shapes = []
for i in range(nprims):
shapes.append([go(), go(), go(), gogo()])
return np.array(shapes, dtype=config.floatX)
def genshapebatch(nprims, nbatch):
shapes = np.random.rand(nprims, nbatch, 4)*2 - 2
return np.array(shapes, dtype=config.floatX)
width = 224
height = 224
# Generate initial rays
exfragcoords = gen_fragcoords(width, height)
nprims = 500
print("Compiling Renderer")
render = make_render(nprims, width, height)
shapes = genshapebatch(nprims, 2)
print("Rendering")
img = render(exfragcoords, shapes)
from ig import display
display.draw(img[:,:,0])
# np.save('data/observed_img', img, allow_pickle=True, fix_imports=True)
#
# # print("Drawing Img")
# # draw(img)
#
# print("Doing Pixel Comparison")
# cost = similarity_cost2(img, nprims, width, height)
def second_order(nprims = 200, nbatch = 50):
"""Creates a network which takes as input a image and returns a cost.
Network extracts features of image to create shape params which are rendered.
The similarity between the rendered image and the actual image is the cost
"""
width = 224
height = 224
params_per_prim = 3
nshape_params = nprims * params_per_prim
img = T.tensor4("input image")
net = {}
net['input'] = InputLayer((nbatch, 1, 224, 224), input_var = img)
net['conv1'] = ConvLayer(net['input'], num_filters=96, filter_size=7, stride=2)
net['norm1'] = NormLayer(net['conv1'], alpha=0.0001) # caffe has alpha = alpha * pool_size
net['pool1'] = PoolLayer(net['norm1'], pool_size=3, stride=3, ignore_border=False)
net['conv2'] = ConvLayer(net['pool1'], num_filters=256, filter_size=5)
net['pool2'] = PoolLayer(net['conv2'], pool_size=2, stride=2, ignore_border=False)
net['conv3'] = ConvLayer(net['pool2'], num_filters=512, filter_size=3, pad=1)
net['conv4'] = ConvLayer(net['conv3'], num_filters=512, filter_size=3, pad=1)
net['conv5'] = ConvLayer(net['conv4'], num_filters=512, filter_size=3, pad=1)
net['pool5'] = PoolLayer(net['conv5'], pool_size=3, stride=3, ignore_border=False)
net['fc6'] = DenseLayer(net['pool5'], num_units=4096)
net['drop6'] = DropoutLayer(net['fc6'], p=0.5)
net['fc7'] = DenseLayer(net['drop6'], num_units=nshape_params)
# net['fc7'] = DenseLayer(net['pool5'], num_units=nshape_params, nonlinearity=lasagne.nonlinearities.tanh)
output_layer = net['fc7']
output = lasagne.layers.get_output(output_layer)
scaled_output = output - 1
## Render these parameters
shape_params = T.reshape(scaled_output, (nprims, nbatch, params_per_prim))
fragCoords = T.tensor3('fragCoords')
print "Symbolic Render"
res, scan_updates = symbolic_render(nprims, shape_params, fragCoords, width, height)
res_reshape = res.dimshuffle([2,'x',0,1])
# Simply using pixel distance
eps = 1e-9
diff = T.maximum(eps, (res_reshape - img)**2)
loss1 = T.sum(diff) / (224*224*nbatch)
mean_shape = T.mean(shape_params, axis=1) # mean across batches
mean_shape = T.reshape(mean_shape, (nprims, 1, params_per_prim))
scale = 1.0
diff2 = T.maximum(eps, (mean_shape - shape_params)**2)
loss2 = T.sum(diff2) / (nprims * params_per_prim * nbatch)
mu = 0
sigma = 4
a = 1/(sigma*np.sqrt(2*np.pi))
b = mu
c = sigma
loss2 = -a*T.exp((-loss2**2)/(2*c**2))
loss = loss2 + loss1
# Create update expressions for training, i.e., how to modify the
# parameters at each training step. Here, we'll use Stochastic Gradient
# Descent (SGD) with Nesterov momentum, but Lasagne offers plenty more.
params = lasagne.layers.get_all_params(output_layer, trainable=True)
network_updates = lasagne.updates.nesterov_momentum(loss, params, learning_rate=0.01, momentum=0.9)
## Merge Updates
for k in network_updates.keys():
assert not(scan_updates.has_key(k))
scan_updates[k] = network_updates[k]
print("Compiling Loss Function")
grad = T.grad(loss, params[0])
netcost = function([fragCoords, img], [loss, grad, res_reshape, shape_params, diff, loss1, loss2], updates=scan_updates, mode=curr_mode)
# netcost = function([fragCoords, img], loss, updates=scan_updates, mode=curr_mode)
## Generate Render Function to make data
# Generate initial rays
exfragcoords = gen_fragcoords(width, height)
print("Compiling Renderer")
render = make_render(nprims, width, height)
return render, netcost, output_layer
