def prepare_dataset(dataset_path): path=os.path.join(dataset_path,"mpii") #prepare annotation annos_dir=os.path.join(path,"mpii_human_pose_v1_u12_2") mat_annos_path=os.path.join(annos_dir,"mpii_human_pose_v1_u12_1.mat") if(os.path.exists(mat_annos_path) is False): logging.info(" downloading annotations") os.system(f"wget https://datasets.d2.mpi-inf.mpg.de/andriluka14cvpr/mpii_human_pose_v1_u12_2.zip -P {path}") unzip(os.path.join(path,"mpii_human_pose_v1_u12_2.zip"),path) del_file(os.path.join(path,"mpii_human_pose_v1_u12_2.zip")) else: logging.info(" annotations exist") #prepare json annotation train_annos_path=os.path.join(annos_dir,"mpii_human_pose_train.json") val_annos_path=os.path.join(annos_dir,"mpii_human_pose_val.json") if((not os.path.exists(train_annos_path)) or (not os.path.exists(val_annos_path))): print(" json annotation doesn't exist, generaing json annotations...") json_annos=generate_json(mat_annos_path) #left 3000 images for val split_val_ids=None split_path=os.path.join(annos_dir,"split_val.json") if(os.path.exists(split_path)): print("using preset split val set") split_val_ids=json.load(open(split_path,"r")) else: print("using the first 3000 annotations as default val dataset") train_annos={} val_annos={} for annos_num,image_path in enumerate(json_annos.keys()): if(split_val_ids!=None): if(image_path in split_val_ids): val_annos[image_path]=json_annos[image_path] else: train_annos[image_path]=json_annos[image_path] else: if(annos_num<3000): val_annos[image_path]=json_annos[image_path] else: train_annos[image_path]=json_annos[image_path] print(f"generated train annos:{len(train_annos.keys())}") print(f"generated val annos:{len(val_annos.keys())}") train_file=open(train_annos_path,"w") json.dump(train_annos,train_file) train_file.close() val_file=open(val_annos_path,"w") json.dump(val_annos,val_file) val_file.close() print(" json annotation generation finished!") #prepare image images_path=os.path.join(path,"images") if(os.path.exists(images_path) is False): logging.info(" downloading images") os.system(f"wget https://datasets.d2.mpi-inf.mpg.de/andriluka14cvpr/mpii_human_pose_v1.tar.gz -P {path}") os.system(f"tar -xvf {os.path.join(path,'mpii_human_pose_v1.tar.gz')}") del_file(os.path.join(path,"mpii_human_pose_v1.tar.gz")) else: logging.info(" images exist") return train_annos_path,val_annos_path,images_path
def load_cyclegan_dataset(filename='summer2winter_yosemite', path='raw_data'): """Load images from CycleGAN's database, see `this link <https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/>`__. Parameters ------------ filename : str The dataset you want, see `this link <https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/>`__. path : str The path that the data is downloaded to, defaults is `data/cyclegan` Examples --------- >>> im_train_A, im_train_B, im_test_A, im_test_B = load_cyclegan_dataset(filename='summer2winter_yosemite') """ path = os.path.join(path, 'cyclegan') url = 'https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/' if folder_exists(os.path.join(path, filename)) is False: logging.info("[*] {} is nonexistent in {}".format(filename, path)) maybe_download_and_extract(filename + '.zip', path, url, extract=True) del_file(os.path.join(path, filename + '.zip')) def load_image_from_folder(path): path_imgs = load_file_list(path=path, regx='\\.jpg', printable=False) return visualize.read_images(path_imgs, path=path, n_threads=10, printable=False) im_train_A = load_image_from_folder(os.path.join(path, filename, "trainA")) im_train_B = load_image_from_folder(os.path.join(path, filename, "trainB")) im_test_A = load_image_from_folder(os.path.join(path, filename, "testA")) im_test_B = load_image_from_folder(os.path.join(path, filename, "testB")) def if_2d_to_3d(images): # [h, w] --> [h, w, 3] for i, _v in enumerate(images): if len(images[i].shape) == 2: images[i] = images[i][:, :, np.newaxis] images[i] = np.tile(images[i], (1, 1, 3)) return images im_train_A = if_2d_to_3d(im_train_A) im_train_B = if_2d_to_3d(im_train_B) im_test_A = if_2d_to_3d(im_test_A) im_test_B = if_2d_to_3d(im_test_B) return im_train_A, im_train_B, im_test_A, im_test_B
def load_cyclegan_dataset(filename='summer2winter_yosemite', path='data'): """Load images from CycleGAN's database, see `this link <https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/>`__. Parameters ------------ filename : str The dataset you want, see `this link <https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/>`__. path : str The path that the data is downloaded to, defaults is `data/cyclegan` Examples --------- >>> im_train_A, im_train_B, im_test_A, im_test_B = load_cyclegan_dataset(filename='summer2winter_yosemite') """ path = os.path.join(path, 'cyclegan') url = 'https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/' if folder_exists(os.path.join(path, filename)) is False: logging.info("[*] {} is nonexistent in {}".format(filename, path)) maybe_download_and_extract(filename + '.zip', path, url, extract=True) del_file(os.path.join(path, filename + '.zip')) def load_image_from_folder(path): path_imgs = load_file_list(path=path, regx='\\.jpg', printable=False) return visualize.read_images(path_imgs, path=path, n_threads=10, printable=False) im_train_A = load_image_from_folder(os.path.join(path, filename, "trainA")) im_train_B = load_image_from_folder(os.path.join(path, filename, "trainB")) im_test_A = load_image_from_folder(os.path.join(path, filename, "testA")) im_test_B = load_image_from_folder(os.path.join(path, filename, "testB")) def if_2d_to_3d(images): # [h, w] --> [h, w, 3] for i, _v in enumerate(images): if len(images[i].shape) == 2: images[i] = images[i][:, :, np.newaxis] images[i] = np.tile(images[i], (1, 1, 3)) return images im_train_A = if_2d_to_3d(im_train_A) im_train_B = if_2d_to_3d(im_train_B) im_test_A = if_2d_to_3d(im_test_A) im_test_B = if_2d_to_3d(im_test_B) return im_train_A, im_train_B, im_test_A, im_test_B
def load_voc_dataset(path='data', dataset='2012', contain_classes_in_person=False): """Pascal VOC 2007/2012 Dataset. It has 20 objects: aeroplane, bicycle, bird, boat, bottle, bus, car, cat, chair, cow, diningtable, dog, horse, motorbike, person, pottedplant, sheep, sofa, train, tvmonitor and additional 3 classes : head, hand, foot for person. Parameters ----------- path : str The path that the data is downloaded to, defaults is ``data/VOC``. dataset : str The VOC dataset version, `2012`, `2007`, `2007test` or `2012test`. We usually train model on `2007+2012` and test it on `2007test`. contain_classes_in_person : boolean Whether include head, hand and foot annotation, default is False. Returns --------- imgs_file_list : list of str Full paths of all images. imgs_semseg_file_list : list of str Full paths of all maps for semantic segmentation. Note that not all images have this map! imgs_insseg_file_list : list of str Full paths of all maps for instance segmentation. Note that not all images have this map! imgs_ann_file_list : list of str Full paths of all annotations for bounding box and object class, all images have this annotations. classes : list of str Classes in order. classes_in_person : list of str Classes in person. classes_dict : dictionary Class label to integer. n_objs_list : list of int Number of objects in all images in ``imgs_file_list`` in order. objs_info_list : list of str Darknet format for the annotation of all images in ``imgs_file_list`` in order. ``[class_id x_centre y_centre width height]`` in ratio format. objs_info_dicts : dictionary The annotation of all images in ``imgs_file_list``, ``{imgs_file_list : dictionary for annotation}``, format from `TensorFlow/Models/object-detection <https://github.com/tensorflow/models/blob/master/object_detection/create_pascal_tf_record.py>`__. Examples ---------- >>> imgs_file_list, imgs_semseg_file_list, imgs_insseg_file_list, imgs_ann_file_list, >>> classes, classes_in_person, classes_dict, >>> n_objs_list, objs_info_list, objs_info_dicts = tl.files.load_voc_dataset(dataset="2012", contain_classes_in_person=False) >>> idx = 26 >>> print(classes) ... ['aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog', 'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor'] >>> print(classes_dict) ... {'sheep': 16, 'horse': 12, 'bicycle': 1, 'bottle': 4, 'cow': 9, 'sofa': 17, 'car': 6, 'dog': 11, 'cat': 7, 'person': 14, 'train': 18, 'diningtable': 10, 'aeroplane': 0, 'bus': 5, 'pottedplant': 15, 'tvmonitor': 19, 'chair': 8, 'bird': 2, 'boat': 3, 'motorbike': 13} >>> print(imgs_file_list[idx]) ... data/VOC/VOC2012/JPEGImages/2007_000423.jpg >>> print(n_objs_list[idx]) ... 2 >>> print(imgs_ann_file_list[idx]) ... data/VOC/VOC2012/Annotations/2007_000423.xml >>> print(objs_info_list[idx]) ... 14 0.173 0.461333333333 0.142 0.496 ... 14 0.828 0.542666666667 0.188 0.594666666667 >>> ann = tl.prepro.parse_darknet_ann_str_to_list(objs_info_list[idx]) >>> print(ann) ... [[14, 0.173, 0.461333333333, 0.142, 0.496], [14, 0.828, 0.542666666667, 0.188, 0.594666666667]] >>> c, b = tl.prepro.parse_darknet_ann_list_to_cls_box(ann) >>> print(c, b) ... [14, 14] [[0.173, 0.461333333333, 0.142, 0.496], [0.828, 0.542666666667, 0.188, 0.594666666667]] References ------------- - `Pascal VOC2012 Website <https://pjreddie.com/projects/pascal-voc-dataset-mirror/>`__. - `Pascal VOC2007 Website <https://pjreddie.com/projects/pascal-voc-dataset-mirror/>`__. """ path = os.path.join(path, 'VOC') def _recursive_parse_xml_to_dict(xml): """Recursively parses XML contents to python dict. We assume that `object` tags are the only ones that can appear multiple times at the same level of a tree. Args: xml: xml tree obtained by parsing XML file contents using lxml.etree Returns: Python dictionary holding XML contents. """ if xml is not None: return {xml.tag: xml.text} result = {} for child in xml: child_result = _recursive_parse_xml_to_dict(child) if child.tag != 'object': result[child.tag] = child_result[child.tag] else: if child.tag not in result: result[child.tag] = [] result[child.tag].append(child_result[child.tag]) return {xml.tag: result} import xml.etree.ElementTree as ET if dataset == "2012": url = "http://pjreddie.com/media/files/" tar_filename = "VOCtrainval_11-May-2012.tar" extracted_filename = "VOC2012" #"VOCdevkit/VOC2012" logging.info(" [============= VOC 2012 =============]") elif dataset == "2012test": extracted_filename = "VOC2012test" #"VOCdevkit/VOC2012" logging.info(" [============= VOC 2012 Test Set =============]") logging.info( " \nAuthor: 2012test only have person annotation, so 2007test is highly recommended for testing !\n" ) import time time.sleep(3) if os.path.isdir(os.path.join(path, extracted_filename)) is False: logging.info( "For VOC 2012 Test data - online registration required") logging.info( " Please download VOC2012test.tar from: \n register: http://host.robots.ox.ac.uk:8080 \n voc2012 : http://host.robots.ox.ac.uk:8080/eval/challenges/voc2012/ \ndownload: http://host.robots.ox.ac.uk:8080/eval/downloads/VOC2012test.tar" ) logging.info( " unzip VOC2012test.tar,rename the folder to VOC2012test and put it into %s" % path) exit() # # http://host.robots.ox.ac.uk:8080/eval/downloads/VOC2012test.tar # url = "http://host.robots.ox.ac.uk:8080/eval/downloads/" # tar_filename = "VOC2012test.tar" elif dataset == "2007": url = "http://pjreddie.com/media/files/" tar_filename = "VOCtrainval_06-Nov-2007.tar" extracted_filename = "VOC2007" logging.info(" [============= VOC 2007 =============]") elif dataset == "2007test": # http://host.robots.ox.ac.uk/pascal/VOC/voc2007/index.html#testdata # http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar url = "http://pjreddie.com/media/files/" tar_filename = "VOCtest_06-Nov-2007.tar" extracted_filename = "VOC2007test" logging.info(" [============= VOC 2007 Test Set =============]") else: raise Exception( "Please set the dataset aug to 2012, 2012test or 2007.") # download dataset if dataset != "2012test": from sys import platform as _platform if folder_exists(os.path.join(path, extracted_filename)) is False: logging.info("[VOC] {} is nonexistent in {}".format( extracted_filename, path)) maybe_download_and_extract(tar_filename, path, url, extract=True) del_file(os.path.join(path, tar_filename)) if dataset == "2012": if _platform == "win32": os.system("move {}\VOCdevkit\VOC2012 {}\VOC2012".format( path, path)) else: os.system("mv {}/VOCdevkit/VOC2012 {}/VOC2012".format( path, path)) elif dataset == "2007": if _platform == "win32": os.system("move {}\VOCdevkit\VOC2007 {}\VOC2007".format( path, path)) else: os.system("mv {}/VOCdevkit/VOC2007 {}/VOC2007".format( path, path)) elif dataset == "2007test": if _platform == "win32": os.system( "move {}\VOCdevkit\VOC2007 {}\VOC2007test".format( path, path)) else: os.system("mv {}/VOCdevkit/VOC2007 {}/VOC2007test".format( path, path)) del_folder(os.path.join(path, 'VOCdevkit')) # object classes(labels) NOTE: YOU CAN CUSTOMIZE THIS LIST classes = [ "aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor" ] if contain_classes_in_person: classes_in_person = ["head", "hand", "foot"] else: classes_in_person = [] classes += classes_in_person # use extra 3 classes for person classes_dict = utils.list_string_to_dict(classes) logging.info("[VOC] object classes {}".format(classes_dict)) # 1. image path list # folder_imgs = path+"/"+extracted_filename+"/JPEGImages/" folder_imgs = os.path.join(path, extracted_filename, "JPEGImages") imgs_file_list = load_file_list(path=folder_imgs, regx='\\.jpg', printable=False) logging.info("[VOC] {} images found".format(len(imgs_file_list))) imgs_file_list.sort( key=lambda s: int(s.replace('.', ' ').replace('_', '').split(' ')[-2] )) # 2007_000027.jpg --> 2007000027 imgs_file_list = [os.path.join(folder_imgs, s) for s in imgs_file_list] # logging.info('IM',imgs_file_list[0::3333], imgs_file_list[-1]) if dataset != "2012test": ##======== 2. semantic segmentation maps path list # folder_semseg = path+"/"+extracted_filename+"/SegmentationClass/" folder_semseg = os.path.join(path, extracted_filename, "SegmentationClass") imgs_semseg_file_list = load_file_list(path=folder_semseg, regx='\\.png', printable=False) logging.info("[VOC] {} maps for semantic segmentation found".format( len(imgs_semseg_file_list))) imgs_semseg_file_list.sort(key=lambda s: int( s.replace('.', ' ').replace('_', '').split(' ')[-2]) ) # 2007_000032.png --> 2007000032 imgs_semseg_file_list = [ os.path.join(folder_semseg, s) for s in imgs_semseg_file_list ] # logging.info('Semantic Seg IM',imgs_semseg_file_list[0::333], imgs_semseg_file_list[-1]) ##======== 3. instance segmentation maps path list # folder_insseg = path+"/"+extracted_filename+"/SegmentationObject/" folder_insseg = os.path.join(path, extracted_filename, "SegmentationObject") imgs_insseg_file_list = load_file_list(path=folder_insseg, regx='\\.png', printable=False) logging.info("[VOC] {} maps for instance segmentation found".format( len(imgs_semseg_file_list))) imgs_insseg_file_list.sort(key=lambda s: int( s.replace('.', ' ').replace('_', '').split(' ')[-2]) ) # 2007_000032.png --> 2007000032 imgs_insseg_file_list = [ os.path.join(folder_insseg, s) for s in imgs_insseg_file_list ] # logging.info('Instance Seg IM',imgs_insseg_file_list[0::333], imgs_insseg_file_list[-1]) else: imgs_semseg_file_list = [] imgs_insseg_file_list = [] # 4. annotations for bounding box and object class # folder_ann = path+"/"+extracted_filename+"/Annotations/" folder_ann = os.path.join(path, extracted_filename, "Annotations") imgs_ann_file_list = load_file_list(path=folder_ann, regx='\\.xml', printable=False) logging.info( "[VOC] {} XML annotation files for bounding box and object class found" .format(len(imgs_ann_file_list))) imgs_ann_file_list.sort( key=lambda s: int(s.replace('.', ' ').replace('_', '').split(' ')[-2] )) # 2007_000027.xml --> 2007000027 imgs_ann_file_list = [ os.path.join(folder_ann, s) for s in imgs_ann_file_list ] # logging.info('ANN',imgs_ann_file_list[0::3333], imgs_ann_file_list[-1]) if dataset == "2012test": # remove unused images in JPEG folder imgs_file_list_new = [] for ann in imgs_ann_file_list: ann = os.path.split(ann)[-1].split('.')[0] for im in imgs_file_list: if ann in im: imgs_file_list_new.append(im) break imgs_file_list = imgs_file_list_new logging.info("[VOC] keep %d images" % len(imgs_file_list_new)) # parse XML annotations def convert(size, box): dw = 1. / size[0] dh = 1. / size[1] x = (box[0] + box[1]) / 2.0 y = (box[2] + box[3]) / 2.0 w = box[1] - box[0] h = box[3] - box[2] x = x * dw w = w * dw y = y * dh h = h * dh return x, y, w, h def convert_annotation(file_name): """Given VOC2012 XML Annotations, returns number of objects and info.""" in_file = open(file_name) out_file = "" tree = ET.parse(in_file) root = tree.getroot() size = root.find('size') w = int(size.find('width').text) h = int(size.find('height').text) n_objs = 0 for obj in root.iter('object'): if dataset != "2012test": difficult = obj.find('difficult').text cls = obj.find('name').text if cls not in classes or int(difficult) == 1: continue else: cls = obj.find('name').text if cls not in classes: continue cls_id = classes.index(cls) xmlbox = obj.find('bndbox') b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text)) bb = convert((w, h), b) out_file += str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n' n_objs += 1 if cls in "person": for part in obj.iter('part'): cls = part.find('name').text if cls not in classes_in_person: continue cls_id = classes.index(cls) xmlbox = part.find('bndbox') b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text)) bb = convert((w, h), b) # out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n') out_file += str(cls_id) + " " + " ".join( [str(a) for a in bb]) + '\n' n_objs += 1 in_file.close() return n_objs, out_file logging.info("[VOC] Parsing xml annotations files") n_objs_list = [] objs_info_list = [] # Darknet Format list of string objs_info_dicts = {} for idx, ann_file in enumerate(imgs_ann_file_list): n_objs, objs_info = convert_annotation(ann_file) n_objs_list.append(n_objs) objs_info_list.append(objs_info) with tf.gfile.GFile(ann_file, 'r') as fid: xml_str = fid.read() xml = etree.fromstring(xml_str) data = _recursive_parse_xml_to_dict(xml)['annotation'] objs_info_dicts.update({imgs_file_list[idx]: data}) return imgs_file_list, imgs_semseg_file_list, imgs_insseg_file_list, imgs_ann_file_list, classes, classes_in_person, classes_dict, n_objs_list, objs_info_list, objs_info_dicts
def prepare_dataset(data_path="./data", version="2017", task="person"): """Download MSCOCO Dataset. Both 2014 and 2017 dataset have train, validate and test sets, but 2017 version put less data into the validation set (115k train, 5k validate) i.e. has more training data. Parameters ----------- path : str The path that the data is downloaded to, defaults is ``data/mscoco...``. dataset : str The MSCOCO dataset version, `2014` or `2017`. task : str person for pose estimation, caption for image captioning, instance for segmentation. Returns --------- train_im_path : str Folder path of all training images. train_ann_path : str File path of training annotations. val_im_path : str Folder path of all validating images. val_ann_path : str File path of validating annotations. test_im_path : str Folder path of all testing images. test_ann_path : None File path of testing annotations, but as the test sets of MSCOCO 2014 and 2017 do not have annotation, returns None. Examples ---------- >>> train_im_path, train_ann_path, val_im_path, val_ann_path, _, _ = \ ... tl.files.load_mscoco_dataset('data', '2017') References ------------- - `MSCOCO <http://mscoco.org>`__. """ if version == "2014": logging.info(" [============= MSCOCO 2014 =============]") path = os.path.join(data_path, 'mscoco2014') if folder_exists(os.path.join(path, "annotations")) is False: logging.info(" downloading annotations") os.system( "wget http://images.cocodataset.org/annotations/annotations_trainval2014.zip -P {}" .format(path)) unzip(os.path.join(path, "annotations_trainval2014.zip"), path) del_file(os.path.join(path, "annotations_trainval2014.zip")) else: logging.info(" annotations exists") if folder_exists(os.path.join(path, "val2014")) is False: logging.info(" downloading validating images") os.system( "wget http://images.cocodataset.org/zips/val2014.zip -P {}". format(path)) unzip(os.path.join(path, "val2014.zip"), path) del_file(os.path.join(path, "val2014.zip")) else: logging.info(" validating images exists") if folder_exists(os.path.join(path, "train2014")) is False: logging.info(" downloading training images") os.system( "wget http://images.cocodataset.org/zips/train2014.zip -P {}". format(path)) unzip(os.path.join(path, "train2014.zip"), path) del_file(os.path.join(path, "train2014.zip")) else: logging.info(" training images exists") if folder_exists(os.path.join(path, "test2014")) is False: logging.info(" downloading testing images") os.system( "wget http://images.cocodataset.org/zips/test2014.zip -P {}". format(path)) unzip(os.path.join(path, "test2014.zip"), path) del_file(os.path.join(path, "test2014.zip")) else: logging.info(" testing images exists") elif version == "2017": # 11.5w train, 0.5w valid, test (no annotation) path = os.path.join(data_path, 'mscoco2017') if folder_exists(os.path.join(path, "annotations")) is False: logging.info(" downloading annotations") os.system( "wget http://images.cocodataset.org/annotations/annotations_trainval2017.zip -P {}" .format(path)) unzip(os.path.join(path, "annotations_trainval2017.zip"), path) del_file(os.path.join(path, "annotations_trainval2017.zip")) else: logging.info(" annotations exists") if folder_exists(os.path.join(path, "val2017")) is False: logging.info(" downloading validating images") os.system( "wget http://images.cocodataset.org/zips/val2017.zip -P {}". format(path)) unzip(os.path.join(path, "val2017.zip"), path) del_file(os.path.join(path, "val2017.zip")) else: logging.info(" validating images exists") if folder_exists(os.path.join(path, "train2017")) is False: logging.info(" downloading training images") os.system( "wget http://images.cocodataset.org/zips/train2017.zip -P {}". format(path)) unzip(os.path.join(path, "train2017.zip"), path) del_file(os.path.join(path, "train2017.zip")) else: logging.info(" training images exists") ''' if folder_exists(os.path.join(path, "test2017")) is False: logging.info(" downloading testing images") os.system("wget http://images.cocodataset.org/zips/test2017.zip -P {}".format(path)) unzip(os.path.join(path, "test2017.zip"), path) del_file(os.path.join(path, "test2017.zip")) else: logging.info(" testing images exists") ''' print("temply ignore test dataset") else: raise Exception( "dataset can only be 2014 and 2017, see MSCOCO website for more details." ) if version == "2014": train_images_path = os.path.join(path, "train2014") if task == "person": train_annotations_file_path = os.path.join( path, "annotations", "person_keypoints_train2014.json") elif task == "caption": train_annotations_file_path = os.path.join( path, "annotations", "captions_train2014.json") elif task == "instance": train_annotations_file_path = os.path.join( path, "annotations", "instances_train2014.json") else: raise Exception("unknown task") val_images_path = os.path.join(path, "val2014") if task == "person": val_annotations_file_path = os.path.join( path, "annotations", "person_keypoints_val2014.json") elif task == "caption": val_annotations_file_path = os.path.join(path, "annotations", "captions_val2014.json") elif task == "instance": val_annotations_file_path = os.path.join(path, "annotations", "instances_val2014.json") test_images_path = os.path.join(path, "test2014") test_annotations_file_path = None #os.path.join(path, "annotations", "person_keypoints_test2014.json") elif version == "2017": train_images_path = os.path.join(path, "train2017") if task == "person": train_annotations_file_path = os.path.join( path, "annotations", "person_keypoints_train2017.json") elif task == "caption": train_annotations_file_path = os.path.join( path, "annotations", "captions_train2017.json") elif task == "instance": train_annotations_file_path = os.path.join( path, "annotations", "instances_train2017.json") else: raise Exception("unknown task") val_images_path = os.path.join(path, "val2017") if task == "person": val_annotations_file_path = os.path.join( path, "annotations", "person_keypoints_val2017.json") elif task == "caption": val_annotations_file_path = os.path.join(path, "annotations", "captions_val2017.json") elif task == "instance": val_annotations_file_path = os.path.join(path, "annotations", "instances_val2017.json") test_images_path = os.path.join(path, "test2017") test_annotations_file_path = None # os.path.join(path, "annotations", "person_keypoints_test2017.json") return train_images_path,train_annotations_file_path,\ val_images_path,val_annotations_file_path,\ test_images_path,test_annotations_file_path
def load_mscoco_dataset(path='data', dataset='2017', task='person'): # TODO move to tl.files later """Download MSCOCO Dataset. Both 2014 and 2017 dataset have train, validate and test sets, but 2017 version put less data into the validation set (115k train, 5k validate) i.e. has more training data. Parameters ----------- path : str The path that the data is downloaded to, defaults is ``data/mscoco...``. dataset : str The MSCOCO dataset version, `2014` or `2017`. task : str person for pose estimation, caption for image captioning, instance for segmentation. Returns --------- train_im_path : str Folder path of all training images. train_ann_path : str File path of training annotations. val_im_path : str Folder path of all validating images. val_ann_path : str File path of validating annotations. test_im_path : str Folder path of all testing images. test_ann_path : None File path of testing annotations, but as the test sets of MSCOCO 2014 and 2017 do not have annotation, returns None. Examples ---------- >>> train_im_path, train_ann_path, val_im_path, val_ann_path, _, _ = \ ... tl.files.load_mscoco_dataset('data', '2017') References ------------- - `MSCOCO <http://mscoco.org>`__. """ import zipfile def unzip(path_to_zip_file, directory_to_extract_to): zip_ref = zipfile.ZipFile(path_to_zip_file, 'r') zip_ref.extractall(directory_to_extract_to) zip_ref.close() if dataset == "2014": logging.info(" [============= MSCOCO 2014 =============]") path = os.path.join(path, 'mscoco2014') if folder_exists(os.path.join(path, "annotations")) is False: logging.info(" downloading annotations") os.system( "wget http://images.cocodataset.org/annotations/annotations_trainval2014.zip -P {}" .format(path)) unzip(os.path.join(path, "annotations_trainval2014.zip"), path) del_file(os.path.join(path, "annotations_trainval2014.zip")) else: logging.info(" annotations exists") if folder_exists(os.path.join(path, "val2014")) is False: logging.info(" downloading validating images") os.system( "wget http://images.cocodataset.org/zips/val2014.zip -P {}". format(path)) unzip(os.path.join(path, "val2014.zip"), path) del_file(os.path.join(path, "val2014.zip")) else: logging.info(" validating images exists") if folder_exists(os.path.join(path, "train2014")) is False: logging.info(" downloading training images") os.system( "wget http://images.cocodataset.org/zips/train2014.zip -P {}". format(path)) unzip(os.path.join(path, "train2014.zip"), path) del_file(os.path.join(path, "train2014.zip")) else: logging.info(" training images exists") if folder_exists(os.path.join(path, "test2014")) is False: logging.info(" downloading testing images") os.system( "wget http://images.cocodataset.org/zips/test2014.zip -P {}". format(path)) unzip(os.path.join(path, "test2014.zip"), path) del_file(os.path.join(path, "test2014.zip")) else: logging.info(" testing images exists") elif dataset == "2017": # 11.5w train, 0.5w valid, test (no annotation) path = os.path.join(path, 'mscoco2017') if folder_exists(os.path.join(path, "annotations")) is False: logging.info(" downloading annotations") os.system( "wget http://images.cocodataset.org/annotations/annotations_trainval2017.zip -P {}" .format(path)) unzip(os.path.join(path, "annotations_trainval2017.zip"), path) del_file(os.path.join(path, "annotations_trainval2017.zip")) else: logging.info(" annotations exists") if folder_exists(os.path.join(path, "val2017")) is False: logging.info(" downloading validating images") os.system( "wget http://images.cocodataset.org/zips/val2017.zip -P {}". format(path)) unzip(os.path.join(path, "val2017.zip"), path) del_file(os.path.join(path, "val2017.zip")) else: logging.info(" validating images exists") if folder_exists(os.path.join(path, "train2017")) is False: logging.info(" downloading training images") os.system( "wget http://images.cocodataset.org/zips/train2017.zip -P {}". format(path)) unzip(os.path.join(path, "train2017.zip"), path) del_file(os.path.join(path, "train2017.zip")) else: logging.info(" training images exists") if folder_exists(os.path.join(path, "test2017")) is False: logging.info(" downloading testing images") os.system( "wget http://images.cocodataset.org/zips/test2017.zip -P {}". format(path)) unzip(os.path.join(path, "test2017.zip"), path) del_file(os.path.join(path, "test2017.zip")) else: logging.info(" testing images exists") else: raise Exception( "dataset can only be 2014 and 2017, see MSCOCO website for more details." ) # logging.info(" downloading annotations") # print(url, tar_filename) # maybe_download_and_extract(tar_filename, path, url, extract=True) # del_file(os.path.join(path, tar_filename)) # # logging.info(" downloading images") # maybe_download_and_extract(tar_filename2, path, url2, extract=True) # del_file(os.path.join(path, tar_filename2)) if dataset == "2014": train_images_path = os.path.join(path, "train2014") if task == "person": train_annotations_file_path = os.path.join( path, "annotations", "person_keypoints_train2014.json") elif task == "caption": train_annotations_file_path = os.path.join( path, "annotations", "captions_train2014.json") elif task == "instance": train_annotations_file_path = os.path.join( path, "annotations", "instances_train2014.json") else: raise Exception("unknown task") val_images_path = os.path.join(path, "val2014") if task == "person": val_annotations_file_path = os.path.join( path, "annotations", "person_keypoints_val2014.json") elif task == "caption": val_annotations_file_path = os.path.join(path, "annotations", "captions_val2014.json") elif task == "instance": val_annotations_file_path = os.path.join(path, "annotations", "instances_val2014.json") test_images_path = os.path.join(path, "test2014") test_annotations_file_path = None #os.path.join(path, "annotations", "person_keypoints_test2014.json") else: train_images_path = os.path.join(path, "train2017") if task == "person": train_annotations_file_path = os.path.join( path, "annotations", "person_keypoints_train2017.json") elif task == "caption": train_annotations_file_path = os.path.join( path, "annotations", "captions_train2017.json") elif task == "instance": train_annotations_file_path = os.path.join( path, "annotations", "instances_train2017.json") else: raise Exception("unknown task") val_images_path = os.path.join(path, "val2017") if task == "person": val_annotations_file_path = os.path.join( path, "annotations", "person_keypoints_val2017.json") elif task == "caption": val_annotations_file_path = os.path.join(path, "annotations", "captions_val2017.json") elif task == "instance": val_annotations_file_path = os.path.join(path, "annotations", "instances_val2017.json") test_images_path = os.path.join(path, "test2017") test_annotations_file_path = None #os.path.join(path, "annotations", "person_keypoints_test2017.json") return train_images_path, train_annotations_file_path, \ val_images_path, val_annotations_file_path, \ test_images_path, test_annotations_file_path
def load_flickr25k_dataset(tag='sky', path="data", n_threads=50, printable=False): """Load Flickr25K dataset. Returns a list of images by a given tag from Flick25k dataset, it will download Flickr25k from `the official website <http://press.liacs.nl/mirflickr/mirdownload.html>`__ at the first time you use it. Parameters ------------ tag : str or None What images to return. - If you want to get images with tag, use string like 'dog', 'red', see `Flickr Search <https://www.flickr.com/search/>`__. - If you want to get all images, set to ``None``. path : str The path that the data is downloaded to, defaults is ``data/flickr25k/``. n_threads : int The number of thread to read image. printable : boolean Whether to print infomation when reading images, default is ``False``. Examples ----------- Get images with tag of sky >>> images = tl.files.load_flickr25k_dataset(tag='sky') Get all images >>> images = tl.files.load_flickr25k_dataset(tag=None, n_threads=100, printable=True) """ path = os.path.join(path, 'flickr25k') filename = 'mirflickr25k.zip' url = 'http://press.liacs.nl/mirflickr/mirflickr25k/' # download dataset if folder_exists(os.path.join(path, "mirflickr")) is False: logging.info("[*] Flickr25k is nonexistent in {}".format(path)) maybe_download_and_extract(filename, path, url, extract=True) del_file(os.path.join(path, filename)) # return images by the given tag. # 1. image path list folder_imgs = os.path.join(path, "mirflickr") path_imgs = load_file_list(path=folder_imgs, regx='\\.jpg', printable=False) path_imgs.sort(key=natural_keys) # 2. tag path list folder_tags = os.path.join(path, "mirflickr", "meta", "tags") path_tags = load_file_list(path=folder_tags, regx='\\.txt', printable=False) path_tags.sort(key=natural_keys) # 3. select images if tag is None: logging.info("[Flickr25k] reading all images") else: logging.info("[Flickr25k] reading images with tag: {}".format(tag)) images_list = [] for idx, _v in enumerate(path_tags): tags = read_file(os.path.join(folder_tags, path_tags[idx])).split('\n') # logging.info(idx+1, tags) if tag is None or tag in tags: images_list.append(path_imgs[idx]) images = visualize.read_images(images_list, folder_imgs, n_threads=n_threads, printable=printable) return images
def load_flickr1M_dataset(tag='sky', size=10, path="data", n_threads=50, printable=False): """Load Flick1M dataset. Returns a list of images by a given tag from Flickr1M dataset, it will download Flickr1M from `the official website <http://press.liacs.nl/mirflickr/mirdownload.html>`__ at the first time you use it. Parameters ------------ tag : str or None What images to return. - If you want to get images with tag, use string like 'dog', 'red', see `Flickr Search <https://www.flickr.com/search/>`__. - If you want to get all images, set to ``None``. size : int integer between 1 to 10. 1 means 100k images ... 5 means 500k images, 10 means all 1 million images. Default is 10. path : str The path that the data is downloaded to, defaults is ``data/flickr25k/``. n_threads : int The number of thread to read image. printable : boolean Whether to print infomation when reading images, default is ``False``. Examples ---------- Use 200k images >>> images = tl.files.load_flickr1M_dataset(tag='zebra', size=2) Use 1 Million images >>> images = tl.files.load_flickr1M_dataset(tag='zebra') """ import shutil path = os.path.join(path, 'flickr1M') logging.info("[Flickr1M] using {}% of images = {}".format(size * 10, size * 100000)) images_zip = [ 'images0.zip', 'images1.zip', 'images2.zip', 'images3.zip', 'images4.zip', 'images5.zip', 'images6.zip', 'images7.zip', 'images8.zip', 'images9.zip' ] tag_zip = 'tags.zip' url = 'http://press.liacs.nl/mirflickr/mirflickr1m/' # download dataset for image_zip in images_zip[0:size]: image_folder = image_zip.split(".")[0] # logging.info(path+"/"+image_folder) if folder_exists(os.path.join(path, image_folder)) is False: # logging.info(image_zip) logging.info("[Flickr1M] {} is missing in {}".format(image_folder, path)) maybe_download_and_extract(image_zip, path, url, extract=True) del_file(os.path.join(path, image_zip)) # os.system("mv {} {}".format(os.path.join(path, 'images'), os.path.join(path, image_folder))) shutil.move(os.path.join(path, 'images'), os.path.join(path, image_folder)) else: logging.info("[Flickr1M] {} exists in {}".format(image_folder, path)) # download tag if folder_exists(os.path.join(path, "tags")) is False: logging.info("[Flickr1M] tag files is nonexistent in {}".format(path)) maybe_download_and_extract(tag_zip, path, url, extract=True) del_file(os.path.join(path, tag_zip)) else: logging.info("[Flickr1M] tags exists in {}".format(path)) # 1. image path list images_list = [] images_folder_list = [] for i in range(0, size): images_folder_list += load_folder_list(path=os.path.join(path, 'images%d' % i)) images_folder_list.sort(key=lambda s: int(s.split('/')[-1])) # folder/images/ddd for folder in images_folder_list[0:size * 10]: tmp = load_file_list(path=folder, regx='\\.jpg', printable=False) tmp.sort(key=lambda s: int(s.split('.')[-2])) # ddd.jpg images_list.extend([os.path.join(folder, x) for x in tmp]) # 2. tag path list tag_list = [] tag_folder_list = load_folder_list(os.path.join(path, "tags")) # tag_folder_list.sort(key=lambda s: int(s.split("/")[-1])) # folder/images/ddd tag_folder_list.sort(key=lambda s: int(os.path.basename(s))) for folder in tag_folder_list[0:size * 10]: tmp = load_file_list(path=folder, regx='\\.txt', printable=False) tmp.sort(key=lambda s: int(s.split('.')[-2])) # ddd.txt tmp = [os.path.join(folder, s) for s in tmp] tag_list += tmp # 3. select images logging.info("[Flickr1M] searching tag: {}".format(tag)) select_images_list = [] for idx, _val in enumerate(tag_list): tags = read_file(tag_list[idx]).split('\n') if tag in tags: select_images_list.append(images_list[idx]) logging.info("[Flickr1M] reading images with tag: {}".format(tag)) images = visualize.read_images(select_images_list, '', n_threads=n_threads, printable=printable) return images
def load_mpii_pose_dataset(path='data', is_16_pos_only=False): """Load MPII Human Pose Dataset. Parameters ----------- path : str The path that the data is downloaded to. is_16_pos_only : boolean If True, only return the peoples contain 16 pose keypoints. (Usually be used for single person pose estimation) Returns ---------- img_train_list : list of str The image directories of training data. ann_train_list : list of dict The annotations of training data. img_test_list : list of str The image directories of testing data. ann_test_list : list of dict The annotations of testing data. Examples -------- >>> import pprint >>> import tensorlayer as tl >>> img_train_list, ann_train_list, img_test_list, ann_test_list = tl.files.load_mpii_pose_dataset() >>> image = tl.vis.read_image(img_train_list[0]) >>> tl.vis.draw_mpii_pose_to_image(image, ann_train_list[0], 'image.png') >>> pprint.pprint(ann_train_list[0]) References ----------- - `MPII Human Pose Dataset. CVPR 14 <http://human-pose.mpi-inf.mpg.de>`__ - `MPII Human Pose Models. CVPR 16 <http://pose.mpi-inf.mpg.de>`__ - `MPII Human Shape, Poselet Conditioned Pictorial Structures and etc <http://pose.mpi-inf.mpg.de/#related>`__ - `MPII Keyponts and ID <http://human-pose.mpi-inf.mpg.de/#download>`__ """ path = os.path.join(path, 'mpii_human_pose') logging.info("Load or Download MPII Human Pose > {}".format(path)) # annotation url = "http://datasets.d2.mpi-inf.mpg.de/andriluka14cvpr/" tar_filename = "mpii_human_pose_v1_u12_2.zip" extracted_filename = "mpii_human_pose_v1_u12_2" if folder_exists(os.path.join(path, extracted_filename)) is False: logging.info("[MPII] (annotation) {} is nonexistent in {}".format( extracted_filename, path)) maybe_download_and_extract(tar_filename, path, url, extract=True) del_file(os.path.join(path, tar_filename)) # images url = "http://datasets.d2.mpi-inf.mpg.de/andriluka14cvpr/" tar_filename = "mpii_human_pose_v1.tar.gz" extracted_filename2 = "images" if folder_exists(os.path.join(path, extracted_filename2)) is False: logging.info("[MPII] (images) {} is nonexistent in {}".format( extracted_filename, path)) maybe_download_and_extract(tar_filename, path, url, extract=True) del_file(os.path.join(path, tar_filename)) # parse annotation, format see http://human-pose.mpi-inf.mpg.de/#download import scipy.io as sio logging.info("reading annotations from mat file ...") # mat = sio.loadmat(os.path.join(path, extracted_filename, "mpii_human_pose_v1_u12_1.mat")) # def fix_wrong_joints(joint): # https://github.com/mitmul/deeppose/blob/master/datasets/mpii_dataset.py # if '12' in joint and '13' in joint and '2' in joint and '3' in joint: # if ((joint['12'][0] < joint['13'][0]) and # (joint['3'][0] < joint['2'][0])): # joint['2'], joint['3'] = joint['3'], joint['2'] # if ((joint['12'][0] > joint['13'][0]) and # (joint['3'][0] > joint['2'][0])): # joint['2'], joint['3'] = joint['3'], joint['2'] # return joint ann_train_list = [] ann_test_list = [] img_train_list = [] img_test_list = [] def save_joints(): # joint_data_fn = os.path.join(path, 'data.json') # fp = open(joint_data_fn, 'w') mat = sio.loadmat( os.path.join(path, extracted_filename, "mpii_human_pose_v1_u12_1.mat")) for _, (anno, train_flag) in enumerate( # all images zip(mat['RELEASE']['annolist'][0, 0][0], mat['RELEASE']['img_train'][0, 0][0])): img_fn = anno['image']['name'][0, 0][0] train_flag = int(train_flag) # print(i, img_fn, train_flag) # DEBUG print all images if train_flag: img_train_list.append(img_fn) ann_train_list.append([]) else: img_test_list.append(img_fn) ann_test_list.append([]) head_rect = [] if 'x1' in str(anno['annorect'].dtype): head_rect = zip([x1[0, 0] for x1 in anno['annorect']['x1'][0]], [y1[0, 0] for y1 in anno['annorect']['y1'][0]], [x2[0, 0] for x2 in anno['annorect']['x2'][0]], [y2[0, 0] for y2 in anno['annorect']['y2'][0]]) else: head_rect = [] # TODO if 'annopoints' in str(anno['annorect'].dtype): annopoints = anno['annorect']['annopoints'][0] head_x1s = anno['annorect']['x1'][0] head_y1s = anno['annorect']['y1'][0] head_x2s = anno['annorect']['x2'][0] head_y2s = anno['annorect']['y2'][0] for annopoint, head_x1, head_y1, head_x2, head_y2 in zip( annopoints, head_x1s, head_y1s, head_x2s, head_y2s): # if annopoint != []: # if len(annopoint) != 0: if annopoint.size: head_rect = [ float(head_x1[0, 0]), float(head_y1[0, 0]), float(head_x2[0, 0]), float(head_y2[0, 0]) ] # joint coordinates annopoint = annopoint['point'][0, 0] j_id = [str(j_i[0, 0]) for j_i in annopoint['id'][0]] x = [x[0, 0] for x in annopoint['x'][0]] y = [y[0, 0] for y in annopoint['y'][0]] joint_pos = {} for _j_id, (_x, _y) in zip(j_id, zip(x, y)): joint_pos[int(_j_id)] = [float(_x), float(_y)] # joint_pos = fix_wrong_joints(joint_pos) # visibility list if 'is_visible' in str(annopoint.dtype): vis = [ v[0] if v.size > 0 else [0] for v in annopoint['is_visible'][0] ] vis = dict([(k, int(v[0])) if len(v) > 0 else v for k, v in zip(j_id, vis)]) else: vis = None # if len(joint_pos) == 16: if ((is_16_pos_only == True) and (len(joint_pos) == 16)) or (is_16_pos_only == False): # only use image with 16 key points / or use all data = { 'filename': img_fn, 'train': train_flag, 'head_rect': head_rect, 'is_visible': vis, 'joint_pos': joint_pos } # print(json.dumps(data), file=fp) # py3 if train_flag: ann_train_list[-1].append(data) else: ann_test_list[-1].append(data) # def write_line(datum, fp): # joints = sorted([[int(k), v] for k, v in datum['joint_pos'].items()]) # joints = np.array([j for i, j in joints]).flatten() # # out = [datum['filename']] # out.extend(joints) # out = [str(o) for o in out] # out = ','.join(out) # # print(out, file=fp) # def split_train_test(): # # fp_test = open('data/mpii/test_joints.csv', 'w') # fp_test = open(os.path.join(path, 'test_joints.csv'), 'w') # # fp_train = open('data/mpii/train_joints.csv', 'w') # fp_train = open(os.path.join(path, 'train_joints.csv'), 'w') # # all_data = open('data/mpii/data.json').readlines() # all_data = open(os.path.join(path, 'data.json')).readlines() # N = len(all_data) # N_test = int(N * 0.1) # N_train = N - N_test # # print('N:{}'.format(N)) # print('N_train:{}'.format(N_train)) # print('N_test:{}'.format(N_test)) # # np.random.seed(1701) # perm = np.random.permutation(N) # test_indices = perm[:N_test] # train_indices = perm[N_test:] # # print('train_indices:{}'.format(len(train_indices))) # print('test_indices:{}'.format(len(test_indices))) # # for i in train_indices: # datum = json.loads(all_data[i].strip()) # write_line(datum, fp_train) # # for i in test_indices: # datum = json.loads(all_data[i].strip()) # write_line(datum, fp_test) save_joints() # split_train_test() # ## read images dir logging.info("reading images list ...") img_dir = os.path.join(path, extracted_filename2) _img_list = load_file_list(path=os.path.join(path, extracted_filename2), regx='\\.jpg', printable=False) # ann_list = json.load(open(os.path.join(path, 'data.json'))) for i, im in enumerate(img_train_list): if im not in _img_list: print( 'missing training image {} in {} (remove from img(ann)_train_list)' .format(im, img_dir)) # img_train_list.remove(im) del img_train_list[i] del ann_train_list[i] for i, im in enumerate(img_test_list): if im not in _img_list: print( 'missing testing image {} in {} (remove from img(ann)_test_list)' .format(im, img_dir)) # img_test_list.remove(im) del img_train_list[i] del ann_train_list[i] ## check annotation and images n_train_images = len(img_train_list) n_test_images = len(img_test_list) n_images = n_train_images + n_test_images logging.info("n_images: {} n_train_images: {} n_test_images: {}".format( n_images, n_train_images, n_test_images)) n_train_ann = len(ann_train_list) n_test_ann = len(ann_test_list) n_ann = n_train_ann + n_test_ann logging.info("n_ann: {} n_train_ann: {} n_test_ann: {}".format( n_ann, n_train_ann, n_test_ann)) n_train_people = len(sum(ann_train_list, [])) n_test_people = len(sum(ann_test_list, [])) n_people = n_train_people + n_test_people logging.info("n_people: {} n_train_people: {} n_test_people: {}".format( n_people, n_train_people, n_test_people)) # add path to all image file name for i, value in enumerate(img_train_list): img_train_list[i] = os.path.join(img_dir, value) for i, value in enumerate(img_test_list): img_test_list[i] = os.path.join(img_dir, value) return img_train_list, ann_train_list, img_test_list, ann_test_list
def load_mpii_pose_dataset(path='data', is_16_pos_only=False): """Load MPII Human Pose Dataset. Parameters ----------- path : str The path that the data is downloaded to. is_16_pos_only : boolean If True, only return the peoples contain 16 pose keypoints. (Usually be used for single person pose estimation) Returns ---------- img_train_list : list of str The image directories of training data. ann_train_list : list of dict The annotations of training data. img_test_list : list of str The image directories of testing data. ann_test_list : list of dict The annotations of testing data. Examples -------- >>> import pprint >>> import tensorlayer as tl >>> img_train_list, ann_train_list, img_test_list, ann_test_list = tl.files.load_mpii_pose_dataset() >>> image = tl.vis.read_image(img_train_list[0]) >>> tl.vis.draw_mpii_pose_to_image(image, ann_train_list[0], 'image.png') >>> pprint.pprint(ann_train_list[0]) References ----------- - `MPII Human Pose Dataset. CVPR 14 <http://human-pose.mpi-inf.mpg.de>`__ - `MPII Human Pose Models. CVPR 16 <http://pose.mpi-inf.mpg.de>`__ - `MPII Human Shape, Poselet Conditioned Pictorial Structures and etc <http://pose.mpi-inf.mpg.de/#related>`__ - `MPII Keyponts and ID <http://human-pose.mpi-inf.mpg.de/#download>`__ """ path = os.path.join(path, 'mpii_human_pose') logging.info("Load or Download MPII Human Pose > {}".format(path)) # annotation url = "http://datasets.d2.mpi-inf.mpg.de/andriluka14cvpr/" tar_filename = "mpii_human_pose_v1_u12_2.zip" extracted_filename = "mpii_human_pose_v1_u12_2" if folder_exists(os.path.join(path, extracted_filename)) is False: logging.info("[MPII] (annotation) {} is nonexistent in {}".format(extracted_filename, path)) maybe_download_and_extract(tar_filename, path, url, extract=True) del_file(os.path.join(path, tar_filename)) # images url = "http://datasets.d2.mpi-inf.mpg.de/andriluka14cvpr/" tar_filename = "mpii_human_pose_v1.tar.gz" extracted_filename2 = "images" if folder_exists(os.path.join(path, extracted_filename2)) is False: logging.info("[MPII] (images) {} is nonexistent in {}".format(extracted_filename, path)) maybe_download_and_extract(tar_filename, path, url, extract=True) del_file(os.path.join(path, tar_filename)) # parse annotation, format see http://human-pose.mpi-inf.mpg.de/#download import scipy.io as sio logging.info("reading annotations from mat file ...") # mat = sio.loadmat(os.path.join(path, extracted_filename, "mpii_human_pose_v1_u12_1.mat")) # def fix_wrong_joints(joint): # https://github.com/mitmul/deeppose/blob/master/datasets/mpii_dataset.py # if '12' in joint and '13' in joint and '2' in joint and '3' in joint: # if ((joint['12'][0] < joint['13'][0]) and # (joint['3'][0] < joint['2'][0])): # joint['2'], joint['3'] = joint['3'], joint['2'] # if ((joint['12'][0] > joint['13'][0]) and # (joint['3'][0] > joint['2'][0])): # joint['2'], joint['3'] = joint['3'], joint['2'] # return joint ann_train_list = [] ann_test_list = [] img_train_list = [] img_test_list = [] def save_joints(): # joint_data_fn = os.path.join(path, 'data.json') # fp = open(joint_data_fn, 'w') mat = sio.loadmat(os.path.join(path, extracted_filename, "mpii_human_pose_v1_u12_1.mat")) for _, (anno, train_flag) in enumerate( # all images zip(mat['RELEASE']['annolist'][0, 0][0], mat['RELEASE']['img_train'][0, 0][0])): img_fn = anno['image']['name'][0, 0][0] train_flag = int(train_flag) # print(i, img_fn, train_flag) # DEBUG print all images if train_flag: img_train_list.append(img_fn) ann_train_list.append([]) else: img_test_list.append(img_fn) ann_test_list.append([]) head_rect = [] if 'x1' in str(anno['annorect'].dtype): head_rect = zip( [x1[0, 0] for x1 in anno['annorect']['x1'][0]], [y1[0, 0] for y1 in anno['annorect']['y1'][0]], [x2[0, 0] for x2 in anno['annorect']['x2'][0]], [y2[0, 0] for y2 in anno['annorect']['y2'][0]] ) else: head_rect = [] # TODO if 'annopoints' in str(anno['annorect'].dtype): annopoints = anno['annorect']['annopoints'][0] head_x1s = anno['annorect']['x1'][0] head_y1s = anno['annorect']['y1'][0] head_x2s = anno['annorect']['x2'][0] head_y2s = anno['annorect']['y2'][0] for annopoint, head_x1, head_y1, head_x2, head_y2 in zip(annopoints, head_x1s, head_y1s, head_x2s, head_y2s): # if annopoint != []: # if len(annopoint) != 0: if annopoint.size: head_rect = [ float(head_x1[0, 0]), float(head_y1[0, 0]), float(head_x2[0, 0]), float(head_y2[0, 0]) ] # joint coordinates annopoint = annopoint['point'][0, 0] j_id = [str(j_i[0, 0]) for j_i in annopoint['id'][0]] x = [x[0, 0] for x in annopoint['x'][0]] y = [y[0, 0] for y in annopoint['y'][0]] joint_pos = {} for _j_id, (_x, _y) in zip(j_id, zip(x, y)): joint_pos[int(_j_id)] = [float(_x), float(_y)] # joint_pos = fix_wrong_joints(joint_pos) # visibility list if 'is_visible' in str(annopoint.dtype): vis = [v[0] if v.size > 0 else [0] for v in annopoint['is_visible'][0]] vis = dict([(k, int(v[0])) if len(v) > 0 else v for k, v in zip(j_id, vis)]) else: vis = None # if len(joint_pos) == 16: if ((is_16_pos_only ==True) and (len(joint_pos) == 16)) or (is_16_pos_only == False): # only use image with 16 key points / or use all data = { 'filename': img_fn, 'train': train_flag, 'head_rect': head_rect, 'is_visible': vis, 'joint_pos': joint_pos } # print(json.dumps(data), file=fp) # py3 if train_flag: ann_train_list[-1].append(data) else: ann_test_list[-1].append(data) # def write_line(datum, fp): # joints = sorted([[int(k), v] for k, v in datum['joint_pos'].items()]) # joints = np.array([j for i, j in joints]).flatten() # # out = [datum['filename']] # out.extend(joints) # out = [str(o) for o in out] # out = ','.join(out) # # print(out, file=fp) # def split_train_test(): # # fp_test = open('data/mpii/test_joints.csv', 'w') # fp_test = open(os.path.join(path, 'test_joints.csv'), 'w') # # fp_train = open('data/mpii/train_joints.csv', 'w') # fp_train = open(os.path.join(path, 'train_joints.csv'), 'w') # # all_data = open('data/mpii/data.json').readlines() # all_data = open(os.path.join(path, 'data.json')).readlines() # N = len(all_data) # N_test = int(N * 0.1) # N_train = N - N_test # # print('N:{}'.format(N)) # print('N_train:{}'.format(N_train)) # print('N_test:{}'.format(N_test)) # # np.random.seed(1701) # perm = np.random.permutation(N) # test_indices = perm[:N_test] # train_indices = perm[N_test:] # # print('train_indices:{}'.format(len(train_indices))) # print('test_indices:{}'.format(len(test_indices))) # # for i in train_indices: # datum = json.loads(all_data[i].strip()) # write_line(datum, fp_train) # # for i in test_indices: # datum = json.loads(all_data[i].strip()) # write_line(datum, fp_test) save_joints() # split_train_test() # ## read images dir logging.info("reading images list ...") img_dir = os.path.join(path, extracted_filename2) _img_list = load_file_list(path=os.path.join(path, extracted_filename2), regx='\\.jpg', printable=False) # ann_list = json.load(open(os.path.join(path, 'data.json'))) for i, im in enumerate(img_train_list): if im not in _img_list: print('missing training image {} in {} (remove from img(ann)_train_list)'.format(im, img_dir)) # img_train_list.remove(im) del img_train_list[i] del ann_train_list[i] for i, im in enumerate(img_test_list): if im not in _img_list: print('missing testing image {} in {} (remove from img(ann)_test_list)'.format(im, img_dir)) # img_test_list.remove(im) del img_train_list[i] del ann_train_list[i] ## check annotation and images n_train_images = len(img_train_list) n_test_images = len(img_test_list) n_images = n_train_images + n_test_images logging.info("n_images: {} n_train_images: {} n_test_images: {}".format(n_images, n_train_images, n_test_images)) n_train_ann = len(ann_train_list) n_test_ann = len(ann_test_list) n_ann = n_train_ann + n_test_ann logging.info("n_ann: {} n_train_ann: {} n_test_ann: {}".format(n_ann, n_train_ann, n_test_ann)) n_train_people = len(sum(ann_train_list, [])) n_test_people = len(sum(ann_test_list, [])) n_people = n_train_people + n_test_people logging.info("n_people: {} n_train_people: {} n_test_people: {}".format(n_people, n_train_people, n_test_people)) # add path to all image file name for i, value in enumerate(img_train_list): img_train_list[i] = os.path.join(img_dir, value) for i, value in enumerate(img_test_list): img_test_list[i] = os.path.join(img_dir, value) return img_train_list, ann_train_list, img_test_list, ann_test_list
def load_voc_dataset(path='data', dataset='2012', contain_classes_in_person=False): """Pascal VOC 2007/2012 Dataset. It has 20 objects: aeroplane, bicycle, bird, boat, bottle, bus, car, cat, chair, cow, diningtable, dog, horse, motorbike, person, pottedplant, sheep, sofa, train, tvmonitor and additional 3 classes : head, hand, foot for person. Parameters ----------- path : str The path that the data is downloaded to, defaults is ``data/VOC``. dataset : str The VOC dataset version, `2012`, `2007`, `2007test` or `2012test`. We usually train model on `2007+2012` and test it on `2007test`. contain_classes_in_person : boolean Whether include head, hand and foot annotation, default is False. Returns --------- imgs_file_list : list of str Full paths of all images. imgs_semseg_file_list : list of str Full paths of all maps for semantic segmentation. Note that not all images have this map! imgs_insseg_file_list : list of str Full paths of all maps for instance segmentation. Note that not all images have this map! imgs_ann_file_list : list of str Full paths of all annotations for bounding box and object class, all images have this annotations. classes : list of str Classes in order. classes_in_person : list of str Classes in person. classes_dict : dictionary Class label to integer. n_objs_list : list of int Number of objects in all images in ``imgs_file_list`` in order. objs_info_list : list of str Darknet format for the annotation of all images in ``imgs_file_list`` in order. ``[class_id x_centre y_centre width height]`` in ratio format. objs_info_dicts : dictionary The annotation of all images in ``imgs_file_list``, ``{imgs_file_list : dictionary for annotation}``, format from `TensorFlow/Models/object-detection <https://github.com/tensorflow/models/blob/master/object_detection/create_pascal_tf_record.py>`__. Examples ---------- >>> imgs_file_list, imgs_semseg_file_list, imgs_insseg_file_list, imgs_ann_file_list, >>> classes, classes_in_person, classes_dict, >>> n_objs_list, objs_info_list, objs_info_dicts = tl.files.load_voc_dataset(dataset="2012", contain_classes_in_person=False) >>> idx = 26 >>> print(classes) ['aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog', 'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor'] >>> print(classes_dict) {'sheep': 16, 'horse': 12, 'bicycle': 1, 'bottle': 4, 'cow': 9, 'sofa': 17, 'car': 6, 'dog': 11, 'cat': 7, 'person': 14, 'train': 18, 'diningtable': 10, 'aeroplane': 0, 'bus': 5, 'pottedplant': 15, 'tvmonitor': 19, 'chair': 8, 'bird': 2, 'boat': 3, 'motorbike': 13} >>> print(imgs_file_list[idx]) data/VOC/VOC2012/JPEGImages/2007_000423.jpg >>> print(n_objs_list[idx]) 2 >>> print(imgs_ann_file_list[idx]) data/VOC/VOC2012/Annotations/2007_000423.xml >>> print(objs_info_list[idx]) 14 0.173 0.461333333333 0.142 0.496 14 0.828 0.542666666667 0.188 0.594666666667 >>> ann = tl.prepro.parse_darknet_ann_str_to_list(objs_info_list[idx]) >>> print(ann) [[14, 0.173, 0.461333333333, 0.142, 0.496], [14, 0.828, 0.542666666667, 0.188, 0.594666666667]] >>> c, b = tl.prepro.parse_darknet_ann_list_to_cls_box(ann) >>> print(c, b) [14, 14] [[0.173, 0.461333333333, 0.142, 0.496], [0.828, 0.542666666667, 0.188, 0.594666666667]] References ------------- - `Pascal VOC2012 Website <https://pjreddie.com/projects/pascal-voc-dataset-mirror/>`__. - `Pascal VOC2007 Website <https://pjreddie.com/projects/pascal-voc-dataset-mirror/>`__. """ try: import lxml.etree as etree except ImportError as e: print(e) raise ImportError("Module lxml not found. Please install lxml via pip or other package managers.") path = os.path.join(path, 'VOC') def _recursive_parse_xml_to_dict(xml): """Recursively parses XML contents to python dict. We assume that `object` tags are the only ones that can appear multiple times at the same level of a tree. Args: xml: xml tree obtained by parsing XML file contents using lxml.etree Returns: Python dictionary holding XML contents. """ if xml is not None: return {xml.tag: xml.text} result = {} for child in xml: child_result = _recursive_parse_xml_to_dict(child) if child.tag != 'object': result[child.tag] = child_result[child.tag] else: if child.tag not in result: result[child.tag] = [] result[child.tag].append(child_result[child.tag]) return {xml.tag: result} import xml.etree.ElementTree as ET if dataset == "2012": url = "http://pjreddie.com/media/files/" tar_filename = "VOCtrainval_11-May-2012.tar" extracted_filename = "VOC2012" #"VOCdevkit/VOC2012" logging.info(" [============= VOC 2012 =============]") elif dataset == "2012test": extracted_filename = "VOC2012test" #"VOCdevkit/VOC2012" logging.info(" [============= VOC 2012 Test Set =============]") logging.info( " \nAuthor: 2012test only have person annotation, so 2007test is highly recommended for testing !\n" ) import time time.sleep(3) if os.path.isdir(os.path.join(path, extracted_filename)) is False: logging.info("For VOC 2012 Test data - online registration required") logging.info( " Please download VOC2012test.tar from: \n register: http://host.robots.ox.ac.uk:8080 \n voc2012 : http://host.robots.ox.ac.uk:8080/eval/challenges/voc2012/ \ndownload: http://host.robots.ox.ac.uk:8080/eval/downloads/VOC2012test.tar" ) logging.info(" unzip VOC2012test.tar,rename the folder to VOC2012test and put it into %s" % path) exit() # # http://host.robots.ox.ac.uk:8080/eval/downloads/VOC2012test.tar # url = "http://host.robots.ox.ac.uk:8080/eval/downloads/" # tar_filename = "VOC2012test.tar" elif dataset == "2007": url = "http://pjreddie.com/media/files/" tar_filename = "VOCtrainval_06-Nov-2007.tar" extracted_filename = "VOC2007" logging.info(" [============= VOC 2007 =============]") elif dataset == "2007test": # http://host.robots.ox.ac.uk/pascal/VOC/voc2007/index.html#testdata # http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar url = "http://pjreddie.com/media/files/" tar_filename = "VOCtest_06-Nov-2007.tar" extracted_filename = "VOC2007test" logging.info(" [============= VOC 2007 Test Set =============]") else: raise Exception("Please set the dataset aug to 2012, 2012test or 2007.") # download dataset if dataset != "2012test": from sys import platform as _platform if folder_exists(os.path.join(path, extracted_filename)) is False: logging.info("[VOC] {} is nonexistent in {}".format(extracted_filename, path)) maybe_download_and_extract(tar_filename, path, url, extract=True) del_file(os.path.join(path, tar_filename)) if dataset == "2012": if _platform == "win32": os.system("move {}\VOCdevkit\VOC2012 {}\VOC2012".format(path, path)) else: os.system("mv {}/VOCdevkit/VOC2012 {}/VOC2012".format(path, path)) elif dataset == "2007": if _platform == "win32": os.system("move {}\VOCdevkit\VOC2007 {}\VOC2007".format(path, path)) else: os.system("mv {}/VOCdevkit/VOC2007 {}/VOC2007".format(path, path)) elif dataset == "2007test": if _platform == "win32": os.system("move {}\VOCdevkit\VOC2007 {}\VOC2007test".format(path, path)) else: os.system("mv {}/VOCdevkit/VOC2007 {}/VOC2007test".format(path, path)) del_folder(os.path.join(path, 'VOCdevkit')) # object classes(labels) NOTE: YOU CAN CUSTOMIZE THIS LIST classes = [ "aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor" ] if contain_classes_in_person: classes_in_person = ["head", "hand", "foot"] else: classes_in_person = [] classes += classes_in_person # use extra 3 classes for person classes_dict = utils.list_string_to_dict(classes) logging.info("[VOC] object classes {}".format(classes_dict)) # 1. image path list # folder_imgs = path+"/"+extracted_filename+"/JPEGImages/" folder_imgs = os.path.join(path, extracted_filename, "JPEGImages") imgs_file_list = load_file_list(path=folder_imgs, regx='\\.jpg', printable=False) logging.info("[VOC] {} images found".format(len(imgs_file_list))) imgs_file_list.sort( key=lambda s: int(s.replace('.', ' ').replace('_', '').split(' ')[-2]) ) # 2007_000027.jpg --> 2007000027 imgs_file_list = [os.path.join(folder_imgs, s) for s in imgs_file_list] # logging.info('IM',imgs_file_list[0::3333], imgs_file_list[-1]) if dataset != "2012test": ##======== 2. semantic segmentation maps path list # folder_semseg = path+"/"+extracted_filename+"/SegmentationClass/" folder_semseg = os.path.join(path, extracted_filename, "SegmentationClass") imgs_semseg_file_list = load_file_list(path=folder_semseg, regx='\\.png', printable=False) logging.info("[VOC] {} maps for semantic segmentation found".format(len(imgs_semseg_file_list))) imgs_semseg_file_list.sort( key=lambda s: int(s.replace('.', ' ').replace('_', '').split(' ')[-2]) ) # 2007_000032.png --> 2007000032 imgs_semseg_file_list = [os.path.join(folder_semseg, s) for s in imgs_semseg_file_list] # logging.info('Semantic Seg IM',imgs_semseg_file_list[0::333], imgs_semseg_file_list[-1]) ##======== 3. instance segmentation maps path list # folder_insseg = path+"/"+extracted_filename+"/SegmentationObject/" folder_insseg = os.path.join(path, extracted_filename, "SegmentationObject") imgs_insseg_file_list = load_file_list(path=folder_insseg, regx='\\.png', printable=False) logging.info("[VOC] {} maps for instance segmentation found".format(len(imgs_semseg_file_list))) imgs_insseg_file_list.sort( key=lambda s: int(s.replace('.', ' ').replace('_', '').split(' ')[-2]) ) # 2007_000032.png --> 2007000032 imgs_insseg_file_list = [os.path.join(folder_insseg, s) for s in imgs_insseg_file_list] # logging.info('Instance Seg IM',imgs_insseg_file_list[0::333], imgs_insseg_file_list[-1]) else: imgs_semseg_file_list = [] imgs_insseg_file_list = [] # 4. annotations for bounding box and object class # folder_ann = path+"/"+extracted_filename+"/Annotations/" folder_ann = os.path.join(path, extracted_filename, "Annotations") imgs_ann_file_list = load_file_list(path=folder_ann, regx='\\.xml', printable=False) logging.info( "[VOC] {} XML annotation files for bounding box and object class found".format(len(imgs_ann_file_list)) ) imgs_ann_file_list.sort( key=lambda s: int(s.replace('.', ' ').replace('_', '').split(' ')[-2]) ) # 2007_000027.xml --> 2007000027 imgs_ann_file_list = [os.path.join(folder_ann, s) for s in imgs_ann_file_list] # logging.info('ANN',imgs_ann_file_list[0::3333], imgs_ann_file_list[-1]) if dataset == "2012test": # remove unused images in JPEG folder imgs_file_list_new = [] for ann in imgs_ann_file_list: ann = os.path.split(ann)[-1].split('.')[0] for im in imgs_file_list: if ann in im: imgs_file_list_new.append(im) break imgs_file_list = imgs_file_list_new logging.info("[VOC] keep %d images" % len(imgs_file_list_new)) # parse XML annotations def convert(size, box): dw = 1. / size[0] dh = 1. / size[1] x = (box[0] + box[1]) / 2.0 y = (box[2] + box[3]) / 2.0 w = box[1] - box[0] h = box[3] - box[2] x = x * dw w = w * dw y = y * dh h = h * dh return x, y, w, h def convert_annotation(file_name): """Given VOC2012 XML Annotations, returns number of objects and info.""" in_file = open(file_name) out_file = "" tree = ET.parse(in_file) root = tree.getroot() size = root.find('size') w = int(size.find('width').text) h = int(size.find('height').text) n_objs = 0 for obj in root.iter('object'): if dataset != "2012test": difficult = obj.find('difficult').text cls = obj.find('name').text if cls not in classes or int(difficult) == 1: continue else: cls = obj.find('name').text if cls not in classes: continue cls_id = classes.index(cls) xmlbox = obj.find('bndbox') b = ( float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text) ) bb = convert((w, h), b) out_file += str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n' n_objs += 1 if cls in "person": for part in obj.iter('part'): cls = part.find('name').text if cls not in classes_in_person: continue cls_id = classes.index(cls) xmlbox = part.find('bndbox') b = ( float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text) ) bb = convert((w, h), b) # out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n') out_file += str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n' n_objs += 1 in_file.close() return n_objs, out_file logging.info("[VOC] Parsing xml annotations files") n_objs_list = [] objs_info_list = [] # Darknet Format list of string objs_info_dicts = {} for idx, ann_file in enumerate(imgs_ann_file_list): n_objs, objs_info = convert_annotation(ann_file) n_objs_list.append(n_objs) objs_info_list.append(objs_info) with tf.io.gfile.GFile(ann_file, 'r') as fid: xml_str = fid.read() xml = etree.fromstring(xml_str) data = _recursive_parse_xml_to_dict(xml)['annotation'] objs_info_dicts.update({imgs_file_list[idx]: data}) return imgs_file_list, imgs_semseg_file_list, imgs_insseg_file_list, imgs_ann_file_list, classes, classes_in_person, classes_dict, n_objs_list, objs_info_list, objs_info_dicts