def train_head(self, subset):
n = NetSpec()
# train
image_data_param = dict(source=subset.get_list_absolute_path(),
batch_size=self.batch_sizes[0],
new_width=self.infmt.new_width,
new_height=self.infmt.new_height,
rand_skip=self.batch_size,
shuffle=True)
if subset.root_folder is not None:
image_data_param['root_folder'] = subset.root_folder
transform_param = dict(
mirror=self.infmt.mirror,
crop_size=self.infmt.crop_size,
# mean_value = self.infmt.mean_pixel,
)
if self.infmt.scale is not None:
transform_param['scale'] = self.infmt.scale
if self.infmt.mean_file is not None:
transform_param['mean_file'] = self.infmt.mean_file
elif self.infmt.mean_pixel is not None:
transform_param['mean_value'] = self.infmt.mean_pixel
n.data, n.label = L.ImageData(ntop=2,
image_data_param=image_data_param,
transform_param=transform_param,
include=dict(phase=caffe.TRAIN))
net = n.to_proto()
net.name = self.name
return net
def main():
from argparse import ArgumentParser
from os import path
parser = ArgumentParser()
parser.add_argument('prototxt')
parser.add_argument('-l', '--load', help='Load a caffemodel')
parser.add_argument('-d', '--data', default=None, help='Image list to use [default prototxt data]')
#parser.add_argument('-q', action='store_true', help='Quiet execution')
parser.add_argument('-sm', action='store_true', help='Summary only')
parser.add_argument('-q', action='store_true', help='Quiet execution')
parser.add_argument('-a', '--all', action='store_true', help='Show the statistic for all layers')
parser.add_argument('-nc', action='store_true', help='Do not use color')
parser.add_argument('-s', type=float, default=1.0, help='Scale the input [only custom data "-d"]')
parser.add_argument('-bs', type=int, default=16, help='Batch size [only custom data "-d"]')
parser.add_argument('-nit', type=int, default=10, help='Number of iterations')
parser.add_argument('--gpu', type=int, default=0, help='What gpu to run it on?')
args = parser.parse_args()
if args.q:
from os import environ
environ['GLOG_minloglevel'] = '2'
import caffe, load
from caffe import NetSpec, layers as L
caffe.set_mode_gpu()
if args.gpu is not None:
caffe.set_device(args.gpu)
model = load.ProtoDesc(args.prototxt)
net = NetSpec()
if args.data is not None:
fl = getFileList(args.data)
if len(fl) == 0:
print("Unknown data type for '%s'"%args.data)
exit(1)
from tempfile import NamedTemporaryFile
f = NamedTemporaryFile('w')
f.write('\n'.join([path.abspath(i)+' 0' for i in fl]))
f.flush()
net.data, net.label = L.ImageData(source=f.name, batch_size=args.bs, new_width=model.input_dim[-1], new_height=model.input_dim[-1], transform_param=dict(mean_value=[104,117,123], scale=args.s),ntop=2)
net.out = model(data=net.data, label=net.label)
else:
net.out = model()
n = netFromString('force_backward:true\n'+str(net.to_proto()), caffe.TRAIN )
if args.load is not None:
n.copy_from(args.load)
cvar = printMeanStddev(n, NIT=args.nit, show_all=args.all, show_color=not args.nc, quiet=args.sm)
cv, gr = computeGraidentRatio(n, NIT=args.nit)
print()
print(' Summary ')
print('-----------')
print()
print('layer name out cvar rate cvar rate mean')
for l in n._layer_names:
if l in cvar and l in cv and l in gr:
print('%-30s %10.2f %10.2f %10.2f'%(l, cvar[l], cv[l], gr[l]) )
def val_head(self, subset, stage=None):
image_data_param = dict(
source=subset.get_list_absolute_path(),
batch_size=self.batch_sizes[1],
# root_folder=subset.root_folder,
rand_skip=self.batch_sizes[1],
shuffle=True,
# new_width,
# new_height
)
transform_param = dict(
mirror=False,
# crop_size = self.infmt.crop_size,
# mean_value = self.infmt.mean_pixel,
# mean_file,
# scale,
)
if subset.root_folder is not None:
image_data_param['root_folder'] = subset.root_folder
if self.crop_on_test:
image_data_param['new_width'] = self.infmt.new_width
image_data_param['new_height'] = self.infmt.new_height
transform_param['crop_size'] = self.infmt.crop_size
else:
image_data_param['new_width'] = self.infmt.crop_size
image_data_param['new_height'] = self.infmt.crop_size
if self.infmt.scale is not None:
transform_param['scale'] = self.infmt.scale
if self.infmt.mean_file is not None:
transform_param['mean_file'] = self.infmt.mean_file
elif self.infmt.mean_pixel is not None:
transform_param['mean_value'] = self.infmt.mean_pixel
include_param = dict(phase=caffe.TEST)
if stage is not None:
include_param['stage'] = stage
n = NetSpec()
n.data, n.label = L.ImageData(ntop=2,
image_data_param=image_data_param,
transform_param=transform_param,
include=include_param)
net = n.to_proto()
net.name = self.name
return net
def lenet(lmdbData, lmdbLabel, batch_size):
n = NetSpec()
n.data = L.Data(batch_size=batch_size, backend=P.Data.LMDB, source=lmdbData,
transform_param=dict(scale=1./255), ntop=1)
n.label = L.Data(batch_size=batch_size, backend=P.Data.LMDB, source=lmdbLabel,
transform_param=dict(scale=1./255), ntop=1)
n.conv1 = L.Convolution(n.data, kernel_size=4, num_output=200, weight_filler=dict(type='xavier'))
n.pool1 = L.Pooling(n.conv1, kernel_size=2, stride=2, pool=P.Pooling.MAX)
n.conv2 = L.Convolution(n.pool1, kernel_size=3, num_output=50, weight_filler=dict(type='xavier'))
n.pool2 = L.Pooling(n.conv2, kernel_size=2, stride=1, pool=P.Pooling.MAX)
n.fc1 = L.InnerProduct(n.pool2, num_output=200, weight_filler=dict(type='xavier'))
n.relu1 = L.ReLU(n.fc1, in_place=True)
n.score = L.InnerProduct(n.relu1, num_output=1200, weight_filler=dict(type='xavier'))
n.loss = L.Python(n.score, n.label, module='pyloss', layer='EuclideanLossLayer')
return n.to_proto()
def extract_head(self, subset):
image_data_param = dict(
source=subset.get_list_absolute_path(),
batch_size=self.batch_size,
root_folder=subset.root_folder,
# new_width,
# new_height
)
transform_param = dict(
mirror=False,
# crop_size = self.infmt.crop_size,
# mean_value = self.infmt.mean_pixel,
# mean_file,
# scale,
)
if self.crop_on_test:
image_data_param['new_width'] = self.infmt.new_width
image_data_param['new_height'] = self.infmt.new_height
transform_param['crop_size'] = self.infmt.crop_size
else:
image_data_param['new_width'] = self.infmt.crop_size
image_data_param['new_height'] = self.infmt.crop_size
if self.infmt.scale is not None:
transform_param['scale'] = self.infmt.scale
if self.infmt.mean_file is not None:
transform_param['mean_file'] = self.infmt.mean_file
elif self.infmt.mean_pixel is not None:
transform_param['mean_value'] = self.infmt.mean_pixel
n = NetSpec()
n.data, n.label = L.ImageData(ntop=2,
image_data_param=image_data_param,
transform_param=transform_param
) # , include=dict(phase=caffe.TEST))
net = n.to_proto()
net.name = self.name
return net
def gen_net(batch_size=512):
n=NetSpec();
n.data = L.DummyData(shape={"dim":[batch_size,3,96,96]})
n.select1 = L.DummyData(shape={"dim":[2]})
n.select2 = L.DummyData(shape={"dim":[2]})
n.label = L.DummyData(shape={"dim":[2]})
caffenet_stack(n.data, n)
n.first = L.BatchReindex(n.fc6, n.select1)
n.second = L.BatchReindex(n.fc6, n.select2)
n.fc6_concat=L.Concat(n.first, n.second);
n.fc7, n.bn7, n.relu7 = fc_relu(n.fc6_concat, 4096, batchnorm=True);
n.fc8, n.relu8 = fc_relu(n.relu7, 4096);
n.fc9 = L.InnerProduct(n.relu8, num_output=8,
weight_filler=dict(type='xavier'));
n.loss = L.SoftmaxWithLoss(n.fc9, n.label, loss_param=dict(normalization=P.Loss.NONE));
prot=n.to_proto()
prot.debug_info=True
return prot;
def main():
from argparse import ArgumentParser
from os import path
parser = ArgumentParser()
parser.add_argument('prototxt')
parser.add_argument('-l', '--load', help='Load a caffemodel')
parser.add_argument('-d',
'--data',
default=None,
help='Image list to use [default prototxt data]')
#parser.add_argument('-q', action='store_true', help='Quiet execution')
parser.add_argument('-sm', action='store_true', help='Summary only')
parser.add_argument('-q', action='store_true', help='Quiet execution')
parser.add_argument('-a',
'--all',
action='store_true',
help='Show the statistic for all layers')
parser.add_argument('-nc', action='store_true', help='Do not use color')
parser.add_argument('-s',
type=float,
default=1.0,
help='Scale the input [only custom data "-d"]')
parser.add_argument('-bs',
type=int,
default=16,
help='Batch size [only custom data "-d"]')
parser.add_argument('-nit',
type=int,
default=10,
help='Number of iterations')
parser.add_argument('--gpu',
type=int,
default=0,
help='What gpu to run it on?')
args = parser.parse_args()
if args.q:
from os import environ
environ['GLOG_minloglevel'] = '2'
import caffe, load
from caffe import NetSpec, layers as L
caffe.set_mode_gpu()
if args.gpu is not None:
caffe.set_device(args.gpu)
if args.data is not None:
model = load.ProtoDesc(args.prototxt)
net = NetSpec()
fl = getFileList(args.data)
if len(fl) == 0:
print("Unknown data type for '%s'" % args.data)
exit(1)
from tempfile import NamedTemporaryFile
f = NamedTemporaryFile('w')
f.write('\n'.join([path.abspath(i) + ' 0' for i in fl]))
f.flush()
net.data, net.label = L.ImageData(source=f.name,
batch_size=args.bs,
new_width=model.input_dim[-1],
new_height=model.input_dim[-1],
transform_param=dict(
mean_value=[104, 117, 123],
scale=args.s),
ntop=2)
net.out = model(data=net.data, label=net.label)
n = netFromString('force_backward:true\n' + str(net.to_proto()),
caffe.TRAIN)
else:
n = caffe.Net(args.prototxt, caffe.TRAIN)
if args.load is not None:
n.copy_from(args.load)
cvar = printMeanStddev(n,
NIT=args.nit,
show_all=args.all,
show_color=not args.nc,
quiet=args.sm)
cv, gr = computeGradientRatio(n, NIT=args.nit)
print()
print(' Summary ')
print('-----------')
print()
print(
'layer name out cvar rate cvar rate mean'
)
for l in n._layer_names:
if l in cvar and l in cv and l in gr:
print('%-30s %10.2f %10.2f %10.2f' %
(l, cvar[l], cv[l], gr[l]))
def main():
from argparse import ArgumentParser
from os import path
import numpy as np
parser = ArgumentParser()
parser.add_argument('prototxt')
parser.add_argument('output_caffemodel')
parser.add_argument('-l', '--load', help='Load a pretrained model and rescale it [bias and type are not supported]')
parser.add_argument('-d', '--data', default=None, help='Image list to use [default prototxt data]')
parser.add_argument('-b', '--bias', type=float, default=0.1, help='Bias')
parser.add_argument('-t', '--type', default='elwise', help='Type: elwise, pca, zca, kmeans, rand (random input patches). Add fast_ to speed up the initialization, but you might lose in precision.')
parser.add_argument('-z', action='store_true', help='Zero all weights and reinitialize')
parser.add_argument('-cs', action='store_true', help='Correct for scaling')
parser.add_argument('-q', action='store_true', help='Quiet execution')
parser.add_argument('-s', type=float, default=1.0, help='Scale the input [only custom data "-d"]')
parser.add_argument('-bs', type=int, default=16, help='Batch size [only custom data "-d"]')
parser.add_argument('-nit', type=int, default=10, help='Number of iterations')
parser.add_argument('--mem-limit', type=int, default=500, help='How much memory should we use for the data buffer (MB)?')
parser.add_argument('--gpu', type=int, default=0, help='What gpu to run it on?')
args = parser.parse_args()
if args.q:
from os import environ
environ['GLOG_minloglevel'] = '2'
import caffe, load
from caffe import NetSpec, layers as L
caffe.set_mode_gpu()
if args.gpu is not None:
caffe.set_device(args.gpu)
if args.data is not None:
model = load.ProtoDesc(args.prototxt)
net = NetSpec()
fl = getFileList(args.data)
if len(fl) == 0:
print("Unknown data type for '%s'"%args.data)
exit(1)
from tempfile import NamedTemporaryFile
f = NamedTemporaryFile('w')
f.write('\n'.join([path.abspath(i)+' 0' for i in fl]))
f.flush()
net.data, net.label = L.ImageData(source=f.name, batch_size=args.bs, new_width=model.input_dim[-1], new_height=model.input_dim[-1], transform_param=dict(mean_value=[104,117,123], scale=args.s),ntop=2)
net.out = model(data=net.data, label=net.label)
n = netFromString('force_backward:true\n'+str(net.to_proto()), caffe.TRAIN )
else:
n = caffe.Net(args.prototxt, caffe.TRAIN)
if args.load is not None:
n.copy_from(args.load)
# Rescale existing layers?
#if args.fix:
#magicFix(n, args.nit)
if args.z:
# Zero out all layers
for l in n.layers:
for b in l.blobs:
b.data[...] = 0
if any([np.abs(l.blobs[0].data).sum() < 1e-10 for l in n.layers if len(l.blobs) > 0]):
print( [m for l,m in zip(n.layers, n._layer_names) if len(l.blobs) > 0 and np.abs(l.blobs[0].data).sum() < 1e-10] )
magicInitialize(n, args.bias, NIT=args.nit, type=args.type, max_data=args.mem_limit*1024*1024/4)
else:
print( "Network already initialized, skipping magic init" )
if args.cs:
# A simply helper function that lets you figure out which layers are not
# homogeneous
#print( estimateHomogenety(n) )
calibrateGradientRatio(n)
n.save(args.output_caffemodel)
def main():
from argparse import ArgumentParser
from os import path
import numpy as np
parser = ArgumentParser()
parser.add_argument('prototxt')
parser.add_argument('output_caffemodel')
parser.add_argument(
'-l',
'--load',
help=
'Load a pretrained model and rescale it [bias and type are not supported]'
)
parser.add_argument('-d',
'--data',
default=None,
help='Image list to use [default prototxt data]')
parser.add_argument('-b', '--bias', type=float, default=0.1, help='Bias')
parser.add_argument(
'-t',
'--type',
default='elwise',
help=
'Type: elwise, pca, zca, kmeans, rand (random input patches). Add fast_ to speed up the initialization, but you might lose in precision.'
)
parser.add_argument(
'--zero_from',
default=None,
help='Zero weights starting from this layer and reinitialize')
parser.add_argument('-z',
action='store_true',
help='Zero all weights and reinitialize')
parser.add_argument(
'--post_zero_from',
default=None,
help=
'AFTER everything else, zero weights starting from this layer (they will NOT be reinitialized)'
)
parser.add_argument('-cs', action='store_true', help='Correct for scaling')
parser.add_argument('-q', action='store_true', help='Quiet execution')
parser.add_argument('-s',
type=float,
default=1.0,
help='Scale the input [only custom data "-d"]')
parser.add_argument('-bs',
type=int,
default=16,
help='Batch size [only custom data "-d"]')
parser.add_argument('-nit',
type=int,
default=10,
help='Number of iterations')
parser.add_argument(
'--mem-limit',
type=int,
default=500,
help='How much memory should we use for the data buffer (MB)?')
parser.add_argument('--gpu',
type=int,
default=0,
help='What gpu to run it on?')
args = parser.parse_args()
if args.q:
from os import environ
environ['GLOG_minloglevel'] = '2'
import caffe, load
from caffe import NetSpec, layers as L
caffe.set_mode_gpu()
if args.gpu is not None:
caffe.set_device(args.gpu)
if args.data is not None:
model = load.ProtoDesc(args.prototxt)
net = NetSpec()
fl = getFileList(args.data)
if len(fl) == 0:
print("Unknown data type for '%s'" % args.data)
exit(1)
from tempfile import NamedTemporaryFile
f = NamedTemporaryFile('w')
f.write('\n'.join([path.abspath(i) + ' 0' for i in fl]))
f.flush()
net.data, net.label = L.ImageData(source=f.name,
batch_size=args.bs,
new_width=model.input_dim[-1],
new_height=model.input_dim[-1],
transform_param=dict(
mean_value=[104, 117, 123],
scale=args.s),
ntop=2)
net.out = model(data=net.data, label=net.label)
n = netFromString('force_backward:true\n' + str(net.to_proto()),
caffe.TRAIN)
else:
n = caffe.Net(args.prototxt, caffe.TRAIN)
if args.load is not None:
n.copy_from(args.load)
# Rescale existing layers?
#if args.fix:
#magicFix(n, args.nit)
if args.z or args.zero_from:
zeroLayers(n, start=args.zero_from)
if any([
np.abs(l.blobs[0].data).sum() < 1e-10 for l in n.layers
if len(l.blobs) > 0
]):
print([
m for l, m in zip(n.layers, n._layer_names)
if len(l.blobs) > 0 and np.abs(l.blobs[0].data).sum() < 1e-10
])
magicInitialize(n,
args.bias,
NIT=args.nit,
type=args.type,
max_data=args.mem_limit * 1024 * 1024 / 4)
else:
print("Network already initialized, skipping magic init")
if args.cs:
# A simply helper function that lets you figure out which layers are not
# homogeneous
#print( estimateHomogenety(n) )
print('Calibrating gradient ratio')
calibrateGradientRatio(n)
if args.post_zero_from:
zeroLayers(n, start=args.post_zero_from)
n.save(args.output_caffemodel)
def get_train_data_layer(batch_size):
#important: conf.train_lmdb
n = NetSpec()
n.data, n.label = L.Data(batch_size=batch_size, backend=P.Data.LMDB, source=conf.train_lmdb, include=dict(phase=caffe_pb2.TRAIN),
transform_param=dict(crop_size=227, mean_value=[104, 117, 123]), ntop=2)
return n.to_proto()
