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 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]))
if output_dir is None:
from tempfile import mkdtemp
output_dir = mkdtemp() + '/'
from os import path, mkdir
if not path.isdir(output_dir):
mkdir(output_dir)
# Define the classification model to use
from caffe_all import *
from data import *
from util import *
from python_layers import Py
import load
model = load.ProtoDesc(args.prototxt)
# Create the training net
ns = NetSpec()
mean_value = [104, 117, 123]
if args.no_mean: mean_value = [0, 0, 0]
ns.data, ns.cls = dataLayer(args.voc_dir,
output_dir,
batch_size=args.bs,
transform_param=dict(crop_size=model.input_dim[-1],
min_scale=args.min_scale,
max_scale=args.max_scale,
mean_value=mean_value,
mirror=True,
scale=args.scale),
resize=args.resize)