host = "http://cytomine.icube.unistra.fr"
public_key = "8da00e26-3bcb-4229-b31d-a2b5937c4e5e" # check your own keys from your account page in the web interface
private_key = "c0018f6a-8aa1-4791-957b-ab72dce4238d"
term = {''}
if __name__ == '__main__':
with Cytomine(host=CYTO_HOST,
public_key=CYTO_PUB_KEY,
private_key=CYTO_PRV_KEY,
verbose=logging.INFO) as cytomine:
annotations = AnnotationCollection()
annotations.project = "1345"
annotations.showWKT = True
annotations.showMeta = True
annotations.showTerm = True
annotations.showGIS = True
annotations.fetch()
print(annotations)
f = open("./anno.csv", "w+")
f.write("ID;Image;Project;Term;User;Area;Perimeter;WKT;TRACK \n")
for annotation in annotations:
f.write("{};{};{};{};{};{};{};{}\n".format(
annotation.id, annotation.image, annotation.project,
annotation.term, annotation.user, annotation.area,
annotation.perimeter, annotation.location))
exit(0)
import time
from main import *
def main():
with CytomineJob.from_cli(sys.argv) as conn:
conn.job.update(status=Job.RUNNING,
progress=0,
status_comment="Initialization of the training phase")
# 1. Create working directories on the machine:
# - WORKING_PATH/in: input images
# - WORKING_PATH/out: output images
# - WORKING_PATH/ground_truth: ground truth images
# - WORKING_PATH/tmp: temporary path
base_path = "{}".format(os.getenv("HOME"))
gt_suffix = "_lbl"
working_path = os.path.join(base_path, str(conn.job.id))
in_path = os.path.join(working_path, "in/")
in_txt = os.path.join(in_path, 'txt/')
out_path = os.path.join(working_path, "out/")
gt_path = os.path.join(working_path, "ground_truth/")
tmp_path = os.path.join(working_path, "tmp/")
if not os.path.exists(working_path):
os.makedirs(working_path)
os.makedirs(in_path)
os.makedirs(out_path)
os.makedirs(gt_path)
os.makedirs(tmp_path)
os.makedirs(in_txt)
# 2. Download the images (first input, then ground truth image)
conn.job.update(
progress=10,
statusComment="Downloading images (to {})...".format(in_path))
print(conn.parameters)
images = ImageInstanceCollection().fetch_with_filter(
"project", conn.parameters.cytomine_id_project)
xpos = {}
ypos = {}
terms = {}
for image in images:
image.dump(dest_pattern=in_path.rstrip('/') + '/%d.%s' %
(image.id, 'jpg'))
annotations = AnnotationCollection()
annotations.project = conn.parameters.cytomine_id_project
annotations.showWKT = True
annotations.showMeta = True
annotations.showGIS = True
annotations.showTerm = True
annotations.image = image.id
annotations.fetch()
for ann in annotations:
l = ann.location
if l.rfind('POINT') == -1:
pol = shapely.wkt.loads(l)
poi = pol.centroid
else:
poi = shapely.wkt.loads(l)
(cx, cy) = poi.xy
xpos[(ann.term[0], image.id)] = int(cx[0])
ypos[(ann.term[0], image.id)] = image.height - int(cy[0])
terms[ann.term[0]] = 1
for image in images:
F = open(in_txt + '%d.txt' % image.id, 'w')
for t in terms.keys():
if (t, image.id) in xpos:
F.write('%d %d %d %f %f\n' %
(t, xpos[(t, image.id)], ypos[(t, image.id)],
xpos[(t, image.id)] / float(image.width),
ypos[(t, image.id)] / float(image.height)))
F.close()
depths = 1. / (2.**np.arange(conn.parameters.model_depth))
(xc, yc, xr, yr, ims, t_to_i, i_to_t) = getallcoords(in_txt)
if conn.parameters.cytomine_id_terms == 'all':
term_list = t_to_i.keys()
else:
term_list = [
int(term)
for term in conn.parameters.cytomine_id_terms.split(',')
]
if conn.parameters.cytomine_training_images == 'all':
tr_im = ims
else:
tr_im = [
int(id_im) for id_im in
conn.parameters.cytomine_training_images.split(',')
]
DATA = None
REP = None
be = 0
#leprogres = 10
#pr_spacing = 90/len(term_list)
#print(term_list)
sfinal = ""
for id_term in conn.monitor(term_list,
start=10,
end=90,
period=0.05,
prefix="Model building for terms..."):
sfinal += "%d " % id_term
(xc, yc, xr, yr) = getcoordsim(in_txt, id_term, tr_im)
nimages = np.max(xc.shape)
mx = np.mean(xr)
my = np.mean(yr)
P = np.zeros((2, nimages))
P[0, :] = xr
P[1, :] = yr
cm = np.cov(P)
passe = False
# additional parameters
feature_parameters = None
if conn.parameters.model_feature_type.lower() == 'gaussian':
std_matrix = np.eye(2) * (
conn.parameters.model_feature_gaussian_std**2)
feature_parameters = np.round(
np.random.multivariate_normal(
[0, 0], std_matrix,
conn.parameters.model_feature_gaussian_n)).astype(int)
elif conn.parameters.model_feature_type.lower() == 'haar':
W = conn.parameters.model_wsize
n = conn.parameters.model_feature_haar_n / (
5 * conn.parameters.model_depth)
h2 = generate_2_horizontal(W, n)
v2 = generate_2_vertical(W, n)
h3 = generate_3_horizontal(W, n)
v3 = generate_3_vertical(W, n)
sq = generate_square(W, n)
feature_parameters = (h2, v2, h3, v3, sq)
for times in range(conn.parameters.model_ntimes):
if times == 0:
rangrange = 0
else:
rangrange = conn.parameters.model_angle
T = build_datasets_rot_mp(
in_path, tr_im, xc, yc, conn.parameters.model_R,
conn.parameters.model_RMAX, conn.parameters.model_P,
conn.parameters.model_step, rangrange,
conn.parameters.model_wsize,
conn.parameters.model_feature_type, feature_parameters,
depths, nimages, 'jpg', conn.parameters.model_njobs)
for i in range(len(T)):
(data, rep, img) = T[i]
(height, width) = data.shape
if not passe:
passe = True
DATA = np.zeros((height * (len(T) + 100) *
conn.parameters.model_ntimes, width))
REP = np.zeros(height * (len(T) + 100) *
conn.parameters.model_ntimes)
b = 0
be = height
DATA[b:be, :] = data
REP[b:be] = rep
b = be
be = be + height
REP = REP[0:b]
DATA = DATA[0:b, :]
clf = ExtraTreesClassifier(
n_jobs=conn.parameters.model_njobs,
n_estimators=conn.parameters.model_ntrees)
clf = clf.fit(DATA, REP)
parameters_hash = {}
parameters_hash[
'cytomine_id_terms'] = conn.parameters.cytomine_id_terms
parameters_hash['model_R'] = conn.parameters.model_R
parameters_hash['model_RMAX'] = conn.parameters.model_RMAX
parameters_hash['model_P'] = conn.parameters.model_P
parameters_hash['model_npred'] = conn.parameters.model_npred
parameters_hash['model_ntrees'] = conn.parameters.model_ntrees
parameters_hash['model_ntimes'] = conn.parameters.model_ntimes
parameters_hash['model_angle'] = conn.parameters.model_angle
parameters_hash['model_depth'] = conn.parameters.model_depth
parameters_hash['model_step'] = conn.parameters.model_step
parameters_hash['window_size'] = conn.parameters.model_wsize
parameters_hash[
'feature_type'] = conn.parameters.model_feature_type
parameters_hash[
'feature_haar_n'] = conn.parameters.model_feature_haar_n
parameters_hash[
'feature_gaussian_n'] = conn.parameters.model_feature_gaussian_n
parameters_hash[
'feature_gaussian_std'] = conn.parameters.model_feature_gaussian_std
model_filename = joblib.dump(clf,
os.path.join(
out_path,
'%d_model.joblib' % (id_term)),
compress=3)[0]
cov_filename = joblib.dump([mx, my, cm],
os.path.join(
out_path,
'%d_cov.joblib' % (id_term)),
compress=3)[0]
parameter_filename = joblib.dump(
parameters_hash,
os.path.join(out_path, '%d_parameters.joblib' % id_term),
compress=3)[0]
AttachedFile(
conn.job,
domainIdent=conn.job.id,
filename=model_filename,
domainClassName="be.cytomine.processing.Job").upload()
AttachedFile(
conn.job,
domainIdent=conn.job.id,
filename=cov_filename,
domainClassName="be.cytomine.processing.Job").upload()
AttachedFile(
conn.job,
domainIndent=conn.job.id,
filename=parameter_filename,
domainClassName="be.cytomine.processing.Job").upload()
if conn.parameters.model_feature_type == 'haar' or conn.parameters.model_feature_type == 'gaussian':
add_filename = joblib.dump(
feature_parameters,
out_path.rstrip('/') + '/' + '%d_fparameters.joblib' %
(id_term))[0]
AttachedFile(
conn.job,
domainIdent=conn.job.id,
filename=add_filename,
domainClassName="be.cytomine.processing.Job").upload()
Property(conn.job, key="id_terms", value=sfinal.rstrip(" ")).save()
conn.job.update(progress=100,
status=Job.TERMINATED,
statusComment="Job terminated.")
"If unset, all images in the project are used.",
default=None)
parser.add_argument('--cytomine_id_job')
params, _ = parser.parse_known_args(sys.argv[1:])
with Cytomine(params.cytomine_host, params.cytomine_public_key,
params.cytomine_private_key) as c:
id_tags_for_images = params.cytomine_id_tags_for_images
id_project = params.cytomine_id_project
image_tags = id_tags_for_images if id_tags_for_images else None
images = ImageInstanceCollection(tags=image_tags).fetch_with_filter(
"project", id_project)
image_ids = [image.id for image in images]
groundtruths = AnnotationCollection()
groundtruths.showTerm = True
groundtruths.showWKT = True
groundtruths.images = image_ids
groundtruths.fetch()
predictions = AnnotationCollection()
predictions.showTerm = True
predictions.showWKT = True
predictions.images = image_ids
predictions.job = params.cytomine_id_job
predictions.fetch()
print("There are {} groundtruths and {} predictions".format(
len(groundtruths), len(predictions)))
def preprocess(cytomine, working_path, id_project, id_terms=None, id_tags_for_images=None):
"""
Get data from Cytomine in order to train YOLO.
:param cytomine: The Cytomine client
:param working_path: The path where files will be stored
:param id_project: The Cytomine project ID used to get data
:param id_terms: The Cytomine term IDS used to get data
:param id_tags_for_images: The Cytomine tags IDS associated to images used to get data
:return:
classes_filename: The name of the file with classes
image_filenames: A list of image filenames
annotation_filenames: A list of filenames with annotations in YOLO format
"""
if not os.path.exists(working_path):
os.makedirs(working_path)
images_path = os.path.join(working_path, IMG_DIRECTORY)
if not os.path.exists(images_path):
os.makedirs(images_path)
annotations_path = os.path.join(working_path, ANNOTATION_DIRECTORY)
if not os.path.exists(annotations_path):
os.makedirs(annotations_path)
terms = TermCollection().fetch_with_filter("project", id_project)
if id_terms:
filtered_term_ids = [int(id_term) for id_term in id_terms.split(',')]
filtered_terms = [term for term in terms if term.id in filtered_term_ids]
else:
filtered_terms = terms
terms_indexes = {term.id: i for i, term in enumerate(filtered_terms)}
# https://github.com/eriklindernoren/PyTorch-YOLOv3#train-on-custom-dataset
# Write obj.names
classes_filename = os.path.join(working_path, CLASSES_FILENAME)
with open(classes_filename, 'w') as f:
for term in filtered_terms:
f.write(term.name + os.linesep)
# Download images
image_filenames = []
image_tags = id_tags_for_images if id_tags_for_images else None
images = ImageInstanceCollection(tags=image_tags).fetch_with_filter("project", id_project)
for image in images:
image.dump(os.path.join(working_path, IMG_DIRECTORY, "{id}.png"), override=False)
image_filenames.append(image.filename)
# Create annotation files
annotation_filenames = []
for image in images:
annotations = AnnotationCollection()
annotations.image = image.id
annotations.terms = [t.id for t in filtered_terms] if id_terms else None
annotations.showWKT = True
annotations.showTerm = True
annotations.fetch()
filename = os.path.join(working_path, ANNOTATION_DIRECTORY, "{}.txt".format(image.id))
with open(filename, 'w') as f:
for annotation in annotations:
geometry = wkt.loads(annotation.location)
x, y, w, h = geometry_to_yolo(geometry, image.width, image.height)
for term_id in annotation.term:
# <object-class> <x_center> <y_center> <width> <height>
f.write("{} {:.12f} {:.12f} {:.12f} {:.12f}".format(terms_indexes[term_id], x, y, w, h) + os.linesep)
annotation_filenames.append(filename)
return classes_filename, image_filenames, annotation_filenames
def get_images_mask_per_annotation_per_user(proj_id, image_id, user_id,
scale_factor, dest):
im = ImageInstanceCollection()
im.project = proj_id
im.image = image_id
im.fetch_with_filter("project", proj_id)
image_width = int(im[0].width)
image_height = int(im[0].height)
print(image_height, image_width)
annotations = AnnotationCollection()
annotations.project = proj_id
annotations.image = image_id
annotations.user = user_id
annotations.showWKT = True
annotations.showMeta = True
annotations.showTerm = True
annotations.showGIS = True
annotations.showImage = True
annotations.showUser = True
annotations.fetch()
dct_anotations = {}
for a in annotations:
print(a.user)
if len(a.term) == 1:
term = a.term[0]
if term not in dct_anotations:
dct_anotations[term] = []
dct_anotations[term].append(a.location)
else:
warnings.warn("Not suited for multiple or no annotation term")
for t, lanno in dct_anotations.items():
result_image = Image.new(mode='1',
size=(int(image_width * scale_factor),
int(image_height * scale_factor)),
color=0)
for pwkt in lanno:
if pwkt.startswith("POLYGON"):
label = "POLYGON"
elif pwkt.startswith("MULTIPOLYGON"):
label = "MULTIPOLYGON"
coordinatesStringList = pwkt.replace(label, '')
if label == "POLYGON":
coordinates_string_lists = [coordinatesStringList]
elif label == "MULTIPOLYGON":
coordinates_string_lists = coordinatesStringList.split(
')), ((')
coordinates_string_lists = [
coordinatesStringList.replace('(', '').replace(')', '')
for coordinatesStringList in coordinates_string_lists
]
for coordinatesStringList in coordinates_string_lists:
# create lists of x and y coordinates
x_coords = []
y_coords = []
for point in coordinatesStringList.split(','):
point = point.strip(
string.whitespace) # remove leading and ending spaces
point = point.strip(
string.punctuation
) # Have seen some strings have a ')' at the end so remove it
x_coords.append(round(float(point.split(' ')[0])))
y_coords.append(round(float(point.split(' ')[1])))
x_coords_correct_lod = [
int(x * scale_factor) for x in x_coords
]
y_coords_correct_lod = [
image_height * scale_factor - int(x * scale_factor)
for x in y_coords
]
coords = [
(i, j)
for i, j in zip(x_coords_correct_lod, y_coords_correct_lod)
]
# draw the polygone in an image and fill it
ImageDraw.Draw(result_image).polygon(coords, outline=1, fill=1)
result_image.save(params.dest + '/' + str(t) + '.png')
def main(argv):
with CytomineJob.from_cli(argv) as cj:
cj.job.update(progress=1, statusComment="Initialisation")
cj.log(str(cj.parameters))
term_ids = [int(term_id) for term_id in cj.parameters.cytomine_id_terms.split(",")]
terms = TermCollection().fetch_with_filter("project", cj.parameters.cytomine_id_project)
terms = [term for term in terms if term.id in term_ids]
image_ids = [int(image_id) for image_id in cj.parameters.cytomine_id_images.split(",")]
images = ImageInstanceCollection(light=True).fetch_with_filter("project", cj.parameters.cytomine_id_project)
images = [image for image in images if image.id in image_ids]
if hasattr(cj.parameters, "cytomine_id_users") and cj.parameters.cytomine_id_users is not None:
user_ids = [int(user_id) for user_id in cj.parameters.cytomine_id_users.split(",")]
else:
user_ids = []
if hasattr(cj.parameters, "cytomine_id_jobs") and cj.parameters.cytomine_id_jobs is not None:
job_ids = [int(job_id) for job_id in cj.parameters.cytomine_id_jobs.split(",")]
jobs = JobCollection(project=cj.parameters.cytomine_id_project).fetch()
jobs = [job for job in jobs if job.id in job_ids]
else:
jobs = []
userjobs_ids = [job.userJob for job in jobs]
all_user_ids = user_ids + userjobs_ids
cj.job.update(progress=20, statusComment="Collect data")
ac = AnnotationCollection()
ac.terms = term_ids
ac.images = image_ids
ac.showMeta = True
ac.showGIS = True
ac.showTerm = True
ac.reviewed = True if cj.parameters.cytomine_reviewed_only else None
ac.users = all_user_ids if len(all_user_ids) > 0 else None
ac.fetch()
cj.job.update(progress=55, statusComment="Compute statistics")
data = dict()
for image in images:
d = dict()
areas = [a.area for a in ac if a.image == image.id]
total_area = np.sum(areas)
d['total'] = total_area
d['count'] = len(areas)
d['ratio'] = 1.0
for term in terms:
annotations = [a for a in ac if a.image == image.id and term.id in a.term]
areas = [a.area for a in annotations]
d[term.name] = dict()
d[term.name]['total'] = np.sum(areas)
d[term.name]['count'] = len(annotations)
d[term.name]['ratio'] = d[term.name]['total'] / float(total_area) if total_area > 0 else 0
d[term.name]['mean'] = np.mean(areas)
d[term.name]['annotations'] = [{"created": a.created, "area": a.area} for a in annotations]
data[image.instanceFilename] = d
cj.job.update(progress=90, statusComment="Write CSV report")
with open("stat-area.csv", "w") as f:
for l in write_csv(data, terms):
f.write("{}\n".format(l))
job_data = JobData(id_job=cj.job.id, key="Area CSV report", filename="stat-area.csv")
job_data = job_data.save()
job_data.upload("stat-area.csv")
cj.job.update(statusComment="Finished.", progress=100)