
imgs = imgs.astype(np.float) / 255.0
imgs_r = np.reshape(imgs, newshape=[-1, 28, 28, 1])
# Check the tensorflow model
y_keras = model.predict(imgs)
# Keras Model Debug
inp = model.input # input placeholder
outputs = [layer.output
for layer in model.layers] # all layer outputs
outputs = [outputs[i]
for i in (1, 2, 3, 4, 6, 8)] # remove dropout, reshape
functors = [K.function([inp], [out])
for out in outputs] # evaluation functions
layer_outs = [func([imgs, 1.]) for func in functors]
# print(layer_outs)
# Check the results of the own made NN
y, zs = n.forward_intermediate(imgs_r)
zs = [zs[i] for i in interesting_layers] # remove reshape layers
eps = 0.1
index = 0
for l_keras_out, l_out in zip(layer_outs, zs):
err = np.abs((l_keras_out - l_out).flatten())
# print(l_keras_out - l_out)
# err_image = 1.0 * (np.abs(l_keras_out - l_out) > eps)
# # err_image = np.reshape(err_image[], newshape=(1, -1, 28, 1))
# err_image = np.squeeze(err_image[0, :, :, 0])
# plt.imshow(err_image, vmin=0.0, vmax=1.0, cmap='gray')
# plt.show()
right_indices = indices(err < eps, lambda b: b)
false_indices = indices(err > eps, lambda b: b)
wrong_values = err[false_indices]
# print(wrong_values)
if not np.all(right_indices):
print("error in layer ", index)
index += 1
lbls_pred_keras = y_keras.argmax(axis=1)
lbls_pred = y.argmax(axis=1)
print("Original: ", lbls.reshape(-1))
print("Keras: ", lbls_pred_keras.reshape(-1))
print("Our Model: ", lbls_pred.reshape(-1))
break
def test_tensorflow_parameter(self):
r1 = ReshapeLayer(newshape=[-1, 28, 28, 1])
cn1 = Conv2dLayer(in_channels=1,
out_channels=16,
kernel_size=3,
activation='relu') # [? 28 28 16]
mp1 = MaxPool2dLayer(size=2) # [? 14 14 16]
cn2 = Conv2dLayer(in_channels=16,
out_channels=32,
kernel_size=3,
activation='relu') # [? 14 14 32]
mp2 = MaxPool2dLayer(size=2) # [? 7 7 32]
r2 = ReshapeLayer(newshape=[-1, 32 * 7 * 7])
fc1 = FullyConnectedLayer(input_size=32 * 7 * 7,
output_size=64,
activation='relu')
fc2 = FullyConnectedLayer(input_size=64,
output_size=10,
activation='softmax')
checkpoint_path = "test/training_1/cp.ckpt"
checkpoint_dir = os.path.abspath(os.path.dirname(checkpoint_path))
os.path.join(checkpoint_dir, "model_config.json")
if not os.path.exists(checkpoint_dir):
raise RuntimeError("There is no trained model data!")
# Reload the model from the 2 files we saved
with open(os.path.join(checkpoint_dir,
"model_config.json")) as json_file:
json_config = json_file.read()
model = keras.models.model_from_json(json_config)
model.load_weights(os.path.join(checkpoint_dir, "weights.h5"))
# Print a summary
Ws = model.get_weights()
# K0 = Ws[0]
# plt.imshow(K0[:,:,1,1], vmin=0.0, vmax=1.0, cmap='gray')
# plt.show()
# See Keras Documentation
# https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv2D
#
# Default ordering of weights for Conv: (batch, height, width, channels)
# Default ordering of weights for Dense
self.assertEqual(cn1.kernel.shape, Ws[0].shape)
self.assertEqual(cn1.b.shape, Ws[1].shape)
self.assertEqual(cn2.kernel.shape, Ws[2].shape)
self.assertEqual(cn2.b.shape, Ws[3].shape)
self.assertEqual(fc1.W.shape, Ws[4].shape)
self.assertEqual(fc1.b.shape, Ws[5].shape)
self.assertEqual(fc2.W.shape, Ws[6].shape)
self.assertEqual(fc2.b.shape, Ws[7].shape)
# Assign values
cn1.kernel = Ws[0]
cn1.b = Ws[1]
cn2.kernel = Ws[2]
cn2.b = Ws[3]
fc1.W = Ws[4]
fc1.b = Ws[5]
fc2.W = Ws[6]
fc2.b = Ws[7]
layers = [r1, cn1, mp1, cn2, mp2, r2, fc1, fc2]
interesting_layers = [1, 2, 3, 4, 6,
7] # don't care about reshape layers
net = Network(layers)
loader = MnistDataDownloader("../../test/MNIST/")
path_img, path_lbl = loader.get_path(DataSetType.TRAIN)
reader = MnistDataReader(path_img, path_lbl)
for lbls, imgs in reader.get_next(20):
imgs = imgs.astype(np.float) / 255.0
imgs_r = np.reshape(imgs, newshape=[-1, 28, 28, 1])
# Check the tensorflow model
y_keras = model.predict(imgs)
# Keras Model Debug
inp = model.input # input placeholder
outputs = [layer.output
for layer in model.layers] # all layer outputs
outputs = [outputs[i]
for i in (1, 2, 3, 4, 6, 8)] # remove dropout, reshape
functors = [K.function([inp], [out])
for out in outputs] # evaluation functions
layer_outs = [func([imgs, 1.]) for func in functors]
# print(layer_outs)
# Check the results of the own made NN
y, zs = net.forward_intermediate(imgs_r)
zs = [zs[i] for i in interesting_layers] # remove reshape layers
eps = 0.1
index = 0
for l_keras_out, l_out in zip(layer_outs, zs):
l_keras_out = l_keras_out[0] # why ever
err = np.abs((l_keras_out - l_out))
# err_subs = ind2sub(indices(err.flatten(), lambda x: x > 1), l_out.shape)
# self.assertTrue(np.allclose(l_out, l_keras_out))
#print(l_keras_out - l_out)
# img_keras = np.squeeze()
# err_image = 1.0 * (np.abs(l_keras_out - l_out) > eps)
# Test: Shift l_out
# l_out[:, 0:-1, 0:-1, :] = l_out[:, 1:, 1:, :]
# err_image = l_keras_out - l_out
# # err_image = np.reshape(err_image, newshape=(1, 28, 28, 1))
# # err_image = np.squeeze(err_image[0, :, :, 0])
# err_image = np.concatenate([np.squeeze(err_image[0, :, :, i]) for i in range(4)], axis=1)
# img_keras = np.concatenate([np.squeeze(l_keras_out[0, :, :, i]) for i in range(4)], axis=1)
# img_nn = np.concatenate([np.squeeze(l_out[0, :, :, i]) for i in range(4)], axis=1)
# img = np.concatenate([img_nn, img_keras, err_image], axis=0)
#
# fig, ax = plt.subplots()
# _im = ax.imshow(img, cmap='gray')
# ax.set_title('Computation Layer {}'.format(index))
# ax.set_yticks([14, 14 + 28, 14 + 2 * 28])
# ax.set_yticklabels(['Our NN', 'Keras', 'Difference'])
# fig.colorbar(_im)
# plt.show()
#right_indices = indices(err < eps, lambda b: b)
#false_indices = indices(err > eps, lambda b: b)
#wrong_values = err[false_indices]
#print(wrong_values)
if not np.allclose(l_out, l_keras_out, atol=0.0001):
print("error in layer ", index)
breakpoint()
index += 1
lbls_pred_keras = y_keras.argmax(axis=1)
lbls_pred = y.argmax(axis=1)
print("Original: ", lbls.reshape(-1))
print("Keras: ", lbls_pred_keras.reshape(-1))
print("Our Model: ", lbls_pred.reshape(-1))
break