def test_e_fp(filename,expected_count=10):
init_gamera()
c = Classifier_with_remove()
c.set_k(1)
c.change_features(["volume64regions"])
ci = c.classify_image(filename)
#files = ["mergedyn2.xml", "mergedyn.xml","only-dynamics.xml",
# "newtrain-dynamic.xml", "preomr.xml"]
files = ["preomr.xml","preomr_edited.xml","preomr_edited_cnn.xml"]
import os.path
# try to match with different trainingsets.
for dynamic in ([ d for d in files if os.path.isfile(d) ]):
ci.load_new_training_data(dynamic)
print "%s - count_of_training=%d, k=%d"%(dynamic,len(c.stats),c.k)
result = {} # Push into buckets based on the count of found glyphs.
csv = {}
sys.stdout.flush()
# Try with different epsilon for false_positives: e_fp
for e_fp in arange(0.01,1.01,0.01):
c.e_fp=e_fp
count = len(ci.classified_glyphs())
# Init bucket.
if not result.has_key(count):
result[count] = []
result[count].append((e_fp,c.d_t()))
csv[e_fp] = count
# Find the best match to the wanted result.
k,res,diff = find_nearest(result,expected_count)
confid = [ (len(v),key,v[0][0],v[0][1]) for key,v in result.iteritems() ]
confid2 = [ (key,len(v)) for key,v in result.iteritems() ]
confid.sort(reverse=True)
confid2.sort()
print "efp,count"
for e_fp,c in sorted(csv.iteritems()):
print "%s,%s"%(e_fp,c)
print
print "count,spansize"
for count,spansize in confid2:
print "%s,%s"%(count,spansize)
return
ret = []
for i in range(0,min(10,len(confid))+1):
ret.append(confid[i])
if not result.has_key(expected_count):
print "Never found the desired amount with %s"%dynamic
print "Found in %d(%d): %s"%(k,diff,[r for r in res])
rgbimg = ci.image.to_rgb()
cg = ci.classified_glyphs(res[0].d_t)
[outline(rgbimg,g,3.0,RGBPixel(255,0,0)) for g in cg]
rgbimg.save_PNG("class_%s_%s.png"%(filename,dynamic))
print
def test_e_fp(filename, expected_count=10):
init_gamera()
c = Classifier_with_remove()
c.set_k(1)
c.change_features(["volume64regions"])
ci = c.classify_image(filename)
#files = ["mergedyn2.xml", "mergedyn.xml","only-dynamics.xml",
# "newtrain-dynamic.xml", "preomr.xml"]
files = ["preomr.xml", "preomr_edited.xml", "preomr_edited_cnn.xml"]
import os.path
# try to match with different trainingsets.
for dynamic in ([d for d in files if os.path.isfile(d)]):
ci.load_new_training_data(dynamic)
print "%s - count_of_training=%d, k=%d" % (dynamic, len(c.stats), c.k)
result = {} # Push into buckets based on the count of found glyphs.
csv = {}
sys.stdout.flush()
# Try with different epsilon for false_positives: e_fp
for e_fp in arange(0.01, 1.01, 0.01):
c.e_fp = e_fp
count = len(ci.classified_glyphs())
# Init bucket.
if not result.has_key(count):
result[count] = []
result[count].append((e_fp, c.d_t()))
csv[e_fp] = count
# Find the best match to the wanted result.
k, res, diff = find_nearest(result, expected_count)
confid = [(len(v), key, v[0][0], v[0][1])
for key, v in result.iteritems()]
confid2 = [(key, len(v)) for key, v in result.iteritems()]
confid.sort(reverse=True)
confid2.sort()
print "efp,count"
for e_fp, c in sorted(csv.iteritems()):
print "%s,%s" % (e_fp, c)
print
print "count,spansize"
for count, spansize in confid2:
print "%s,%s" % (count, spansize)
return
ret = []
for i in range(0, min(10, len(confid)) + 1):
ret.append(confid[i])
if not result.has_key(expected_count):
print "Never found the desired amount with %s" % dynamic
print "Found in %d(%d): %s" % (k, diff, [r for r in res])
rgbimg = ci.image.to_rgb()
cg = ci.classified_glyphs(res[0].d_t)
[outline(rgbimg, g, 3.0, RGBPixel(255, 0, 0)) for g in cg]
rgbimg.save_PNG("class_%s_%s.png" % (filename, dynamic))
print
