def train(network, nprims = 200, nbatch = 50, num_epochs = 500):
width = 224
height = 224
exfragcoords = gen_fragcoords(width, height)
print("Starting Training")
for epoch in range(num_epochs):
rand_data = genshapebatch(nprims, nbatch)
print("Rendering Test Data")
test_data = render(exfragcoords, rand_data)
test_data = np.transpose(test_data, (2,0,1))
reshaped_test_data = np.reshape(test_data, (nbatch,1,width, height))
print("Computing Loss")
test_err = netcost(exfragcoords, reshaped_test_data)
print(test_err[3])
print(test_err[0])
ig.display.draw(test_err[4][0,0])
print "loss1", test_err[5]
print "loss2", test_err[6]
# print(" test loss:\t\t\t{:.6f}".format(test_err))
return lasagne.layers.get_all_param_values(network)
test_err = costfunc(exfragcoords, rand_shape_params)
print "epoch", epoch
print "loss", test_err[0]
print "loss1", test_err[1]
print "loss2", test_err[2]
print "pdiff", test_err[3]
print "summed_op", test_err[4]
print "param grad abs sum", np.sum(np.abs(test_err[7]))
print "\n"
if save_data:
fname = "epoch%s" % (epoch)
full_fname = os.path.join(full_dir_name, fname)
np.savez_compressed(full_fname, *test_err)
return lasagne.layers.get_all_param_values(network)
def network_mb(network):
o = lasagne.layers.get_all_param_values(network)
q = np.concatenate([pp.flatten() for pp in o])
return (float(len(q))*32) / 1024.0**2
width = 224
height = 224
exfragcoords = gen_fragcoords(width, height)
nprims = 50
nbatch = 24
costfunc, network = learn_to_move(nprims = nprims, nbatch = nbatch, width = width, height = height)
# print "Weights in MB"
# print network_mb(network)
train(network, costfunc, exfragcoords, nprims = nprims, nbatch = nbatch)
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
