def do_training(args=None):
goodrefs, badrefs = [EMData.read_images(a) for a in args]
nnet_savename = "nnet_classify.hdf"
bxsz = goodrefs[0]["nx"]
sz = 64
shrinkfac = old_div(float(bxsz), float(sz))
print("Setting up model ...")
rng = np.random.RandomState(123)
nkernel = [20, 20, 1]
ksize = [15, 15, 15]
poolsz = [2, 1, 1]
batch_size = 10
image_shape = (batch_size, 1, sz, sz)
convnet = StackedConvNet(rng,
nkernel=nkernel,
ksize=ksize,
poolsz=poolsz,
imageshape=image_shape)
convnet.sumout = T.mean(convnet.clslayer.get_image().reshape(
(batch_size, -1)),
axis=1)
convnet.sumout = T.maximum(0, convnet.sumout)
#convnet.sumout=T.minimum(1,convnet.sumout)
print("Pre-processing particles...")
#### here we shrink the particles so they are 64x64
#### and duplicate so there are more than 500 good and 500 bad particles
nref_target = 500
data = [] ### particles in flattened numpy array
lbs = [] ### labels in flattened numpy array
for label, refs in enumerate([badrefs, goodrefs]):
nref = len(refs)
if nref < 5:
print(
"Not enough references. Please box at least 5 good and 5 bad reference..."
)
return []
ncopy = old_div(nref_target, nref) + 1
for pp in refs:
ptl = pp.process("math.fft.resample", {"n": shrinkfac})
ptl.clip_inplace(Region(0, 0, sz, sz))
#ptl.process_inplace("filter.highpass.gauss",{"cutoff_freq":0.005})
#ptl.process_inplace("filter.lowpass.gauss",{"cutoff_freq":0.05})
ptl.process_inplace("filter.highpass.gauss", {"cutoff_pixels": 2})
ptl.process_inplace("filter.lowpass.gauss", {"cutoff_abs": 0.25})
for c in range(ncopy):
tr = Transform()
tr.set_rotation({
"type": "2d",
"alpha": np.random.random() * 360.0
})
img = ptl.process("xform", {"transform": tr})
ar = img.numpy().copy()
data.append(ar.flatten())
lbs.append(label)
#print shrinkfac
rndid = list(range(len(data)))
np.random.shuffle(rndid)
data = [data[i] for i in rndid]
lbs = [lbs[i] for i in rndid]
data = np.asarray(data, dtype=theano.config.floatX)
#print np.std(data), np.mean(np.std(data,axis=1))
div = np.mean(np.std(data, axis=1))
data /= div #np.std(data)#*2.
mx = 4.
data[data > mx] = mx
data[data < -mx] = -mx
lbs = np.asarray(lbs, dtype=theano.config.floatX)
train_set_x = theano.shared(data, borrow=True)
#### make target output
#img=EMData(sz/2,sz/2)
#img.process_inplace("testimage.gaussian",{'sigma':5.})
#img.div(img["maximum"])
#gaus=img.numpy().copy().flatten()
#gaus=gaus.astype(theano.config.floatX)
#lbarrs=np.array([np.zeros_like(gaus, dtype=theano.config.floatX), gaus])
#label_np=lbarrs[lbs]
labels = theano.shared(lbs.astype(theano.config.floatX), borrow=True)
#print lbs.astype(theano.config.floatX)
#print gaus.shape, data.shape, label_np.shape
print("Now Training...")
classify = get_classify_func(convnet, train_set_x, labels, batch_size)
learning_rate = 0.005
weightdecay = 1e-5
n_train_batches = old_div(len(data), batch_size)
for epoch in range(20):
# go through the training set
c = []
for batch_index in range(n_train_batches):
err = classify(batch_index, lr=learning_rate, wd=weightdecay)
c.append(err)
learning_rate *= .96
print('Training epoch %d, cost ' % (epoch), end=' ')
print(np.mean(c), ", learning rate", learning_rate)
save_model(convnet, nnet_savename)
tstsz = 100
convnet.update_shape((tstsz, 1, sz, sz))
test_cls = theano.function(inputs=[],
outputs=convnet.clslayer.get_image(),
givens={convnet.x: train_set_x[:tstsz]})
tstout = test_cls()
trainoutfile = "trainout_nnet_classify.hdf"
if os.path.isfile(trainoutfile):
os.remove(trainoutfile)
for i, mm in enumerate(tstout):
t = train_set_x[i].eval().reshape(sz, sz)
img = from_numpy(t)
#img.process_inplace("normalize")
img.write_image(trainoutfile, -1)
for m in mm:
img = from_numpy(m)
nx = img["nx"]
img = img.get_clip(
Region(old_div(-nx, 2), old_div(-nx, 2), nx * 2, nx * 2))
img.scale(2.)
#img.process_inplace("math.fft.resample",{"n":.5})
#img.mult(5)
img.process_inplace("threshold.clampminmax.nsigma", {"nsigma": 4})
img.write_image(trainoutfile, -1)
def do_training(args=None):
refs0, refs1, badrefs=[EMData.read_images(a) for a in args]
nnet_savename="nnet_pickptcls_2cls.hdf"
bxsz=refs0[0]["nx"]
sz=64
shrinkfac=old_div(float(bxsz),float(sz))
print("Importing dependencies...")
if not hasattr(boxerConvNet,'import_done'):
if not boxerConvNet.do_import():
print("Cannot import required dependencies..Stop.")
print("Setting up model ...")
rng = np.random.RandomState(123)
nkernel=[20,20,2]
ksize=[15,15,15]
poolsz=[2,1,1]
batch_size=10
image_shape=(batch_size, 1, sz, sz)
convnet = StackedConvNet(
rng,
nkernel=nkernel,
ksize=ksize,
poolsz=poolsz,
imageshape=image_shape
)
print("Pre-processing particles...")
#### here we shrink the particles so they are 64x64
#### and duplicate so there are more than 500 good and 500 bad particles
nref_target=500
data=[] ### particles in flattened numpy array
lbs=[] ### labels in flattened numpy array
for label, refs in enumerate([badrefs,refs0, refs1]):
nref=len(refs)
if nref<5:
print("Not enough references. Please box at least 5 good and 5 bad reference...")
return []
ncopy=old_div(nref_target,nref) + 1
for pp in refs:
ptl=pp.process("math.fft.resample",{"n":shrinkfac})
ptl.clip_inplace(Region(0,0, sz, sz))
ptl.process_inplace("filter.highpass.gauss",{"cutoff_freq":0.005})
ptl.process_inplace("filter.lowpass.gauss",{"cutoff_freq":0.05})
for c in range(ncopy):
tr=Transform()
tr.set_rotation({"type":"2d","alpha":np.random.random()*360.0})
img=ptl.process("xform",{"transform":tr})
ar=img.numpy().copy()
data.append(ar.flatten())
lbs.append(label)
rndid=list(range(len(data)))
np.random.shuffle(rndid)
data=[data[i] for i in rndid]
lbs=[lbs[i] for i in rndid]
data=np.asarray(data,dtype=theano.config.floatX)
data/=np.std(data)
data[data>2.]=2.
data[data<-2.]=-2.
lbs=np.asarray(lbs,dtype=int)
train_set_x= theano.shared(data,borrow=True)
#### make target output
img=EMData(old_div(sz,2),old_div(sz,2))
img.process_inplace("testimage.gaussian",{'sigma':5.})
img.div(img["maximum"])
gaus=img.numpy().copy().flatten()
gaus=gaus.astype(theano.config.floatX)
zero=np.zeros_like(gaus, dtype=theano.config.floatX)
g0=np.hstack([gaus, zero])
g1=np.hstack([zero, gaus])
z0=np.hstack([zero, zero])
lbarrs=np.array([z0, g0, g1])
label_np=lbarrs[lbs]
#print label_np.shape
labels=theano.shared(label_np, borrow=True)
print("Now Training...")
classify=convnet.get_classify_func(train_set_x,labels,batch_size)
learning_rate=0.002
weightdecay=1e-5
n_train_batches = old_div(len(data), batch_size)
for epoch in range(20):
# go through the training set
c = []
for batch_index in range(n_train_batches):
err=classify(batch_index,
lr=learning_rate,
wd=weightdecay)
c.append(err)
learning_rate*=.96
print('Training epoch %d, cost ' % ( epoch), end=' ')
print(np.mean(c),", learning rate",learning_rate)
save_model(convnet, nnet_savename)
tstsz=100
convnet.update_shape((tstsz, 1, sz, sz))
test_cls = theano.function(
inputs=[],
outputs=convnet.clslayer.get_image(),
givens={
convnet.x: train_set_x[:tstsz]
}
)
tstout=test_cls()
trainoutfile="trainout_nnet.hdf"
if os.path.isfile(trainoutfile):
os.remove(trainoutfile)
for i,mm in enumerate(tstout):
t=train_set_x[i].eval().reshape(sz,sz)
img=from_numpy(t)
img.process_inplace("normalize")
img.write_image(trainoutfile, -1)
#print m.shape
for m in mm:
img=from_numpy(m)
nx=img["nx"]
img=img.get_clip(Region(old_div(-nx,2),old_div(-nx,2),nx*2,nx*2))
img.scale(2.)
#img.process_inplace("math.fft.resample",{"n":.5})
img.mult(5)
img.write_image(trainoutfile, -1)