def makeDir(imFolder, outFolder, labelFile, dirFile, classRef, res=(300, 300)):
coords, imNames, classes = get_labels(labelFile)
print('Got labels')
imFiles = listdir(imFolder)
with open(dirFile, 'w') as outFile:
for im in imFiles:
if im.endswith('.tif'):
arr = np.array(Image.open(path.join(imFolder, im)))
chips, boxes, boxClasses = chip_image(arr,
coords[imNames == im],
classes[imNames == im],
res)
for i in range(len(chips)):
chip = Image.fromarray(chips[i])
newName = path.join(outFolder,
"{}_{}.jpg".format(im[:-4], i))
chip.save(newName)
boxStr = []
emptyChip = False
for j in range(len(boxes[i])):
box = boxes[i][j]
boxClass = boxClasses[i][j]
if boxClass == 0:
emptyChip = True
classID = getRealID(int(boxClasses[i][j]), classRef)
boxStr.append("{},{},{},{},{}".format(
int(box[0]), int(box[1]), int(box[2]), int(box[3]),
classID))
if not emptyChip:
infoStr = '{} {}\n'.format(newName, " ".join(boxStr))
outFile.write(infoStr)
# print(newName)
print(im)
def get_labels_for_chip(src, json_file):
"""
Get the bbox and class for a chip
:param src: path to chip image
:param json_file: path to json_file with labels
:return: bbox coords and classes
"""
coords, chips, classes = wv.get_labels(json_file)
chip_name = image_name(src)
coords = coords[chips == chip_name]
classes = classes[chips == chip_name].astype(np.int64)
return coords, classes
type=str)
parser.add_argument('-d', '--id2name', help='the id2name txt file', type=str)
parser.add_argument('-o',
'--output',
help='output directory',
type=str,
default='./')
parser.add_argument('-r',
'--resolution',
help='output image resolution',
type=int,
default=672)
args = parser.parse_args()
## load all annotations
coords, img_fn, classes = wv.get_labels(args.geojson)
img_files = list(set(img_fn))
print("total image files: ", len(img_files), "first 5 image files = ",
img_files[:5])
cls_cnt = Counter(classes).most_common()
## Load id2name
cid2name = {}
with open(args.id2name, 'r') as f:
for line in f:
x, y = line.strip().split(':')
cid2name[int(x)] = y
# map id to consecutive ids
idremap = {x: y for x, y in zip(sorted(cid2name.keys()), range(len(cid2name)))}
img_dir = args.images
## divide the TIF images into smaller jpg images
import aug_util as aug
import wv_util as wv
import matplotlib.pyplot as plt
from PIL import Image
import numpy as np
import csv
import tqdm
fdir = '/data/zjc4/'
#Load an image
chip_name = fdir + 'train_images/104.tif'
cdir = "/data/zjc4/chipped/train/"
arr = wv.get_image(chip_name)
#Loading our labels
coords1, chips1, classes1 = wv.get_labels(fdir + 'xView_train.geojson')
import glob
all_images = glob.glob(fdir + 'train_images/*.tif')
#Load the class number -> class string label map
labels = {}
with open('xview_class_labels.txt') as f:
for row in csv.reader(f):
labels[int(row[0].split(":")[0])] = row[0].split(":")[1]
pass
pass
i = 0
for chip_name in tqdm.tqdm(all_images[:300]):
chip_name = (chip_name.split("/")[-1])
img_name = chip_name.split(".")[0]
parser = argparse.ArgumentParser(
description='Create Annotations and images for xview chips')
parser.add_argument('chip_size', type=int)
args = parser.parse_args()
######### Inputs
CHIP_SIZE = args.chip_size
OLD_ROOT = "../xView"
NEW_ROOT = "../xView-voc-{}".format(CHIP_SIZE)
IMAGESETS_PATH = os.path.join(NEW_ROOT, "ImageSets", "Main")
CHIP_SHAPE = (CHIP_SIZE, CHIP_SIZE)
OVERLAP = 0.20
#########
# Load all of the labels from .geojson
all_coords, all_chips, all_classes = wv.get_labels(OLD_ROOT +
"/xView_train.geojson")
print("Full Dataset Stats:")
print(all_coords.shape)
print(all_chips.shape)
print(all_classes.shape)
# Get all of the unique .tif names from all_chips
tif_names = np.unique(all_chips)
rows = []
xyz = 0
# For each unique .tif
for unique_tif in tif_names:
#resolutions should be largest -> smallest. We take the number of chips in the largest resolution and make
#sure all future resolutions have less than 1.5times that number of images to prevent chip size imbalance.
#res = [(500,500),(400,400),(300,300),(200,200)]
res = [(args.resolution, args.resolution)]
images = {}
boxes = {}
train_chips = 0
test_chips = 0
skip_chips = 0
#Parameters
max_chips_per_res = 100000
coords, chips, classes = wv.get_labels(args.json_filepath)
for res_ind, it in enumerate(res):
tot_box = 0
logging.info("Res: %s" % str(it))
ind_chips = 0
fnames = glob.glob(args.image_folder + "*.tif")
if args.images:
fimages = args.images.split(',')
image_filter = [
'%s%s.tif' % (args.image_folder, f) for f in fimages
]
fnames = [f for f in fnames if f in image_filter]
print(fnames)
import matplotlib.pyplot as plt
import numpy as np
import csv
chip_name = "1052.tif"
arr = wv.get_image("../xView/train_images/" + chip_name)
#### Load labels for whole dataset
# - coords.shape = (601937, 4)
# - chips.shape = (601937,)
# - classes.shape = (601937,)
# This makes three flat, index aligned lists, where all of the chips from all images are
# assembled. If we want all of the info for one chip, we look up the chip name in chips
# list and use those indexes to access the other lists.
coords, chips, classes = wv.get_labels("../xView/xView_train.geojson")
#print coords[0] # = [2712, 1145, 2746, 1177]
#print chips[0] # = 2355.tif
#print classes[0] # = 73.0
# Get info specific to our chip
coords = coords[chips == chip_name]
classes = classes[chips == chip_name].astype(np.int64)
print("# Objects In Image: ", len(classes))
# Create a Class # -> Class Label Map
labels = {}
with open('xview_class_labels.txt') as f:
for row in csv.reader(f):
