retval['halign'] = image.halign
return retval
def main(images):
temp_dc = wx.MemoryDC()
temp_dc.SelectObject(destbitmap)
mimg = MultiImage(images)
drawrect = wx.Rect(10, 10, 220, 440)
mimg.draw(temp_dc, drawrect)
temp_dc.SelectObject(wx.NullBitmap)
if __name__ == '__main__':
import util, syck
from skins import images as imgmngr
from skins import skins
app = wx.PySimpleApp()
# image['source'] = 'skins/default/checkerboard9.png'
skins.res_path = "../../res/"
destbitmap = imgmngr.get('skins/default/blue-flower.jpg')
f = file("../../res/skins/skinExample")
images = to_storage(syck.load(f)).Images
f.close()
util.profile(main, images)
destbitmap.SaveFile('C:/workspace/Digsby/res/skins/default/output.png',
wx.BITMAP_TYPE_PNG)
# -*- coding: utf-8 -*-
"""
add your model discription and calculate the computation!
"""
import keras
from util import profile
# TODO: RELUs
# TODO: BatchNorms
# Residual Paths
model = keras.applications.resnet50.ResNet50(weights=None)
# look at model
model.summary()
# run profile
layer_name, layer_flops, inshape, weights = profile(model)
# visualize results
for name, flop, shape, weight in zip(layer_name, layer_flops, inshape, weights):
print("layer:", name, shape, " MegaFLOPS:", flop/1e6, " MegaWeights:", weight/1e6)
print("Total FLOPS[GFLOPS]:", sum(layer_flops)/1e9)
# TODO: summarize results as dict
def main():
logger.info("Loading data...")
tokenizer = BertTokenizer.from_pretrained('bert-base-chinese')
train_loader = util.profile('train.txt', tokenizer)
# test_loader = util.profile('test.txt', tokenizer)
dev_loader = util.profile('dev.txt', tokenizer)
logger.info("Build model...")
bert = BertModel.from_pretrained('bert-base-chinese')
model = fn_cls(bert)
criterion = nn.BCELoss()
sigmoid = nn.Sigmoid()
max_epoch = args.epoch
model.cuda()
model.train()
optim = torch.optim.Adam(model.parameters(), lr=1e-5)
for epoch in range(1, max_epoch + 1):
tacc = []
losslis = []
# train epoch
train_time = time.time()
for batch_idx, (data, target) in enumerate(train_loader):
data = data.cuda()
target = target.cuda()
mask = []
for sample in data:
mask.append([1 if i != 0 else 0 for i in sample])
mask = torch.tensor(mask).cuda()
output = model(data, attention_mask=mask)
pred = torch.argmax(output, 1)
tacc.append(
np.mean((pred == torch.argmax(target, 1)).cpu().numpy()))
loss = criterion(sigmoid(output).view(-1, 10), target)
losslis.append(loss.item())
loss.backward()
optim.step()
optim.zero_grad()
logger.info('Train Epoch: {} \tLoss:{:.6f} Acc:{}'.format(
epoch, np.mean(losslis), 100 * np.mean(tacc)))
logger.info('time:{}'.format((time.time() - train_time)))
# evaluate epoch
model.eval()
li = []
acc = []
for batch_idx, (data, target) in enumerate(dev_loader):
data, target = torch.tensor(data).cuda(), torch.tensor(
target).cuda()
mask = []
for sample in data:
mask.append([1 if i != 0 else 0 for i in sample])
mask = torch.tensor(mask).cuda()
output = model(data, attention_mask=mask)
pred = torch.argmax(output, 1)
acc.append(np.mean((pred == target).cpu().numpy()))
eval_loss = criterion(sigmoid(output).view(-1, 10), target)
li.append(eval_loss.item())
logger.info('-' * 50)
logger.info('Validate Epoch: {} acc:{:.2f}%\tLoss:{:.6f}'.format(
1,
np.mean(acc) * 100, np.mean(li)))
def __init__(self,
trial,
x,
y,
num_steps,
data_path,
log_path,
learning_rate=0.5,
norm=False,
radius=None,
tensorboard=False,
gpu=None):
'''
trial: string, name of the trial
data: tensorflow dataset iterator
x, y: int, dimension of the map
feat_nr: int, number of inpt_features
num_steps: int, number of training steps
norm: bool, if True then data will be normalized
radius: int, if None use default radius max(x,y)/2
tensorboard: bool, if True, logs the graph and runs a performance test
gpu: int, picks gpu from cluster by number
'''
self.trial = trial
self.data_path = data_path
self.log_path = log_path
self.x = x
self.y = y
self.num_steps = num_steps
self.learning_rate = learning_rate
self.radius = radius
self.norm = norm
self.tensorboard = tensorboard
self.gpu = gpu
if gpu != None:
##########
### PICK GPU ###################
os.environ["CUDA_VISIBLE_DEVICES"] = str(gpu)
with tf.variable_scope("input"):
with tf.variable_scope("data"):
if norm is True:
self.data = normalize(
np.load(data_path).astype(np.float32))
else:
self.data = np.load(data_path).astype(np.float32)
self.feat_nr = len(self.data[0])
self.nr_inst = len(self.data)
with tf.variable_scope("pipeline"):
inpt = pipe(self.data, prefetch=20)
# step count
self.step = tf.placeholder(tf.float32)
# create weight matrix
self.weights = tf.get_variable(
"weights",
shape=[self.x * self.y, self.feat_nr],
initializer=tf.random_uniform_initializer)
#initializer=tf.random_normal_initializer)
with tf.variable_scope("locations"):
self.locations = tf.constant(
np.array(
list([
np.array([i, j]) for i in range(self.x)
for j in range(self.y)
])))
if radius == None:
self.radius = tf.constant(max(self.x, self.y) / 2,
dtype=tf.float32)
#Calculate current learning rate and radius
# todo: different decay options
with tf.variable_scope("decay"):
decay = tf.cast(1 - (self.step / self.num_steps), dtype=tf.float32)
with tf.variable_scope("current_lr"):
current_lr = self.learning_rate * decay
with tf.variable_scope("current_radius"):
current_radius = self.radius * decay
with tf.variable_scope("bmu"):
# calculate Best Matching Unit (euclidean distances)
distances = tf.sqrt(tf.reduce_sum((self.weights - inpt)**2, 1))
bmu = tf.reduce_min(distances)
#bmu = tf.argmin(distances, 0)
with tf.variable_scope("bmu_loc"):
# get the location of the bmu
#mask = tf.pad(tf.reshape(bmu, [1]), tf.constant(np.array([[0, 1]])))
#size = tf.cast(tf.constant(np.array([1, 2])), dtype=tf.int64)
#bmu_loc = tf.reshape(tf.slice(self.locations, mask, size), [2])
mask = tf.equal(distances, bmu)
bmu_locs = tf.boolean_mask(self.locations, mask)
bmu_loc = tf.slice(bmu_locs, [0, 0],
[1, 2])[0] # make sure its only one location
with tf.variable_scope("neighborhood"):
# calculate the influence on the neighborhood of the bmu
bmu_dist = tf.sqrt(
tf.cast(tf.reduce_sum((self.locations - bmu_loc)**2, 1),
dtype=tf.float32))
nbr_func = tf.exp(-bmu_dist / (2 * (current_radius**2)))
with tf.variable_scope("delta"):
# get the delta of the weights
delta = tf.expand_dims(nbr_func,
-1) * current_lr * (inpt - self.weights)
with tf.variable_scope("new_weights"):
#update the new weights
new_weights = self.weights + delta
self.train_step = tf.assign(self.weights, new_weights)
# initialize session
self.sess = tf.InteractiveSession()
self.sess.run(tf.global_variables_initializer())
if self.tensorboard is True:
wrtr = tf.summary.FileWriter(
os.path.expanduser(self.log_path + self.trial))
wrtr.add_graph(self.sess.graph)
profile(self.sess,
wrtr,
new_weights,
feed_dict=None,
prerun=3,
tag='flow')
wrtr.flush()
retval['halign'] = image.halign
return retval
def main(images):
temp_dc = wx.MemoryDC();
temp_dc.SelectObject(destbitmap);
mimg = MultiImage(images)
drawrect = wx.Rect(10,10,220,440)
mimg.draw(temp_dc, drawrect)
temp_dc.SelectObject(wx.NullBitmap)
if __name__ == '__main__':
import util, syck
from skins import images as imgmngr
from skins import skins
app = wx.PySimpleApp()
# image['source'] = 'skins/default/checkerboard9.png'
skins.res_path = "../../res/"
destbitmap = imgmngr.get('skins/default/blue-flower.jpg')
f = file("../../res/skins/skinExample")
images = to_storage(syck.load(f)).Images
f.close()
util.profile(main, images)
destbitmap.SaveFile('C:/workspace/Digsby/res/skins/default/output.png',
wx.BITMAP_TYPE_PNG)
if not self.sizing:
self.sizing = True
dx, dy = x - self.orig[0], y - self.orig[1]
self.SetSize(
(self.origsize[0] + dx, self.origsize[1] + dy))
self.sizing = False
elif self.click_state == 'moving':
fp = (x - self.delta[0], y - self.delta[1])
self.Move(fp)
def method_sizing(self):
pass
if __name__ == '__main__':
import util
import windowfx
app = wx.PySimpleApp()
from gui import skininit
skininit('../../res', 'halloween')
frame = Skindow(None, 'IMWin', title='Skindow Test')
from uberwidgets.UberBook import SamplePanel
frame.set_content(SamplePanel(frame.content, 'orange'))
windowfx.fadein(frame)
app.SetTopWindow(frame)
util.profile(app.MainLoop)
wx.EVT_BUTTON, lambda e: self.capbar.ShowCapabilities(
not self.capbar.cbar.IsShown()))
b2.Bind(
wx.EVT_BUTTON,
lambda e: self.capbar.ShowToFrom(not self.capbar.tfbar.IsShown()))
b3.Bind(
wx.EVT_BUTTON, lambda e: self.capbar.ShowComposeButton(
not self.capbar.bcompose.IsShown()))
self.panel.Sizer.Add(b1)
self.panel.Sizer.Add(b2)
self.panel.Sizer.Add(b3)
self.capbar.bsms.Bind(wx.EVT_BUTTON, self.OnButton)
self.capbar.binfo.Bind(wx.EVT_BUTTON,
lambda e: self.capbar.bsms.SendButtonEvent())
def OnButton(self, event):
print "button clicked"
def Go():
f = Frame()
f.Show(True)
if __name__ == '__main__':
a = App(Go)
from util import profile
profile(a.MainLoop)
self.sizing = True
dx, dy = x - self.orig[0], y - self.orig[1]
self.SetSize( ( self.origsize[0] + dx, self.origsize[1] + dy ) )
self.sizing = False
elif self.click_state == 'moving':
fp = (x - self.delta[0], y - self.delta[1])
self.Move( fp )
def method_sizing(self):
pass
if __name__ == '__main__':
import util
import windowfx
app = wx.PySimpleApp()
from gui import skininit
skininit('../../res','halloween')
frame = Skindow( None,'IMWin', title='Skindow Test' )
from uberwidgets.UberBook import SamplePanel
frame.set_content(SamplePanel(frame.content, 'orange'))
windowfx.fadein( frame )
app.SetTopWindow( frame )
util.profile(app.MainLoop)
self.panel.Sizer.Add(self.capbar,0,wx.EXPAND)
b1=wx.Button(self.panel,-1,'Hide Capabilities')
b2=wx.Button(self.panel,-1,'Hide To/From')
b3=wx.Button(self.panel,-1,'Hide Compose')
b1.Bind(wx.EVT_BUTTON,lambda e: self.capbar.ShowCapabilities(not self.capbar.cbar.IsShown()))
b2.Bind(wx.EVT_BUTTON,lambda e: self.capbar.ShowToFrom(not self.capbar.tfbar.IsShown()))
b3.Bind(wx.EVT_BUTTON, lambda e: self.capbar.ShowComposeButton(not self.capbar.bcompose.IsShown()))
self.panel.Sizer.Add(b1)
self.panel.Sizer.Add(b2)
self.panel.Sizer.Add(b3)
self.capbar.bsms.Bind(wx.EVT_BUTTON,self.OnButton)
self.capbar.binfo.Bind(wx.EVT_BUTTON,lambda e: self.capbar.bsms.SendButtonEvent())
def OnButton(self,event):
print "button clicked"
def Go():
f=Frame()
f.Show(True)
if __name__=='__main__':
a = App( Go )
from util import profile
profile(a.MainLoop)
