def test(config):
config[
'num_threads'] = 1 # only <num_threads = 1> supported when testing_usr
config['flip'] = False # not allowed to flip image
config['add_colorjit'] = False # not allowed to use color jitting
dataset = create_dataset(config)
model = create_model(config)
model.setup(config)
result_root_path = os.path.join(config['checkpoints_dir'], config['name'],
config['results_dir'])
util.mkdir(result_root_path)
print(" create testing_usr folder: " + result_root_path)
# set module to testing_usr mode
model.eval()
for i, data in enumerate(dataset):
model.set_input(data) # push test datasets to module
model.test() # forward module
for k in range(len(model.test_result)):
img = util.tensor2im(model.test_result[k][1])
img_path = os.path.join(result_root_path, data['PATH'][0])
util.save_image(img, img_path)
print("Testing forward-- complete:" + str(i + 1) + " total:" +
str(dataset.__len__()))
def save_images(webpage, visuals, image_path, width=256):
""""""
""" this function save images in "visuals" to html file.
args:
webpage (the HTML class) -- the html class to save the images (see html.py for details)
visuals (OrderedDict) -- OrderedDict to save name/iamges
image_path (str) -- iamge path
aspect_ratio (float) -- the aspect ratio for saving image (default 1.0)
width (int) -- set iamge width, the image will be scaled width x width size (default 256)
"""
image_dir = webpage.get_image_dir()
short_path = ntpath.basename(image_path[0])
name = os.path.splitext(short_path)[0]
webpage.add_header(name)
ims, txts, links = [], [], []
for label, im_data in visuals.items():
im = tools.tensor2im(im_data)
image_name = '%s_%s.png' % (name, label)
save_path = os.path.join(image_dir, image_name)
h, w, _ = im.shape
tools.save_image(im, save_path)
ims.append(image_name)
txts.append(label)
links.append(image_name)
webpage.add_images(ims, txts, links, width=width)
def test(config):
config[
'num_threads'] = 1 # only <num_threads = 1> supported when testing_usr
config['flip'] = False # not allowed to flip image
config['status'] = 'test'
config['crop_scale'] = 1.0
dataset = create_dataset(config)
model = create_model(config)
model.setup(config)
result_root_path = os.path.join(config['checkpoints_dir'], config['name'],
'evaluation')
util.mkdir(result_root_path)
util.mkdir(os.path.join(result_root_path, 'prediction_distance'))
util.mkdir(os.path.join(result_root_path, 'prediction_heatmap'))
print(" create evaluate folder: " + result_root_path)
# set module to testing_usr mode
model.eval()
save_npy = np.ndarray(shape=(dataset.__len__() + 1, 2), dtype=np.float)
save_npy[0][0], save_npy[0][1] = -1, -1
for i, data in enumerate(dataset):
model.set_input(data) # push test datasets to module
model.test() # forward module
datapoints = (model.test_result[0][1]).cpu().data.numpy()
index = data["PATH"].cpu().data.numpy()[0]
save_npy[index][0], save_npy[index][1] = datapoints[0][0], datapoints[
0][1]
dist_img = model.test_result[1][1]
util.save_image(
util.tensor2im(dist_img),
os.path.join(result_root_path, 'prediction_distance',
str(index) + ".png"))
heatmap_img = model.test_result[2][1]
util.save_image(
util.tensor2im(heatmap_img),
os.path.join(result_root_path, 'prediction_heatmap',
str(index) + ".png"))
print("Evaluate forward-- complete:" + str(i + 1) + " total:" +
str(dataset.__len__()))
np.save(os.path.join(result_root_path, 'regression.npy'), save_npy)
l2_dist, easy_dist, hard_dist = evaluation.evaluate_detailed(save_npy)
print("Testing npy result have been saved! Evaluation distance: " +
str(round(l2_dist)) + "(" + str(round(easy_dist)) + "," +
str(round(hard_dist)) + ")")
def save_images(webpage, visuals, image_path, width=256):
image_dir = webpage.get_image_dir()
short_path = ntpath.basename(image_path[0])
name = os.path.splitext(short_path)[0]
webpage.add_header(name)
ims, txts, links = [], [], []
for label, im_data in visuals.items():
im = tools.tensor2im(im_data)
image_name = '%s_%s.png' % (name, label)
save_path = os.path.join(image_dir, image_name)
h, w, _ = im.shape
tools.save_image(im, save_path)
ims.append(image_name)
txts.append(label)
links.append(image_name)
webpage.add_images(ims, txts, links, width=width)
def val(config, epoch, dataset, model):
result_root_path = os.path.join(config['checkpoints_dir'], config['name'],
config['results_dir'],
"epoch" + str(epoch))
util.mkdir(result_root_path)
model.eval()
save_npy = np.ndarray(shape=(dataset.__len__() + 1, 2), dtype=np.float)
save_npy[0][0], save_npy[0][1] = -1, -1
print("Start evaluating epoch " + str(epoch) + "...")
for i, data in enumerate(dataset):
model.set_input(data) # push test datasets to module
model.test() # forward module
datapoints = (model.test_result[0][1]).cpu().data.numpy()
index = data["PATH"].cpu().data.numpy()[0]
save_npy[index][0], save_npy[index][1] = datapoints[0][0], datapoints[
0][1]
dist_img = model.test_result[1][1]
util.save_image(util.tensor2im(dist_img),
os.path.join(result_root_path,
str(index) + ".png"))
model.train()
np.save(os.path.join(result_root_path, 'regression.npy'), save_npy)
l2_dist, easy_dist, hard_dist = evaluation.evaluate_detailed(save_npy)
text = open(
os.path.join(config['checkpoints_dir'], config['name'],
config['results_dir'], "evaluation.txt"), "a+")
text.writelines("EPOCH " + str(epoch) + ": " + str(round(l2_dist, 4)) +
" " + str(round(easy_dist, 4)) + ' ' +
str(round(hard_dist, 4)) + "\n")
text.close()
print("Testing npy result have been saved! Evaluation distance: " +
str(round(l2_dist)) + "(" + str(round(easy_dist)) + "," +
str(round(hard_dist)) + ")")
def display_current_results(self, visuals, epoch, save_result):
""""""
""" diaplay current result in visdom and save to html
args:
visuals (OrderedDict) - - image OrderedDict to visulize of save
epoch (int) - - current epoch
save_result (bool) - - save current result to html or not
"""
# show image in browser using visdom
if self.display_id > 0:
ncols = self.ncols
# show all the iamge in one visdom web pannel
if ncols > 0:
ncols = min(ncols, len(visuals))
h, w = next(iter(visuals.values())).shape[:2]
table_css = """<style>
table {border-collapse: separate; border-spacing: 4px; white-space: nowrap; text-align: center}
table td {width: % dpx; height: % dpx; padding: 4px; outline: 4px solid black}
</style>""" % (w, h) # create CSS of the tabel
title = self.name
label_html = ''
label_html_row = ''
images = []
idx = 0
for label, image in visuals.items():
image_numpy = tools.tensor2im(image)
label_html_row += '<td>%s</td>' % label
images.append(image_numpy.transpose([2, 0, 1]))
idx += 1
if idx % ncols == 0:
label_html += '<tr>%s</tr>' % label_html_row
label_html_row = ''
white_image = np.ones_like(image_numpy.transpose([2, 0, 1
])) * 255
while idx % ncols != 0:
images.append(white_image)
label_html_row += '<td></td>'
idx += 1
if label_html_row != '':
label_html += '<tr>%s</tr>' % label_html_row
try:
self.vis.images(images,
nrow=ncols,
win=self.display_id + 1,
padding=2,
opts=dict(title=title + ' images'))
label_html = '<table>%s</table>' % label_html
self.vis.text(table_css + label_html,
win=self.display_id + 2,
opts=dict(title=title + ' labels'))
except VisdomExceptionBase:
self.create_visdom_connections()
else:
idx = 1
try:
for label, image in visuals.items():
image_numpy = tools.tensor2im(image)
self.vis.image(image_numpy.transpose([2, 0, 1]),
opts=dict(title=label),
win=self.display_id + idx)
idx += 1
except VisdomExceptionBase:
self.create_visdom_connections()
if self.use_html and (save_result or not self.saved):
self.saved = True
for label, image in visuals.items():
image_numpy = tools.tensor2im(image)
img_path = os.path.join(self.img_dir,
'epoch%.3d_%s.png' % (epoch, label))
tools.save_image(image_numpy, img_path)
# refresh html
webpage = html.HTML(self.web_dir,
'Experiment name = %s' % self.name)
for n in range(epoch, 0, -1):
webpage.add_header('epoch [%d]' % n)
ims, txts, links = [], [], []
for label, image_numpy in visuals.items():
img_path = 'epoch%.3d_%s.png' % (n, label)
ims.append(img_path)
txts.append(label)
links.append(img_path)
webpage.add_images(ims, txts, links, width=self.win_size)
webpage.save()