# check if weight path was passed via command line
if options.input_weight_path:
C.base_net_weights = options.input_weight_path
else:
# set the path to weights based on backend and model
C.base_net_weights = nn.get_weight_path()
# place weight files on your directory
ase_net_weights = nn.get_weight_path()
#### load images here ####
# get voc images
all_imgs, classes_count, class_mapping = get_data(options.train_path)
print(classes_count)
# add background class as 21st class
if 'bg' not in classes_count:
classes_count['bg'] = 0
class_mapping['bg'] = len(class_mapping)
C.class_mapping = class_mapping
inv_map = {v: k for k, v in class_mapping.items()}
print('Training images per class:')
pprint.pprint(classes_count)
print('Num classes (including bg) = {}'.format(len(classes_count)))
elif options.network == 'resnet50':
from keras_frcnn import resnet as nn
C.network = 'resnet50'
else:
print('Not a valid model')
raise ValueError
# check if weight path was passed via command line
if options.input_weight_path:
C.base_net_weights = options.input_weight_path
else:
# set the path to weights based on backend and model
C.base_net_weights = nn.get_weight_path()
all_imgs, classes_count, class_mapping = get_data(options.train_path)
if 'bg' not in classes_count:
classes_count['bg'] = 0
class_mapping['bg'] = len(class_mapping)
C.class_mapping = class_mapping
inv_map = {v: k for k, v in class_mapping.items()}
print('Training images per class:')
pprint.pprint(classes_count)
print('Num classes (including bg) = {}'.format(len(classes_count)))
config_output_filename = options.config_filename
C.num_rois,
nb_classes=len(class_mapping),
trainable=True)
model_rpn = Model(img_input, rpn_layers)
model_classifier_only = Model([feature_map_input, roi_input], classifier)
model_classifier = Model([feature_map_input, roi_input], classifier)
model_rpn.load_weights(C.model_path, by_name=True)
model_classifier.load_weights(C.model_path, by_name=True)
model_rpn.compile(optimizer='sgd', loss='mse')
model_classifier.compile(optimizer='sgd', loss='mse')
test_imgs, _, _ = get_data(options.test_path)
#test_imgs = [s for s in all_imgs if s['imageset'] == 'test']
begin = time.time()
cls_list = [
' seagram', ' pebriz', ' boxtape', ' cass', ' detergent', ' kantata',
' kechap', ' myzzo', ' papercup', ' parisredbean', ' pringles', ' sausage',
' seoulmilk', ' shrimpsnack', ' sunuporange', ' tunacan', ' vita500',
' vitajelly'
]
T = {cls: [] for cls in cls_list}
P = {cls: [] for cls in cls_list}
iou_result = 0
progbar = generic_utils.Progbar(len(test_imgs))
for idx, img_data in enumerate(test_imgs):
#print('{}/{}'.format(idx + 1,len(test_imgs)))
#if idx %(40*3) not in [0, 1, 2]: continue
test_cls = [
'aeroplane', 'bicycle', 'boat', 'bus', 'car', 'chair', 'diningtable',
'motorbike', 'sofa', 'train', 'tvmonitor'
]
# turn off any data augmentation at test time
C.use_horizontal_flips = False
C.use_vertical_flips = False
C.rot_90 = False
if os.path.exists('pickle_data/mAVP_test_file.pickle'):
with open('pickle_data/mAVP_test_file.pickle') as f:
all_imgs, _, _ = pickle.load(f)
else:
all_imgs, _, _ = get_data(test_path)
test_imgs = [s for s in all_imgs if s['imageset'] == 'trainval']
test_imgs.sort(key=lambda k: k['filepath'])
def format_img(img, C):
img_min_side = float(C.im_size)
(height, width, _) = img.shape
if width <= height:
f = img_min_side / width
new_height = int(f * height)
new_width = int(img_min_side)
else:
f = img_min_side / height
new_width = int(f * width)
C.use_horizontal_flips = False
C.use_vertical_flips = False
C.rot_90 = False
C.model_path = "dataset/model.hdf5"
C.num_rois = 10
C.network = 'resnet50'
C.base_net_weights = "model/resnet50_weights_tf_dim_ordering_tf_kernels.h5"
# else set the path to weights based on backend and model
# C.base_net_weights = nn.get_weight_path()
config_output_filename = "dataset/config.pickle"
epoch_length = 400
num_epochs = 30
ab_path = os.path.dirname(os.path.abspath(__file__))
all_imgs, classes_count, class_mapping = get_data(ab_path + "/dataset")
if 'bg' not in classes_count:
classes_count['bg'] = 0
class_mapping['bg'] = len(class_mapping)
C.class_mapping = class_mapping
#inv_map {0: 'RBC', 1: 'bg'}
#class_mapping{'RBC': 0, 'bg': 1}
inv_map = {v: k for k, v in class_mapping.items()}
print('Training images per class:')
pprint.pprint(classes_count)
print('Num classes (including bg) = {}'.format(len(classes_count)))
with open(config_output_filename, 'wb') as config_f:
pickle.dump(C, config_f)
from keras_frcnn import vgg as nn
print('use vgg')
elif cfg.network == 'resnet50':
from keras_frcnn import resnet as nn
print('use resnet50')
else:
print('Not a valid model')
raise ValueError
if cfg.input_weight_path: # 这里已经被赋值为cfg里的值
cfg.base_net_weights = cfg.input_weight_path
else:
print('does not init')
#raise ValueError
all_imgs, classes_count, bird_class_count = get_data(cfg.train_path,part_class_mapping)
data_lei = march.get_voc_label(all_imgs, classes_count, part_class_mapping, bird_class_count, bird_class_mapping,config= cfg,trainable=True)
#pprint.pprint(classes_count)
#pprint.pprint(part_class_mapping)
# 这里的类在match里边定义
if 'bg' not in classes_count:
classes_count['bg'] = 0
part_class_mapping['bg'] = len(part_class_mapping)
cfg.class_mapping = part_class_mapping
print('Training images per class:')
pprint.pprint(classes_count)
pprint.pprint(part_class_mapping)
print('Num classes (including bg) = {}'.format(len(classes_count)))
if C.parser == 'pascal_voc':
from keras_frcnn.pascal_voc_parser import get_data
elif C.parser == 'simple':
from keras_frcnn.simple_parser import get_data
else:
raise ValueError("Command line option parser must be one of 'pascal_voc' or 'simple'")
splits = None
# if the splits already exist, we will load them in
# delete this file if you are a different amount of pictures now
if os.path.exists(C.output_folder+"splits.pickle"):
with open(C.output_folder+"splits.pickle", 'rb') as splits_f:
splits = pickle.load(splits_f)
all_imgs_dict, classes_count, class_mapping = get_data(
C.train_path, image_folder=IMAGE_FOLDER, train_test_split=splits)
all_imgs = []
for key in all_imgs_dict:
all_imgs.append(all_imgs_dict[key])
if 'bg' not in classes_count:
classes_count['bg'] = 0
class_mapping['bg'] = len(class_mapping)
C.class_mapping = class_mapping
C.classes_count = classes_count
# inv_map = {v: k for k, v in class_mapping.items()}
print('Training images per class:')
pprint.pprint(classes_count)
print('Num classes (including bg) = {}'.format(len(classes_count)))
elif options.network == 'resnet50':
from keras_frcnn import resnet_rgbt as nn
C.network = 'resnet50'
else:
print('Not a valid model')
raise ValueError
# check if weight path was passed via command line
if options.input_weight_path:
C.base_net_weights = options.input_weight_path
else:
# set the path to weights based on backend and model
C.base_net_weights = nn.get_weight_path()
all_train_imgs, classes_count, class_mapping = get_data(options.train_path, 'train')
all_val_imgs, val_classes_count, val_class_mapping = get_data(options.train_path, 'test')
if 'bg' not in classes_count:
classes_count['bg'] = 0
class_mapping['bg'] = len(class_mapping)
if 'bg' not in val_classes_count:
val_classes_count['bg'] = 0
val_class_mapping['bg'] = len(class_mapping)
C.class_mapping = class_mapping
inv_map = {v: k for k, v in class_mapping.items()}
from keras_frcnn import vgg as nn
if options.network == 'resnet50':
C.network = 'resnet50'
from keras_frcnn import resnet as nn
else:
print('No valid model')
raise ValueError
# 检查权重文件是否来自命令行
if options.input_weight_path:
C.base_net_weights = options.input_weight_path
else:
C.base_net_weights = nn.get_weight_path()
# 读取voc数据集的所有图片，类别统计，类的映射
all_imgs, classes_count, class_mapping = get_data('')
# 若没有背景类，向里面添加背景类
if 'bg' not in classes_count:
classes_count['bg'] = 0
# 背景所在的类别映射是最大的
class_mapping = len(classes_count)
C.class_mapping = class_mapping
# 以列表返回可遍历的(键, 值) 元组数组
inv_class_mapping = {v: k for k, v in class_mapping.items()}
print('Training_imgs per class:')
pprint.pprint(classes_count)
print('Num classes(bg) = {}'.format(len(classes_count)))
# open打开文件，默认是只读模式，现在是写模式
# pickle.dump：将对象obj保存到文件file中去
def work(path, curelist, textedit):
#print("I'm hearing too")
#textedit.append("I'm hearing too")
sys.setrecursionlimit(40000)
test_path = path
parser = OptionParser()
parser.add_option("-p",
"--path",
dest="test_path",
help="Path to test data.",
default=test_path)
parser.add_option(
"-n",
"--num_rois",
dest="num_rois",
help="Number of ROIs per iteration. Higher means more memory use.",
default=256)
parser.add_option(
"--config_filename",
dest="config_filename",
help=
"Location to read the metadata related to the training (generated when training).",
default="config.pickle")
parser.add_option("-o",
"--parser",
dest="parser",
help="Parser to use. One of simple or pascal_voc",
default="pascal_voc"), #default="pascal_voc"
(options, args) = parser.parse_args()
if not options.test_path: # if filename is not given
parser.error(
'Error: path to test data must be specified. Pass --path to command line'
)
if options.parser == 'pascal_voc':
from keras_frcnn.pascal_voc_parser import get_data
elif options.parser == 'simple':
from keras_frcnn.simple_parser import get_data
else:
raise ValueError(
"Command line option parser must be one of 'pascal_voc' or 'simple'"
)
config_output_filename = options.config_filename
with open(config_output_filename, 'rb') as f_in:
C = pickle.load(f_in)
# turn off any data augmentation at test time
C.use_horizontal_flips = False
C.use_vertical_flips = False
C.rot_90 = False
img_path = options.test_path
class_mapping = C.class_mapping
if 'bg' not in class_mapping:
class_mapping['bg'] = len(class_mapping)
#class_mapping = {v: k for k, v in class_mapping.iteritems()}
class_mapping = {v: k for k, v in class_mapping.items()}
print(class_mapping)
class_to_color = {
class_mapping[v]: np.random.randint(0, 255, 3)
for v in class_mapping
}
C.num_rois = int(options.num_rois)
if K.image_dim_ordering() == 'th':
input_shape_img = (3, None, None)
input_shape_features = (1024, None, None)
else:
input_shape_img = (None, None, 3)
input_shape_features = (None, None, 1024)
img_input = Input(shape=input_shape_img)
roi_input = Input(shape=(C.num_rois, 4))
feature_map_input = Input(shape=input_shape_features)
# define the base network (resnet here, can be VGG, Inception, etc)
shared_layers = nn.nn_base(img_input, trainable=True)
# define the RPN, built on the base layers
num_anchors = len(C.anchor_box_scales) * len(C.anchor_box_ratios)
rpn_layers = nn.rpn(shared_layers, num_anchors)
classifier = nn.classifier(feature_map_input,
roi_input,
C.num_rois,
nb_classes=len(class_mapping),
trainable=True)
model_rpn = Model(img_input, rpn_layers)
model_classifier_only = Model([feature_map_input, roi_input], classifier)
model_classifier = Model([feature_map_input, roi_input], classifier)
model_rpn.load_weights(C.model_path, by_name=True)
model_classifier.load_weights(C.model_path, by_name=True)
model_rpn.compile(optimizer='sgd', loss='mse')
model_classifier.compile(optimizer='sgd', loss='mse')
#####
all_imgs, _, _ = get_data(options.test_path)
test_imgs = [s for s in all_imgs if s['imageset'] == 'test']
#test_imgs=test_imgs1[3111:4056]
T = {}
P = {}
for idx, img_data in enumerate(test_imgs):
print('{}/{}'.format(idx, len(test_imgs)))
#textedit.append('{}/{}'.format(idx,len(test_imgs)))
st = time.time()
filepath = img_data['filepath']
print(filepath)
img = cv2.imread(filepath)
X, fx, fy = format_img(img, C)
if K.image_dim_ordering() == 'tf':
X = np.transpose(X, (0, 2, 3, 1))
# get the feature maps and output from the RPN
[Y1, Y2, F] = model_rpn.predict(X)
R = roi_helpers.rpn_to_roi(Y1,
Y2,
C,
K.image_dim_ordering(),
overlap_thresh=0.5) ##0.7
# convert from (x1,y1,x2,y2) to (x,y,w,h)
R[:, 2] -= R[:, 0]
R[:, 3] -= R[:, 1]
# apply the spatial pyramid pooling to the proposed regions
bboxes = {}
probs = {}
for jk in range(R.shape[0] // C.num_rois + 1):
ROIs = np.expand_dims(R[C.num_rois * jk:C.num_rois * (jk + 1), :],
axis=0)
if ROIs.shape[1] == 0:
break
if jk == R.shape[0] // C.num_rois:
# pad R
curr_shape = ROIs.shape
target_shape = (curr_shape[0], C.num_rois, curr_shape[2])
ROIs_padded = np.zeros(target_shape).astype(ROIs.dtype)
ROIs_padded[:, :curr_shape[1], :] = ROIs
ROIs_padded[0, curr_shape[1]:, :] = ROIs[0, 0, :]
ROIs = ROIs_padded
[P_cls, P_regr] = model_classifier_only.predict([F, ROIs])
for ii in range(P_cls.shape[1]):
if np.argmax(P_cls[0, ii, :]) == (P_cls.shape[2] - 1):
continue
cls_name = class_mapping[np.argmax(P_cls[0, ii, :])]
if cls_name not in bboxes:
bboxes[cls_name] = []
probs[cls_name] = []
(x, y, w, h) = ROIs[0, ii, :]
cls_num = np.argmax(P_cls[0, ii, :])
try:
(tx, ty, tw, th) = P_regr[0, ii,
4 * cls_num:4 * (cls_num + 1)]
tx /= C.classifier_regr_std[0]
ty /= C.classifier_regr_std[1]
tw /= C.classifier_regr_std[2]
th /= C.classifier_regr_std[3]
x, y, w, h = roi_helpers.apply_regr(
x, y, w, h, tx, ty, tw, th)
except:
pass
bboxes[cls_name].append(
[16 * x, 16 * y, 16 * (x + w), 16 * (y + h)])
probs[cls_name].append(np.max(P_cls[0, ii, :]))
all_dets = []
for key in bboxes:
bbox = np.array(bboxes[key])
new_boxes, new_probs = roi_helpers.non_max_suppression_fast(
bbox, np.array(probs[key]), overlap_thresh=0.45) ###0.5
for jk in range(new_boxes.shape[0]):
(x1, y1, x2, y2) = new_boxes[jk, :]
det = {
'x1': x1,
'x2': x2,
'y1': y1,
'y2': y2,
'class': key,
'prob': new_probs[jk]
}
all_dets.append(det)
print('Elapsed time = {}'.format(time.time() - st))
cursor = textedit.textCursor()
cursor.movePosition(QtGui.QTextCursor.End)
cursor.insertText('{}/{}'.format(idx, len(test_imgs)))
cursor.insertText("\r\n")
cursor.insertText('Elapsed time = {}'.format(time.time() - st))
cursor.insertText("\r\n")
# textedit.append('Elapsed time = {}'.format(time.time() - st))
textedit.setTextCursor(cursor)
textedit.ensureCursorVisible()
t, p = get_map(all_dets, img_data['bboxes'], (fx, fy))
for key in t.keys():
if key not in T:
T[key] = []
P[key] = []
T[key].extend(t[key])
P[key].extend(p[key])
p1 = []
t1 = []
p1.append(P["airbase"])
t1.append(T["airbase"])
p1.append(P["harbour"])
t1.append(T["harbour"])
p1.append(P["island"])
t1.append(T["island"])
prefastr = []
recfastr = []
apfastr = []
for m in range(len(p1)):
p11 = np.zeros(len(p1[m]))
for i in range(len(p1[m])):
if p1[m][i] > 0.45:
p11[i] = 1
else:
p11[i] = 0
p_p1 = p11
t_t1 = t1[m]
false_positives = np.zeros((0, ))
true_positives = np.zeros((0, ))
scores = np.zeros((0, ))
num_annotations = 0.0
nump = len(p_p1)
# for n in range (1915):#(len(p_p1)):
for n in range(len(p_p1)):
if t_t1[n] == 1 and p_p1[n] == 1:
true_positives = np.append(true_positives, 1)
false_positives = np.append(false_positives, 0)
scores = np.append(scores, p1[m][n])
if t_t1[n] == 0 and p_p1[n] == 1:
true_positives = np.append(true_positives, 0)
false_positives = np.append(false_positives, 1)
scores = np.append(scores, p1[m][n])
# if t_t1[n]==1 and p_p1[n]==0:
# true_positives = np.append(true_positives, 0)
# false_positives = np.append(false_positives, 0)
# scores = np.append(scores, p1[m][n])
if t_t1[n] == 1:
num_annotations = num_annotations + 1
descending_indices = np.argsort(-scores)
true_positives = true_positives[descending_indices]
false_positives = false_positives[descending_indices]
# compute false positives and true positives
true_positives = np.cumsum(true_positives)
false_positives = np.cumsum(false_positives)
# compute recall and precision
recall1 = true_positives / num_annotations
precision1 = true_positives / np.maximum(
true_positives + false_positives,
np.finfo(np.float64).eps)
average_precision = compute_ap(recall1, precision1)
prefastr.append(precision1)
recfastr.append(recall1)
apfastr.append(average_precision)
for i in range(0, len(recfastr)):
curelist[i].setData(recfastr[i], prefastr[i])
print('use resnet50')
# cfg.network = 'resnet50'
else:
print('Not a valid model')
raise ValueError
# 使用restnet网络
# check if weight path was passed via command line
if cfg.input_weight_path: # 这里已经被赋值为cfg里的值
cfg.base_net_weights = cfg.input_weight_path
else:
# set the path to weights based on backend and model
cfg.base_net_weights = nn.get_weight_path()
# 设定restore路径
all_imgs, classes_count, class_mapping, bird_class_count, bird_class_mapping = get_data(
cfg.train_path) # get_data函数在pascalvocparser.py里变
if 'bg' not in classes_count:
classes_count['bg'] = 0
class_mapping['bg'] = len(class_mapping)
cfg.class_mapping = class_mapping
inv_map = {v: k for k, v in class_mapping.items()}
print('Training images per class:')
pprint.pprint(classes_count)
print('Num classes (including bg) = {}'.format(len(classes_count)))
print('Training bird per class:')
pprint.pprint(bird_class_count)
print('total birds class is {}'.format(len(bird_class_count)))
import random
import pprint
import sys
import json
from keras_frcnn import config
sys.setrecursionlimit(40000)
C = config.Config()
C.num_rois = 8
from keras_frcnn.pascal_voc_parser import get_data
all_imgs, classes_count, class_mapping = get_data(sys.argv[1])
if 'bg' not in classes_count:
classes_count['bg'] = 0
class_mapping['bg'] = len(class_mapping)
with open('classes.json', 'w') as class_data_json:
json.dump(class_mapping, class_data_json)
inv_map = {v: k for k, v in class_mapping.iteritems()}
pprint.pprint(classes_count)
random.shuffle(all_imgs)
num_imgs = len(all_imgs)
train_imgs = [s for s in all_imgs if s['imageset'] == 'trainval']
rpn_layers = nn.rpn(shared_layers, num_anchors)
classifier = nn.classifier(feature_map_input, roi_input, C.num_rois, nb_classes = len(class_mapping), trainable = False)
model_rpn = Model(img_input, rpn_layers)
model_classifier = Model([feature_map_input, roi_input], classifier)
C.model_path = model_path
model_rpn.load_weights(C.model_path, by_name = True)
model_classifier.load_weights(C.model_path, by_name = True)
model_rpn.compile(optimizer = 'sgd', loss = 'mse')
model_classifier.compile(optimizer = 'sgd', loss = 'mse')
all_imgs, _, _ = get_data(options.data_path)
test_imgs = [s for s in all_imgs if s['imageset'] == options.file_type]
if len(test_imgs) == 0:
raise NameError('No images to process. Verify the path to testing images file and file_type parameter.')
print("Number of images to process: {}".format(len(test_imgs)))
print("============ Starting Detections ============")
T = {}
P = {}
st = time.time()
for idx, img_data in enumerate(test_imgs):
if idx % 100 == 0 and idx > 0:
print('================== {}/{} =================='.format(idx, len(test_imgs)))
