def _convert_to_nn(self, svm_model, y_train, x_val):
#convert to linear NN
print('converting {} model to linear NN'.format(
self.__class__.__name__))
W = svm_model.coef_.T
B = svm_model.intercept_
if numpy.unique(y_train).size == 2:
linear_layer = Linear(W.shape[0], 2)
linear_layer.W = numpy.concatenate([-W, W], axis=1)
linear_layer.B = numpy.concatenate([-B, B], axis=0)
else:
linear_layer = Linear(*(W.shape))
linear_layer.W = W
linear_layer.B = B
svm_model = self.model
nn_model = Sequential([Flatten(), linear_layer])
if not self.use_gpu: nn_model.to_numpy()
#sanity check model conversion
self._sanity_check_model_conversion(svm_model, nn_model, x_val)
print('model conversion sanity check passed')
return nn_model
def test_Linear(self):
np.random.seed(42)
torch.manual_seed(42)
batch_size, n_in, n_out = 2, 3, 4
for _ in range(100):
# layers initialization
torch_layer = torch.nn.Linear(n_in, n_out)
custom_layer = Linear(n_in, n_out)
custom_layer.W = torch_layer.weight.data.numpy()
custom_layer.b = torch_layer.bias.data.numpy()
layer_input = np.random.uniform(
-10, 10, (batch_size, n_in)).astype(np.float32)
next_layer_grad = np.random.uniform(
-10, 10, (batch_size, n_out)).astype(np.float32)
# 1. check layer output
custom_layer_output = custom_layer.updateOutput(layer_input)
layer_input_var = Variable(torch.from_numpy(layer_input),
requires_grad=True)
torch_layer_output_var = torch_layer(layer_input_var)
self.assertTrue(
np.allclose(torch_layer_output_var.data.numpy(),
custom_layer_output,
atol=1e-6))
# 2. check layer input grad
custom_layer_grad = custom_layer.updateGradInput(
layer_input, next_layer_grad)
torch_layer_output_var.backward(torch.from_numpy(next_layer_grad))
torch_layer_grad_var = layer_input_var.grad
self.assertTrue(
np.allclose(torch_layer_grad_var.data.numpy(),
custom_layer_grad,
atol=1e-6))
# 3. check layer parameters grad
custom_layer.accGradParameters(layer_input, next_layer_grad)
weight_grad = custom_layer.gradW
bias_grad = custom_layer.gradb
torch_weight_grad = torch_layer.weight.grad.data.numpy()
torch_bias_grad = torch_layer.bias.grad.data.numpy()
self.assertTrue(
np.allclose(torch_weight_grad, weight_grad, atol=1e-6))
self.assertTrue(np.allclose(torch_bias_grad, bias_grad, atol=1e-6))
def _read_txt_helper(path):
with open(path,'rb') as f:
content = f.read().split('\n')
modules = []
c = 0
line = content[c]
while len(line) > 0:
if line.startswith(Linear.__name__): # @UndefinedVariable import error suppression for PyDev users
'''
Format of linear layer
Linear <rows_of_W> <columns_of_W>
<flattened weight matrix W>
<flattened bias vector>
'''
_,m,n = line.split(); m = int(m); n = int(n)
layer = Linear(m,n)
layer.W = np.array([float(weightstring) for weightstring in content[c+1].split() if len(weightstring) > 0]).reshape((m,n))
layer.B = np.array([float(weightstring) for weightstring in content[c+2].split() if len(weightstring) > 0])
modules.append(layer)
c+=3 # the description of a linear layer spans three lines
elif line.startswith(Convolution.__name__): # @UndefinedVariable import error suppression for PyDev users
'''
Format of convolution layer
Convolution <rows_of_W> <columns_of_W> <depth_of_W> <number_of_filters_W> <stride_axis_0> <stride_axis_1>
<flattened filter block W>
<flattened bias vector>
'''
_,h,w,d,n,s0,s1 = line.split()
h = int(h); w = int(w); d = int(d); n = int(n); s0 = int(s0); s1 = int(s1)
layer = Convolution(filtersize=(h,w,d,n), stride=(s0,s1))
layer.W = np.array([float(weightstring) for weightstring in content[c+1].split() if len(weightstring) > 0]).reshape((h,w,d,n))
layer.B = np.array([float(weightstring) for weightstring in content[c+2].split() if len(weightstring) > 0])
modules.append(layer)
c+=3 #the description of a convolution layer spans three lines
elif line.startswith(SumPool.__name__): # @UndefinedVariable import error suppression for PyDev users
'''
Format of sum pooling layer
SumPool <mask_heigth> <mask_width> <stride_axis_0> <stride_axis_1>
'''
_,h,w,s0,s1 = line.split()
h = int(h); w = int(w); s0 = int(s0); s1 = int(s1)
layer = SumPool(pool=(h,w),stride=(s0,s1))
modules.append(layer)
c+=1 # one line of parameterized layer description
elif line.startswith(MaxPool.__name__): # @UndefinedVariable import error suppression for PyDev users
'''
Format of max pooling layer
MaxPool <mask_heigth> <mask_width> <stride_axis_0> <stride_axis_1>
'''
_,h,w,s0,s1 = line.split()
h = int(h); w = int(w); s0 = int(s0); s1 = int(s1)
layer = MaxPool(pool=(h,w),stride=(s0,s1))
modules.append(layer)
c+=1 # one line of parameterized layer description
elif line.startswith(Flatten.__name__): # @UndefinedVariable import error suppression for PyDev users
modules.append(Flatten()) ; c+=1 #one line of parameterless layer description
elif line.startswith(Rect.__name__): # @UndefinedVariable import error suppression for PyDev users
modules.append(Rect()) ; c+= 1 #one line of parameterless layer description
elif line.startswith(Tanh.__name__): # @UndefinedVariable import error suppression for PyDev users
modules.append(Tanh()) ; c+= 1 #one line of parameterless layer description
elif line.startswith(SoftMax.__name__): # @UndefinedVariable import error suppression for PyDev users
modules.append(SoftMax()) ; c+= 1 #one line of parameterless layer description
else:
raise ValueError('Layer type identifier' + [s for s in line.split() if len(s) > 0][0] + ' not supported for reading from plain text file')
#skip info of previous layers, read in next layer header
line = content[c]
return Sequential(modules)
def _read_txt_helper(path):
with open(path, 'rb') as f:
content = f.read().split('\n')
modules = []
c = 0
line = content[c]
while len(line) > 0:
if line.startswith(
Linear.__name__
): # @UndefinedVariable import error suppression for PyDev users
'''
Format of linear layer
Linear <rows_of_W> <columns_of_W>
<flattened weight matrix W>
<flattened bias vector>
'''
_, m, n = line.split()
m = int(m)
n = int(n)
layer = Linear(m, n)
layer.W = np.array([
float(weightstring)
for weightstring in content[c + 1].split()
if len(weightstring) > 0
]).reshape((m, n))
layer.B = np.array([
float(weightstring)
for weightstring in content[c + 2].split()
if len(weightstring) > 0
])
modules.append(layer)
c += 3 # the description of a linear layer spans three lines
elif line.startswith(
Convolution.__name__
): # @UndefinedVariable import error suppression for PyDev users
'''
Format of convolution layer
Convolution <rows_of_W> <columns_of_W> <depth_of_W> <number_of_filters_W> <stride_axis_0> <stride_axis_1>
<flattened filter block W>
<flattened bias vector>
'''
_, h, w, d, n, s0, s1 = line.split()
h = int(h)
w = int(w)
d = int(d)
n = int(n)
s0 = int(s0)
s1 = int(s1)
layer = Convolution(filtersize=(h, w, d, n),
stride=(s0, s1))
layer.W = np.array([
float(weightstring)
for weightstring in content[c + 1].split()
if len(weightstring) > 0
]).reshape((h, w, d, n))
layer.B = np.array([
float(weightstring)
for weightstring in content[c + 2].split()
if len(weightstring) > 0
])
modules.append(layer)
c += 3 #the description of a convolution layer spans three lines
elif line.startswith(
SumPool.__name__
): # @UndefinedVariable import error suppression for PyDev users
'''
Format of sum pooling layer
SumPool <mask_heigth> <mask_width> <stride_axis_0> <stride_axis_1>
'''
_, h, w, s0, s1 = line.split()
h = int(h)
w = int(w)
s0 = int(s0)
s1 = int(s1)
layer = SumPool(pool=(h, w), stride=(s0, s1))
modules.append(layer)
c += 1 # one line of parameterized layer description
elif line.startswith(
MaxPool.__name__
): # @UndefinedVariable import error suppression for PyDev users
'''
Format of max pooling layer
MaxPool <mask_heigth> <mask_width> <stride_axis_0> <stride_axis_1>
'''
_, h, w, s0, s1 = line.split()
h = int(h)
w = int(w)
s0 = int(s0)
s1 = int(s1)
layer = MaxPool(pool=(h, w), stride=(s0, s1))
modules.append(layer)
c += 1 # one line of parameterized layer description
elif line.startswith(
Flatten.__name__
): # @UndefinedVariable import error suppression for PyDev users
modules.append(Flatten())
c += 1 #one line of parameterless layer description
elif line.startswith(
Rect.__name__
): # @UndefinedVariable import error suppression for PyDev users
modules.append(Rect())
c += 1 #one line of parameterless layer description
elif line.startswith(
Tanh.__name__
): # @UndefinedVariable import error suppression for PyDev users
modules.append(Tanh())
c += 1 #one line of parameterless layer description
elif line.startswith(
SoftMax.__name__
): # @UndefinedVariable import error suppression for PyDev users
modules.append(SoftMax())
c += 1 #one line of parameterless layer description
else:
raise ValueError(
'Layer type identifier' +
[s for s in line.split() if len(s) > 0][0] +
' not supported for reading from plain text file')
#skip info of previous layers, read in next layer header
line = content[c]
return Sequential(modules)