def main():
# Make output dir if not exists
if not os.path.isdir(args.output_dir):
os.makedirs(args.output_dir)
# Make image output dirs
if args.save_output_images > 0:
output_image_dir = args.output_dir + 'image_outputs/'
if not os.path.isdir(output_image_dir):
os.makedirs(output_image_dir)
# Create cityscapes manager class
CS = cityscapes(args.cityscapes_dir)
n_cl = len(CS.classes)
# Get labeled frames for evaluation
label_frames = CS.list_label_frames(args.split)
# GPU runs out of memory, so keep using CPU
# caffe.set_device(args.gpu_id)
# caffe.set_mode_gpu()
# Load FCN-8s network
net = caffe.Net(args.caffemodel_dir + '/deploy.prototxt',
args.caffemodel_dir + 'fcn-8s-cityscapes.caffemodel',
caffe.TEST)
hist_perframe = np.zeros((n_cl, n_cl))
# For all labeled frames
for i, idx in enumerate(label_frames):
if i % 10 == 0:
print('Evaluating: %d/%d' % (i, len(label_frames)))
city = idx.split('_')[0]
# idx is city_shot_frame
label = CS.load_label(args.split, city, idx)
im_file = args.result_dir + '/' + idx + '_leftImg8bit.png'
im = np.array(
Image.open(im_file).resize((label.shape[1], label.shape[2])))
out = segrun(net, CS.preprocess(im))
hist_perframe += fast_hist(label.flatten(), out.flatten(), n_cl)
if args.save_output_images > 0:
label_im = CS.palette(label)
pred_im = CS.palette(out)
scipy.misc.imsave(output_image_dir + '/' + str(i) + '_pred.jpg',
pred_im)
scipy.misc.imsave(output_image_dir + '/' + str(i) + '_gt.jpg',
label_im)
scipy.misc.imsave(output_image_dir + '/' + str(i) + '_input.jpg',
im)
mean_pixel_acc, mean_class_acc, mean_class_iou, per_class_acc, per_class_iou = get_scores(
hist_perframe)
with open(args.output_dir + '/evaluation_results.txt', 'w') as f:
f.write('Mean pixel accuracy: %f\n' % mean_pixel_acc)
f.write('Mean class accuracy: %f\n' % mean_class_acc)
f.write('Mean class IoU: %f\n' % mean_class_iou)
f.write('************ Per class numbers below ************\n')
for i, cl in enumerate(CS.classes):
while len(cl) < 15:
cl = cl + ' '
f.write('%s: acc = %f, iou = %f\n' %
(cl, per_class_acc[i], per_class_iou[i]))
def get_chi_training_data(chi_df):
for i in list(dfs.geo_avgs.T):
if (i == 'Chicago Loop') or (i == 'Loop'):
pass
else:
i_places = dfs.places['GeoArea'] == i
workers = list(
dfs.places[i_places]['MappedUser'].value_counts()) * 4
if len(workers) > 0:
workers = math.ceil(sum(workers) / max(workers))
else:
workers = 0
if i == 'Mckinley Park':
i = 'McKinley Park'
n = i + ' Chicago'
area = calculate_area(gmclient, n)
num_places = len(dfs.places[i_places])
walkscore, transitscore, bikescore = get_scores(
n, 'Neighbourhood', 'IL')
chi_df.loc[len(chi_df)] = \
(i, workers, area, num_places, \
walkscore, transitscore, bikescore)
async def scores(self, ctx):
s = util.get_scores(self.conn, ctx.message.guild.id)
if not s:
return await ctx.send("No streaks in the server bro 😩")
u = await asyncio.gather(*[self.bot.fetch_user(x[0]) for x in s])
u = filter(lambda x: type(x) is discord.User, u)
s = [(x, *y[1:]) for x, y in zip(u, s)]
msg = tabulate(s, headers=["User", "Current", "Highest", "Total"])
msg = f"```css\n{msg}```"
await ctx.send(msg)
def main():
if not os.path.isdir(args.output_dir):
os.makedirs(args.output_dir)
if args.save_output_images > 0:
output_image_dir = args.output_dir + 'image_outputs/'
if not os.path.isdir(output_image_dir):
os.makedirs(output_image_dir)
CS = cityscapes(args.cityscapes_dir)
n_cl = len(CS.classes)
label_frames = CS.list_label_frames(args.split)
print(label_frames)
caffe.set_mode_cpu()
net = caffe.Net(args.caffemodel_dir + '/deploy.prototxt',
args.caffemodel_dir + 'fcn-8s-cityscapes.caffemodel',
caffe.TEST)
hist_perframe = np.zeros((n_cl, n_cl))
for i, idx in enumerate(label_frames):
if i % 10 == 0:
print('Evaluating: %d/%d' % (i, len(label_frames)))
city = idx.split('_')[0]
# idx is city_shot_frame
label = CS.load_label(args.split, city, idx)
im_file = args.result_dir + '/' + idx + '_leftImg8bit.png'
##print(im_file)
im = np.array(Image.open(im_file))
#im = scipy.misc.imresize(im, (label.shape[1], label.shape[2]))
im = np.array(Image.fromarray(im).resize((label.shape[2], label.shape[1])))
out = segrun(net, CS.preprocess(im))
hist_perframe += fast_hist(label.flatten(), out.flatten(), n_cl)
if args.save_output_images > 0:
label_im = CS.palette(label)
pred_im = CS.palette(out)
#scipy.misc.imsave(output_image_dir + '/' + str(i) + '_pred.jpg', pred_im)
#scipy.misc.imsave(output_image_dir + '/' + str(i) + '_gt.jpg', label_im)
#scipy.misc.imsave(output_image_dir + '/' + str(i) + '_input.jpg', im)
imageio.imwrite(output_image_dir + '/' + str(i) + '_pred.jpg', pred_im)
imageio.imwrite(output_image_dir + '/' + str(i) + '_gt.jpg', label_im)
imageio.imwrite(output_image_dir + '/' + str(i) + '_input.jpg', im)
#if i > 3:
# break
mean_pixel_acc, mean_class_acc, mean_class_iou, per_class_acc, per_class_iou = get_scores(hist_perframe)
with open(args.output_dir + '/evaluation_results.txt', 'w') as f:
f.write('Mean pixel accuracy: %f\n' % mean_pixel_acc)
f.write('Mean class accuracy: %f\n' % mean_class_acc)
f.write('Mean class IoU: %f\n' % mean_class_iou)
f.write('************ Per class numbers below ************\n')
for i, cl in enumerate(CS.classes):
while len(cl) < 15:
cl = cl + ' '
f.write('%s: acc = %f, iou = %f\n' % (cl, per_class_acc[i], per_class_iou[i]))
def main():
if not os.path.isdir(args.output_dir):
os.makedirs(args.output_dir)
if args.save_output_images > 0:
output_image_dir = args.output_dir + 'image_outputs/'
if not os.path.isdir(output_image_dir):
os.makedirs(output_image_dir)
CS = cityscapes(args.cityscapes_dir)
n_cl = len(CS.classes)
label_frames = CS.list_label_frames(args.split)
# caffe.set_device(args.gpu_id)
# caffe.set_mode_gpu()
# net = caffe.Net(args.caffemodel_dir + '/deploy.prototxt',
# args.caffemodel_dir + 'fcn-8s-cityscapes.caffemodel',
# caffe.TEST)
hist_perframe = np.zeros((n_cl, n_cl))
for i, idx in enumerate(label_frames):
if i % 10 == 0:
print('Evaluating: %d/%d' % (i, len(label_frames)))
city = idx.split('_')[0]
# idx is city_shot_frame
label = CS.load_label(args.split, city, idx)
im_file = args.result_dir + '/' + idx + '_leftImg8bit.png'
# im = np.array(Image.open(im_file))
# out_path = args.cityscapes_dir + 'gtFine/val/' + city + '/' + idx + '_gtFine_color.png'
# im = scipy.misc.imresize(im, (256, 256))
# im = scipy.misc.imresize(im, (label.shape[1], label.shape[2]))
# out = segrun(net, CS.preprocess(im))
# out = scipy.misc.imresize(out, (label.shape[1], label.shape[2]))
out = ReturnGrayImage(im_file)
hist_perframe += fast_hist(label.flatten(), out.flatten(), n_cl)
mean_pixel_acc, mean_class_acc, mean_class_iou, per_class_acc, per_class_iou = get_scores(hist_perframe)
with open(args.output_dir + '/evaluation_results.txt', 'w') as f:
f.write('Mean pixel accuracy: %f\n' % mean_pixel_acc)
f.write('Mean class accuracy: %f\n' % mean_class_acc)
f.write('Mean class IoU: %f\n' % mean_class_iou)
f.write('************ Per class numbers below ************\n')
for i, cl in enumerate(CS.classes):
while len(cl) < 15:
cl = cl + ' '
f.write('%s: acc = %f, iou = %f\n' % (cl, per_class_acc[i], per_class_iou[i]))
import imreg
import chist
parser = argparse.ArgumentParser()
parser.add_argument('-c', default=10, type=int, dest='nclusters')
parser.add_argument('-plot', action='store_true')
args = parser.parse_args()
nclusters = args.nclusters
fout = 'score_' + str(nclusters) + '.pickle'
if os.path.isfile(fout):
with open(fout, 'r') as fin:
(nm, cd) = pickle.load(fin)
else:
(nm, cd) = util.get_scores(nclusters, 'both', hbins=64, rand=True)
with open(fout, 'w') as fout:
pickle.dump((nm, cd), fout)
(images, files) = util.get_images(nclusters)
#print [(files[i], files[j]) for i in range(1000) for j in range(1000)
# if (nm[i, j] > 15 and not util.same_cluster(i, j))]
x = []
y = []
for i in range(nm.shape[0]):
for j in range(nm.shape[1]):
if nm[i, j] != 0:
x.append((nm[i, j], cd[i, j]))
if util.same_cluster(i, j):
y.append(1)
import numpy as np
import matplotlib.pylab as plt
import scipy.linalg
import sklearn.metrics
import util
CLUSTERS = 200
XINTERC = 0.001
bmat = np.ones((util.FILES_PER_CLUSTER, util.FILES_PER_CLUSTER), dtype = 'bool')
blocks = [bmat for i in range(CLUSTERS)]
true = scipy.linalg.block_diag(*blocks)
hbins_array = [16, 25, 32, 50, 64, 80, 100, 128]
aucs = []
for hbins in hbins_array:
scores = -util.get_scores(CLUSTERS, 'hist', hbins=hbins)
fpr, tpr, thresh = sklearn.metrics.roc_curve(true.flatten(), scores.flatten())
print np.interp(XINTERC, fpr, tpr)
# plt.plot(fpr, tpr)
# plt.show()
# aucs.append(sklearn.metrics.roc_auc_score(true.flatten(), scores.flatten()))
aucs.append(np.interp(XINTERC, fpr, tpr))
print (hbins, aucs[-1])
plt.plot(hbins_array, aucs)
plt.show()