def train_kitti():
# config for data argument
cfg = config.Config()
cfg.use_horizontal_flips = True
cfg.use_vertical_flips = True
cfg.rot_90 = True
cfg.num_rois = 32
cfg.base_net_weights = os.path.join('./model/', nn.get_weight_path())
# TODO: the only file should to be change for other data to train
cfg.model_path = './model/kitti_frcnn_last.hdf5'
cfg.simple_label_file = 'simple_label.txt'
all_images, classes_count, class_mapping = get_data(cfg.simple_label_file)
#print(len(all_images))
if 'bg' not in classes_count:
classes_count['bg'] = 0
class_mapping['bg'] = len(class_mapping)
cfg.class_mapping = class_mapping
with open(cfg.config_save_file, 'wb') as config_f:
pickle.dump(cfg, config_f)
print(
'Config has been written to {}, and can be loaded when testing to ensure correct results'
.format(cfg.config_save_file))
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)))
random.shuffle(all_images)
num_imgs = len(all_images)
train_imgs = [s for s in all_images if s['imageset'] == 'trainval']
#print(len(train_imgs))
val_imgs = [s for s in all_images if s['imageset'] == 'test']
print('Num train samples {}'.format(len(train_imgs)))
print('Num val samples {}'.format(len(val_imgs)))
data_gen_train = data_generators.get_anchor_gt(train_imgs,
classes_count,
cfg,
nn.get_img_output_length,
K.image_dim_ordering(),
mode='train')
data_gen_val = data_generators.get_anchor_gt(val_imgs,
classes_count,
cfg,
nn.get_img_output_length,
K.image_dim_ordering(),
mode='val')
if K.image_dim_ordering() == 'th':
input_shape_img = (3, None, None)
else:
input_shape_img = (None, None, 3)
img_input = Input(shape=input_shape_img)
roi_input = Input(shape=(None, 4))
# 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(cfg.anchor_box_scales) * len(cfg.anchor_box_ratios)
rpn = nn.rpn(shared_layers, num_anchors)
classifier = nn.classifier(shared_layers,
roi_input,
cfg.num_rois,
nb_classes=len(classes_count),
trainable=True)
model_rpn = Model(img_input, rpn[:2])
model_classifier = Model([img_input, roi_input], classifier)
# this is a model that holds both the RPN and the classifier, used to load/save weights for the models
model_all = Model([img_input, roi_input], rpn[:2] + classifier)
try:
print('loading weights from {}'.format(cfg.base_net_weights))
model_rpn.load_weights(cfg.model_path, by_name=True)
model_classifier.load_weights(cfg.model_path, by_name=True)
except Exception as e:
print(e)
print(
'Could not load pretrained model weights. Weights can be found in the keras application folder '
'https://github.com/fchollet/keras/tree/master/keras/applications')
optimizer = Adam(lr=1e-5)
optimizer_classifier = Adam(lr=1e-5)
model_rpn.compile(optimizer=optimizer,
loss=[
losses_fn.rpn_loss_cls(num_anchors),
losses_fn.rpn_loss_regr(num_anchors)
])
model_classifier.compile(
optimizer=optimizer_classifier,
loss=[
losses_fn.class_loss_cls,
losses_fn.class_loss_regr(len(classes_count) - 1)
],
metrics={'dense_class_{}'.format(len(classes_count)): 'accuracy'})
model_all.compile(optimizer='sgd', loss='mae')
epoch_length = 1000
num_epochs = int(cfg.num_epochs)
iter_num = 0
losses = np.zeros((epoch_length, 5))
rpn_accuracy_rpn_monitor = []
rpn_accuracy_for_epoch = []
start_time = time.time()
best_loss = np.Inf
class_mapping_inv = {v: k for k, v in class_mapping.items()}
print('Starting training')
vis = True
for epoch_num in range(num_epochs):
progbar = generic_utils.Progbar(epoch_length)
print('Epoch {}/{}'.format(epoch_num + 1, num_epochs))
while True:
try:
if len(rpn_accuracy_rpn_monitor
) == epoch_length and cfg.verbose:
mean_overlapping_bboxes = float(
sum(rpn_accuracy_rpn_monitor)) / len(
rpn_accuracy_rpn_monitor)
rpn_accuracy_rpn_monitor = []
print(
'Average number of overlapping bounding boxes from RPN = {} for {} previous iterations'
.format(mean_overlapping_bboxes, epoch_length))
if mean_overlapping_bboxes == 0:
print(
'RPN is not producing bounding boxes that overlap'
' the ground truth boxes. Check RPN settings or keep training.'
)
X, Y, img_data = next(data_gen_train)
loss_rpn = model_rpn.train_on_batch(X, Y)
P_rpn = model_rpn.predict_on_batch(X)
result = roi_helpers.rpn_to_roi(P_rpn[0],
P_rpn[1],
cfg,
K.image_dim_ordering(),
use_regr=True,
overlap_thresh=0.6,
max_boxes=300)
# note: calc_iou converts from (x1,y1,x2,y2) to (x,y,w,h) format
X2, Y1, Y2, IouS = roi_helpers.calc_iou(
result, img_data, cfg, class_mapping)
if X2 is None:
rpn_accuracy_rpn_monitor.append(0)
rpn_accuracy_for_epoch.append(0)
continue
neg_samples = np.where(Y1[0, :, -1] == 1)
pos_samples = np.where(Y1[0, :, -1] == 0)
if len(neg_samples) > 0:
neg_samples = neg_samples[0]
else:
neg_samples = []
if len(pos_samples) > 0:
pos_samples = pos_samples[0]
else:
pos_samples = []
rpn_accuracy_rpn_monitor.append(len(pos_samples))
rpn_accuracy_for_epoch.append((len(pos_samples)))
if cfg.num_rois > 1:
if len(pos_samples) < cfg.num_rois // 2:
selected_pos_samples = pos_samples.tolist()
else:
selected_pos_samples = np.random.choice(
pos_samples, cfg.num_rois // 2,
replace=False).tolist()
try:
selected_neg_samples = np.random.choice(
neg_samples,
cfg.num_rois - len(selected_pos_samples),
replace=False).tolist()
except:
selected_neg_samples = np.random.choice(
neg_samples,
cfg.num_rois - len(selected_pos_samples),
replace=True).tolist()
sel_samples = selected_pos_samples + selected_neg_samples
else:
# in the extreme case where num_rois = 1, we pick a random pos or neg sample
selected_pos_samples = pos_samples.tolist()
selected_neg_samples = neg_samples.tolist()
if np.random.randint(0, 2):
sel_samples = random.choice(neg_samples)
else:
sel_samples = random.choice(pos_samples)
loss_class = model_classifier.train_on_batch(
[X, X2[:, sel_samples, :]],
[Y1[:, sel_samples, :], Y2[:, sel_samples, :]])
losses[iter_num, 0] = loss_rpn[1]
losses[iter_num, 1] = loss_rpn[2]
losses[iter_num, 2] = loss_class[1]
losses[iter_num, 3] = loss_class[2]
losses[iter_num, 4] = loss_class[3]
iter_num += 1
progbar.update(
iter_num,
[('rpn_cls', np.mean(losses[:iter_num, 0])),
('rpn_regr', np.mean(losses[:iter_num, 1])),
('detector_cls', np.mean(losses[:iter_num, 2])),
('detector_regr', np.mean(losses[:iter_num, 3]))])
if iter_num == epoch_length:
loss_rpn_cls = np.mean(losses[:, 0])
loss_rpn_regr = np.mean(losses[:, 1])
loss_class_cls = np.mean(losses[:, 2])
loss_class_regr = np.mean(losses[:, 3])
class_acc = np.mean(losses[:, 4])
mean_overlapping_bboxes = float(sum(
rpn_accuracy_for_epoch)) / len(rpn_accuracy_for_epoch)
rpn_accuracy_for_epoch = []
if cfg.verbose:
print(
'Mean number of bounding boxes from RPN overlapping ground truth boxes: {}'
.format(mean_overlapping_bboxes))
print(
'Classifier accuracy for bounding boxes from RPN: {}'
.format(class_acc))
print('Loss RPN classifier: {}'.format(loss_rpn_cls))
print('Loss RPN regression: {}'.format(loss_rpn_regr))
print('Loss Detector classifier: {}'.format(
loss_class_cls))
print('Loss Detector regression: {}'.format(
loss_class_regr))
print('Elapsed time: {}'.format(time.time() -
start_time))
curr_loss = loss_rpn_cls + loss_rpn_regr + loss_class_cls + loss_class_regr
iter_num = 0
start_time = time.time()
if curr_loss < best_loss:
if cfg.verbose:
print(
'Total loss decreased from {} to {}, saving weights'
.format(best_loss, curr_loss))
best_loss = curr_loss
model_all.save_weights(cfg.model_path)
break
except Exception as e:
print('Exception: {}'.format(e))
# save model
model_all.save_weights(cfg.model_path)
continue
print('Training complete, exiting.')
img_input = Input(shape=input_shape_img)
roi_input = Input(shape=(C_deepfashion.num_rois, 4))
feature_map_input = Input(shape=input_shape_features)
#df model
# define the base network (resnet here, can be VGG, Inception, etc)
shared_layers_df = nn.nn_base(img_input, trainable=False)
# define the RPN, built on the base layers
num_anchors_df = len(C_deepfashion.anchor_box_scales) * len(
C_deepfashion.anchor_box_ratios)
rpn_layers_df = nn.rpn(shared_layers_df, num_anchors_df)
classifier_df = nn.classifier(feature_map_input,
roi_input,
C_deepfashion.num_rois,
nb_classes=len(class_mapping_df),
trainable=True)
model_rpn_df = Model(img_input, rpn_layers_df)
model_classifier_only_df = Model([feature_map_input, roi_input], classifier_df)
model_classifier_df = Model([feature_map_input, roi_input], classifier_df)
# print('Loading weights from {}'.format(C.model_path))
model_rpn_df.load_weights("model_frcnn.hdf5_epoch_9", by_name=True)
model_classifier_df.load_weights("model_frcnn.hdf5_epoch_9", by_name=True)
model_rpn_df.compile(optimizer='sgd', loss='mse')
model_classifier_df.compile(optimizer='sgd', loss='mse')
else:
input_shape_img = (None, None, 3)
img_input = Input(shape=input_shape_img)
roi_input = Input(shape=(None, 4))
# 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 = nn.rpn(shared_layers, num_anchors)
classifier = nn.classifier(shared_layers,
roi_input,
C.num_rois,
nb_classes=len(classes_count),
trainable=True)
model_rpn = Model(img_input, rpn[:2])
model_classifier = Model([img_input, roi_input], classifier)
# this is a model that holds both the RPN and the classifier, used to load/save weights for the models
model_all = Model([img_input, roi_input], rpn[:2] + classifier)
try:
print('loading weights from {}'.format(C.base_net_weights))
model_rpn.load_weights(C.base_net_weights, by_name=True)
model_classifier.load_weights(C.base_net_weights, by_name=True)
except Exception as e:
print(
feature_map_input = Input(shape=input_shape_features)
roi_input = Input(shape=(num_rois, 4))
# define the base network (resnet here, can be VGG, Inception, etc)
shared_layers = nn.nn_base(img_input)
# define the RPN, built on the base layers
num_anchors = len(C.anchor_box_scales) * len(C.anchor_box_ratios)
rpn = nn.rpn(shared_layers, num_anchors)
# classifier, uses base layers + proposals
print(class_mapping)
classifier = nn.classifier(feature_map_input,
roi_input,
num_rois,
nb_classes=len(class_mapping))
model_rpn = Model(img_input, rpn + [shared_layers])
model_classifier = Model([feature_map_input, roi_input], classifier)
weights_path = 'model_frcnn.hdf5'
model_rpn.load_weights(weights_path, by_name=True)
model_classifier.load_weights(weights_path, by_name=True)
model_rpn.compile(optimizer='sgd', loss='mse')
model_classifier.compile(optimizer='sgd', loss='mse')
all_imgs = []
classes = {}
def measure_map(config_output_filename, real_model_path):
with open(config_output_filename, 'r') as f_in:
C = pickle.load(f_in)
# img_path = options.test_path
img_path = '/home/comp/e4252392/map4frcnn.txt'
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()}
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)
C.num_rois = 32
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(real_model_path, by_name=True)
model_classifier.load_weights(real_model_path, by_name=True)
model_rpn.compile(optimizer='sgd', loss='mse')
model_classifier.compile(optimizer='sgd', loss='mse')
all_imgs, _, _ = get_data(img_path)
# test_imgs = [s for s in all_imgs if s['imageset'] == 'test']
test_imgs = [s for s in all_imgs]
T = {}
P = {}
print('Calculating mAP')
st = time.time()
for idx, img_data in enumerate(test_imgs):
# print('{}/{}'.format(idx,len(test_imgs)))
# st = time.time()
filepath = img_data['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=0.7)
# 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 = []
album_ap = 0.0
logo_ap = 0.0
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=0.5)
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))
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])
all_aps = []
for key in T.keys():
ap = average_precision_score(T[key], P[key])
# print('{} AP: {}'.format(key, ap))
all_aps.append(ap)
if idx == len(test_imgs) - 1:
if key == 'album':
album_ap = ap
if key == 'logo':
logo_ap = ap
# print('mAP = {}'.format(np.mean(np.array(all_aps))))
if idx == len(test_imgs) - 1:
mAP = np.mean(np.array(all_aps))
print('Elapsed time = {}'.format(time.time() - st))
print('album ap = {}'.format(album_ap))
print('logo ap = {}'.format(logo_ap))
print('mAP = {}'.format(mAP))
return [album_ap, logo_ap, mAP]
if K.image_dim_ordering() == 'th':
input_shape_img = (3, None, None)
else:
input_shape_img = (None, None, 3)
img_input = Input(shape=input_shape_img)
roi_input = Input(shape=(C.num_rois, 4))
# 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 = nn.rpn(shared_layers, num_anchors)
classifier = nn.classifier(shared_layers, roi_input, C.num_rois, nb_classes=len(classes_count), trainable=True)
model_rpn = Model(img_input, rpn[:2])
model_classifier = Model([img_input, roi_input], classifier)
# this is a model that holds both the RPN and the classifier, used to load/save weights for the models
model_all = Model([img_input, roi_input], rpn[:2] + classifier)
try:
print('loading weights from {}'.format(C.base_net_weights))
model_rpn.load_weights(C.base_net_weights, by_name=True)
model_classifier.load_weights(C.base_net_weights, by_name=True)
except:
print('Could not load pretrained model weights. Weights can be found at {} and {}'.format(
'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_th_dim_ordering_th_kernels_notop.h5',
'https://github.com/fchollet/deep-learning-models/releases/download/v0.2/resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5'
def predict(args_):
path = args_.path
with open('config.pickle', 'rb') as f_in:
cfg = pickle.load(f_in)
cfg.use_horizontal_flips = False
cfg.use_vertical_flips = False
cfg.rot_90 = False
class_mapping = cfg.class_mapping
if 'bg' not in class_mapping:
class_mapping['bg'] = len(class_mapping)
class_mapping = {v: k for k, v in class_mapping.items()}
# tensorflow的输入方式是none,none,3
input_shape_img = (None, None, 3)
# 这里如果是resnet，num_features = 1024
# 如果是vgg，num_features = 512
input_shape_features = (None, None, 1024)
img_input = Input(shape=input_shape_img)
roi_input = Input(shape=(cfg.num_rois, 4))
feature_map_input = Input(shape=input_shape_features)
shared_layers = nn.nn_base(img_input, trainable=True)
# define the RPN, built on the base layers
# 构建rpn输出
# anchor的个数
num_anchors = len(cfg.anchor_box_scales) * len(cfg.anchor_box_ratios)
rpn_layers = nn.rpn(shared_layers, num_anchors)
# 构建classifier的输出，参数分别是：特征层输出，预选框，探测框的输入，多少个类，是否可训练。
classifier = nn.classifier(feature_map_input,
roi_input,
cfg.num_rois,
nb_classes=len(class_mapping),
trainable=True)
# 构建网络
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)
# 加载参数
print('Loading weights from {}'.format(cfg.model_path))
# self.model_path = 'model_trained/model_frcnn.vgg.hdf5'
# 这里是resnet，所以不太明白这里的model_path？？？
model_rpn.load_weights(cfg.model_path, by_name=True)
model_classifier.load_weights(cfg.model_path, by_name=True)
# 这里是测试阶段。不用训练，但是这种加载模型，之后要求编译是keras要求的，随便找个mse即可
model_rpn.compile(optimizer='sgd', loss='mse')
model_classifier.compile(optimizer='sgd', loss='mse')
Ap = [[] for i in range(len(class_mapping))]
print("Appp", Ap)
if os.path.isdir(path):
for idx, img_name in enumerate(sorted(os.listdir(path))):
if not img_name.lower().endswith(
('.bmp', '.jpeg', '.jpg', '.png', '.tif', '.tiff')):
continue
print(img_name)
predict_single_image(os.path.join(path, img_name), model_rpn,
model_classifier_only, cfg, class_mapping, Ap)
elif os.path.isfile(path):
print('predict image from {}'.format(path))
predict_single_image(path, model_rpn, model_classifier_only, cfg,
class_mapping, Ap)
print("Ap:")
print(Ap)
Acc = []
for i in range(len(class_mapping)):
sum = 0
avg = 0
for j in Ap[i]:
sum += j
if len(Ap[i]) != 0:
avg = sum / (len(Ap[i]))
Acc.append(avg)
else:
Acc.append(0)
for i in range(len(class_mapping)):
print(class_mapping[i] + "acc:{}".format(Acc[i]))
def configure_keras_models(config):
"""Configures Keras.
Args:
nn (Neural Net): A keras NN.
config (object): The config file.
Returns:
tuple: A tuple of three classifiers: (1) the rpn classifier, (2) the
classifier (only), (3) the classifier.
"""
# Import the correct NN according to config
# This must be called within main so that import is called
if config.network == 'resnet50':
import keras_frcnn.resnet as nn
num_features = 1024
elif config.network == 'vgg':
import keras_frcnn.vgg as nn
num_features = 512
# Configure Keras
if K.image_dim_ordering() == 'th':
input_shape_img = (3, None, None)
input_shape_features = (num_features, None, None)
else:
input_shape_img = (None, None, 3)
input_shape_features = (None, None, num_features)
# Config inputs
img_input = Input(shape=input_shape_img)
roi_input = Input(shape=(config.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(config.anchor_box_scales) * len(config.anchor_box_ratios)
rpn_layers = nn.rpn(shared_layers, num_anchors)
# Classifier to return
classifier = nn.classifier(feature_map_input,
roi_input,
config.num_rois,
nb_classes=len(config.class_mapping),
trainable=True)
print("Configuring Keras with:")
print(" - Neural Network: %s..." % config.network)
print(" - Weights loaded from: %s" % config.model_path)
print(" - Dimension Ordering: %s" % K.image_dim_ordering())
print(" - Num Features: %s" % num_features)
print(" - Num rois: %s" % config.num_rois)
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(config.model_path, by_name=True)
model_classifier.load_weights(config.model_path, by_name=True)
model_rpn.compile(optimizer='sgd', loss='mse')
model_classifier.compile(optimizer='sgd', loss='mse')
return (model_rpn, model_classifier_only, model_classifier)
def upload_file():
print("request is ", request.files)
st = time.time()
content_length = request.content_length
print(f"Content_length : {content_length}")
print("data type is ", type(request))
print("data type of request files ", type(request.files))
data_dict = request.form.to_dict()
#print(type(data_dict))
#print(data_dict['file'])
data = (data_dict['file'].split(',')[1])
#print(len(data_dict))
#print(data)
imgdata = base64.b64decode(data)
print("imagedata type is", type(imgdata))
img2 = Image.open(io.BytesIO(imgdata))
print(type(img2))
#img2.show()
#img = cv2.imread(img2)
#print('opencv type' , type(img))
#print(type(img))
a = np.array(img2.getdata()).astype(np.float64)
#print('datatype of w ', w.dtype)
#b = np.ones(172800,3)
#a = np.concatenate((w,b), axis=None)
print('type of data to model ', type(a))
print('shape of data from frontend', a.shape)
#r, c = a.shape
#print('Value of r', r)
if a.shape == (480000, 3):
data = a.reshape(600, 800, 3)
else:
data = a.reshape(480, 640, 3)
st = time.time()
parser = OptionParser()
parser.add_option(
"-n",
"--num_rois",
type="int",
dest="num_rois",
help="Number of ROIs per iteration. Higher means more memory use.",
default=4)
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("--network",
dest="network",
help="Base network to use. Supports vgg or resnet50.",
default='vgg')
(options, args) = parser.parse_args()
config_output_filename = options.config_filename
with open(config_output_filename, 'rb') as f_in:
C = pickle.load(f_in)
if C.network == 'resnet50':
import keras_frcnn.resnet as nn
elif C.network == 'vgg':
import keras_frcnn.vgg as nn
# turn off any data augmentation at test time
C.use_horizontal_flips = False
C.use_vertical_flips = False
C.rot_90 = False
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.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 C.network == 'resnet50':
num_features = 1024
elif C.network == 'vgg':
num_features = 512
if K.image_dim_ordering() == 'th':
input_shape_img = (3, None, None)
input_shape_features = (num_features, None, None)
else:
input_shape_img = (None, None, 3)
input_shape_features = (None, None, num_features)
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)
print('Loading weights from {}'.format(C.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 = []
classes = {}
bbox_threshold = 0.6
visualise = True
#if not img_name.lower().endswith(('.bmp', '.jpeg', '.jpg', '.png', '.tif', '.tiff')):
# continue
#print(img_name)
#filepath = os.path.join(img_path,img_name)
img = data
#cv2.imshow('img', img)
#cv2.waitKey(0)
X, ratio = 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=0.6)
# 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.max(P_cls[0, ii, :]) < bbox_threshold or 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([
C.rpn_stride * x, C.rpn_stride * y, C.rpn_stride * (x + w),
C.rpn_stride * (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=0.6)
for jk in range(new_boxes.shape[0]):
(x1, y1, x2, y2) = new_boxes[jk, :]
(real_x1, real_y1, real_x2,
real_y2) = get_real_coordinates(ratio, x1, y1, x2, y2)
cv2.rectangle(
img, (real_x1, real_y1), (real_x2, real_y2),
(int(class_to_color[key][0]), int(
class_to_color[key][1]), int(class_to_color[key][2])), 2)
textLabel = '{}: {}'.format(key, int(100 * new_probs[jk]))
all_dets.append((key, 100 * new_probs[jk]))
(retval, baseLine) = cv2.getTextSize(textLabel,
cv2.FONT_HERSHEY_COMPLEX, 1,
1)
textOrg = (real_x1, real_y1 - 0)
cv2.rectangle(
img, (textOrg[0] - 5, textOrg[1] + baseLine - 5),
(textOrg[0] + retval[0] + 5, textOrg[1] - retval[1] - 5),
(0, 0, 0), 2)
cv2.rectangle(
img, (textOrg[0] - 5, textOrg[1] + baseLine - 5),
(textOrg[0] + retval[0] + 5, textOrg[1] - retval[1] - 5),
(255, 255, 255), -1)
cv2.putText(img, textLabel, textOrg, cv2.FONT_HERSHEY_DUPLEX, 1,
(0, 0, 0), 1)
print('Elapsed time = {}'.format(time.time() - st))
print('number of windoiws detected', len(all_dets))
print(all_dets)
r = len(all_dets)
img3 = normalize(img)
#plt.imshow(img)
#cv2.imshow('img3', img3)
#cv2.waitKey(0)
K.clear_session()
#data = process(data)
#print('after reshape',data.shape)
im2 = Image.fromarray(img.astype("uint8"), "RGB")
print("im2 data type is ", type(im2))
#to_frontend = (" ".join(str(x) for x in data))
db = data.tobytes()
print('type of data to database :', type(db))
todb = insertBLOB('Image007', db)
print('final data shape fed to model : ', data.shape)
# ImageFile img = db.b64encode()
# with open("t.png", "rb") as imageFile:
# str = base64.b64encode(imageFile.read())
#cv2.imshow('image', cv2.cvtColor(data, cv2.COLOR_BGR2GRAY))
#cv2.waitKey()
#str = base64.b64encode(data)
# return jsonify(to_frontend, r)
#img = Image.open( 'C:\Window Counter_Project\Flickr\Window_101 (131).jpg' )
#img.load()
#data = np.asarray( img, dtype="int32" )
#im = Image.fromarray(data.astype("uint8"))
#im.show() # uncomment to look at the image
rawBytes = io.BytesIO()
print(rawBytes)
im2.save(rawBytes, "jpeg")
#im2.show()
print('type of im2 is ', type(im2))
rawBytes.seek(0) # return to the start of the file
response_obj = {
'count': r,
'image':
"data:image/jpeg;base64," + str(base64.b64encode(rawBytes.read()))
}
#print("response is", type(response_obj))
return jsonify(Data=response_obj)
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])
def operation():
#After prediction
K.clear_session()
sys.setrecursionlimit(40000)
parser = OptionParser()
parser.add_option("-p",
"--path",
dest="test_path",
default="images",
help="Path to test data.")
parser.add_option(
"-n",
"--num_rois",
dest="num_rois",
help="Number of ROIs per iteration. Higher means more memory use.",
default=32)
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("--network",
dest="network",
help="Base network to use. Supports vgg or resnet50.",
default='resnet50')
(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'
)
config_output_filename = options.config_filename
with open(config_output_filename, 'rb') as f_in:
C = pickle.load(f_in)
if C.network == 'resnet50':
import keras_frcnn.resnet as nn
elif C.network == 'vgg':
import keras_frcnn.vgg as nn
# 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
def format_img_size(img, C):
""" formats the image size based on config """
img_min_side = float(C.im_size)
(height, width, _) = img.shape
if width <= height:
ratio = img_min_side / width
new_height = int(ratio * height)
new_width = int(img_min_side)
else:
ratio = img_min_side / height
new_width = int(ratio * width)
new_height = int(img_min_side)
img = cv2.resize(img, (new_width, new_height),
interpolation=cv2.INTER_CUBIC)
return img, ratio
def format_img_channels(img, C):
""" formats the image channels based on config """
img = img[:, :, (2, 1, 0)]
img = img.astype(np.float32)
img[:, :, 0] -= C.img_channel_mean[0]
img[:, :, 1] -= C.img_channel_mean[1]
img[:, :, 2] -= C.img_channel_mean[2]
img /= C.img_scaling_factor
img = np.transpose(img, (2, 0, 1))
img = np.expand_dims(img, axis=0)
return img
def format_img(img, C):
""" formats an image for model prediction based on config """
img, ratio = format_img_size(img, C)
img = format_img_channels(img, C)
return img, ratio
# Method to transform the coordinates of the bounding box to its original size
def get_real_coordinates(ratio, x1, y1, x2, y2):
real_x1 = int(round(x1 // ratio))
real_y1 = int(round(y1 // ratio))
real_x2 = int(round(x2 // ratio))
real_y2 = int(round(y2 // ratio))
return (real_x1, real_y1, real_x2, real_y2)
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.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 C.network == 'resnet50':
num_features = 1024
elif C.network == 'vgg':
num_features = 512
if K.image_dim_ordering() == 'th':
input_shape_img = (3, None, None)
input_shape_features = (num_features, None, None)
else:
input_shape_img = (None, None, 3)
input_shape_features = (None, None, num_features)
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)
print('Loading weights from {}'.format(C.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 = []
classes = {}
bbox_threshold = 0.8
visualise = True
object = []
for idx, img_name in enumerate(sorted(os.listdir(img_path))):
if not img_name.lower().endswith(
('.bmp', '.jpeg', '.jpg', '.png', '.tif', '.tiff')):
continue
print(img_name)
st = time.time()
filepath = os.path.join(img_path, img_name)
img = cv2.imread(filepath)
X, ratio = 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=0.7)
# 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.max(P_cls[0, ii, :]) < bbox_threshold or 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([
C.rpn_stride * x, C.rpn_stride * y, C.rpn_stride * (x + w),
C.rpn_stride * (y + h)
])
probs[cls_name].append(np.max(P_cls[0, ii, :]))
all_dets = []
item = []
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=0.5)
for jk in range(new_boxes.shape[0]):
(x1, y1, x2, y2) = new_boxes[jk, :]
(real_x1, real_y1, real_x2,
real_y2) = get_real_coordinates(ratio, x1, y1, x2, y2)
cv2.rectangle(
img, (real_x1, real_y1), (real_x2, real_y2),
(int(class_to_color[key][0]), int(class_to_color[key][1]),
int(class_to_color[key][2])), 2)
textLabel = '{}: {}'.format(key, int(100 * new_probs[jk]))
all_dets.append((key, 100 * new_probs[jk]))
(retval, baseLine) = cv2.getTextSize(textLabel,
cv2.FONT_HERSHEY_COMPLEX,
1, 1)
textOrg = (real_x1, real_y1 - 0)
cv2.rectangle(
img, (textOrg[0] - 5, textOrg[1] + baseLine - 5),
(textOrg[0] + retval[0] + 5, textOrg[1] - retval[1] - 5),
(0, 0, 0), 2)
cv2.rectangle(
img, (textOrg[0] - 5, textOrg[1] + baseLine - 5),
(textOrg[0] + retval[0] + 5, textOrg[1] - retval[1] - 5),
(255, 255, 255), -1)
cv2.putText(img, textLabel, textOrg, cv2.FONT_HERSHEY_DUPLEX,
1, (0, 0, 0), 1)
# print(textLabel)
# print(real_x1, real_y1, real_x2, real_y2)
if (100 * new_probs[jk]) > 95:
item.append([key, [real_x1, real_y1, real_x2, real_y2]])
print(all_dets)
object.append([[idx], [item]])
# print (object)
# print('Elapsed time = {}'.format(time.time() - st))
# cv2.imshow('img', img)
# cv2.waitKey(0)
cv2.imwrite('./results_imgs/{}.png'.format(idx), img)
print("=======================")
return object
def testModel(config_filename='config_ui.pickle'):
st.markdown('## Starting validation of test data set')
sys.setrecursionlimit(40000)
config = tf.compat.v1.ConfigProto()
config.gpu_options.allow_growth = True
config.log_device_placement = True
sess = tf.compat.v1.Session(config=config)
K.set_session(sess)
test_path = 'test'
num_rois = 4
config_filename = config_filename
network = 'resnet50'
config_output_filename = config_filename
with open(config_output_filename, 'rb') as f_in:
C = pickle.load(f_in)
if C.network == 'resnet50':
import keras_frcnn.resnet as nn
elif C.network == 'vgg':
import keras_frcnn.vgg as nn
# turn off any data augmentation at test time
C.use_horizontal_flips = False
C.use_vertical_flips = False
C.rot_90 = False
img_path = 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.items()}
st.write('Class Mapping', class_mapping)
class_to_color = {
class_mapping[v]: np.random.randint(0, 255, 3)
for v in class_mapping
}
C.num_rois = int(num_rois)
if C.network == 'resnet50':
num_features = 1024
elif C.network == 'vgg':
num_features = 512
if K.image_data_format() == 'channels_first':
input_shape_img = (3, None, None)
input_shape_features = (num_features, None, None)
else:
input_shape_img = (None, None, 3)
input_shape_features = (None, None, num_features)
img_input = Input(shape=input_shape_img)
roi_input = Input(shape=(C.num_rois, 4))
feature_map_input = Input(shape=input_shape_features)
## Defining Model
# 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)
st.write(f'Loading weights from {C.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 = []
classes = {}
## few hyper parameters to select bbox
bbox_threshold = 0.9
visualise = True
set_Overlap_threshold = 0.1
progress_bar = st.progress(0.0)
with st.spinner('Wait for sample test images...'):
for idx, img_name in enumerate(sorted(os.listdir(img_path))):
progress_bar.progress((idx + 0.1) / len(os.listdir(img_path)))
if not img_name.lower().endswith(
('.bmp', '.jpeg', '.jpg', '.png', '.tif', '.tiff')):
continue
st.write(img_name)
stTime = time.time()
filepath = os.path.join(img_path, img_name)
img = cv2.imread(filepath)
X, ratio = format_img(img, C)
if K.image_data_format() == 'channels_last':
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_data_format(),
overlap_thresh=0.7) #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:
print("ROI Shape: ", ROIs.shape[1])
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]):
#print("np max:",np.max(P_cls[0, ii, :]))
#print("np argmax:",np.argmax(P_cls[0, ii, :]))
#print(np.max(P_cls[0, ii, :]) < bbox_threshold)
if np.max(P_cls[0, ii, :]) < bbox_threshold or np.argmax(
P_cls[0, ii, :]) == (P_cls.shape[2] - 1):
continue
cls_name = class_mapping[np.argmax(P_cls[0, ii, :])]
#print('class name:',cls_name)
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([
C.rpn_stride * x, C.rpn_stride * y,
C.rpn_stride * (x + w), C.rpn_stride * (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=set_Overlap_threshold)
for jk in range(new_boxes.shape[0]):
(x1, y1, x2, y2) = new_boxes[jk, :]
(real_x1, real_y1, real_x2,
real_y2) = get_real_coordinates(ratio, x1, y1, x2, y2)
cv2.rectangle(img, (real_x1, real_y1), (real_x2, real_y2),
(int(class_to_color[key][0]),
int(class_to_color[key][1]),
int(class_to_color[key][2])), 2)
textLabel = f'{key}: {int(100*new_probs[jk])}'
all_dets.append((key, 100 * new_probs[jk]))
(retval,
baseLine) = cv2.getTextSize(textLabel,
cv2.FONT_HERSHEY_COMPLEX, 1,
1)
textOrg = (real_x1, real_y1 - 0)
cv2.rectangle(img,
(textOrg[0] - 5, textOrg[1] + baseLine - 5),
(textOrg[0] + retval[0] + 5,
textOrg[1] - retval[1] - 5), (0, 0, 0), 2)
cv2.rectangle(img,
(textOrg[0] - 5, textOrg[1] + baseLine - 5),
(textOrg[0] + retval[0] + 5,
textOrg[1] - retval[1] - 5),
(255, 255, 255), -1)
cv2.putText(img, textLabel, textOrg,
cv2.FONT_HERSHEY_DUPLEX, 1, (0, 0, 0), 1)
st.write(f'Elapsed time = {time.time() - stTime}')
st.write(all_dets)
plt.figure(figsize=(10, 10))
plt.grid()
plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
#plt.show()
st.image(img, use_column_width=True, clamp=True)
#cv2.imwrite('./results_imgs-fp-mappen-test/{}.png'.format(os.path.splitext(str(img_name))[0]),img)
from keras_frcnn.simple_parser import get_data
test_path = 'test_annotationAlt.txt' # Test data (annotation file)
startTime = time.time()
test_imgs, classes_count, class_mapping = get_data(test_path)
st.write('Spend %0.2f mins to load test data' %
((time.time() - startTime) / 60))
class_mapping = C.class_mapping
class_mapping = {v: k for k, v in class_mapping.items()}
st.write(class_mapping)
class_to_color = {
class_mapping[v]: np.random.randint(0, 255, 3)
for v in class_mapping
}
from sklearn.metrics import average_precision_score
set_Overlap_threshold = 0.1
T = {}
P = {}
mAPs = []
iou_map = []
progress_bar1 = st.progress(0.0)
with st.spinner('Wait for test set evaluation...'):
for idx, img_data in enumerate(test_imgs):
progress_bar1.progress((idx + 0.1) / len(test_imgs))
st.write('{}/{}'.format(idx, len(test_imgs)))
startTime = time.time()
filepath = img_data['filepath']
img = cv2.imread(filepath)
X, fx, fy = format_img_map(img, C)
# Change X (img) shape from (1, channel, height, width) to (1, height, width, channel)
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 = rpn_to_roi(Y1,
Y2,
C,
K.image_data_format(),
overlap_thresh=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])
# Calculate all classes' bboxes coordinates on resized image (300, 400)
# Drop 'bg' classes bboxes
for ii in range(P_cls.shape[1]):
# If class name is 'bg', continue
if np.argmax(P_cls[0, ii, :]) == (P_cls.shape[2] - 1):
continue
# Get class name
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])
# Apply non-max-suppression on final bboxes to get the output bounding boxe
new_boxes, new_probs = non_max_suppression_fast(
bbox,
np.array(probs[key]),
overlap_thresh=set_Overlap_threshold)
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)
st.write('Elapsed time = {}'.format(time.time() - startTime))
t, p, iouVal = 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])
all_aps = []
for key in T.keys():
ap = average_precision_score(T[key], P[key])
st.write('{} AP: {}'.format(key, ap))
all_aps.append(ap)
st.write('mAP = {}'.format(np.mean(np.array(all_aps))))
st.write('iou = {}'.format(np.mean(iouVal)))
mAPs.append(np.mean(np.array(all_aps)))
iou_map.append(iouVal)
st.markdown('## Mean IOU:', Average(iou_map))
st.markdown('## Mean average precision:', np.mean(np.array(mAPs)))
def test_frcnn(img_name, config, model):
from keras.models import Model
from keras_frcnn.RoiPoolingConv import RoiPoolingConv
import keras_frcnn.resnet as nn
config_output_filename = config
with open(config_output_filename, 'rb') as f_in:
C = pickle.load(f_in)
C.use_horizontal_flips = False
C.use_vertical_flips = False
C.rot_90 = False
C.num_rois = 32
C.model_path = model
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.items()}
print(class_mapping)
num_features = 1024
if K.image_dim_ordering() == 'th':
input_shape_img = (3, None, None)
input_shape_features = (num_features, None, None)
else:
input_shape_img = (None, None, 3)
input_shape_features = (None, None, num_features)
img_input = Input(shape=input_shape_img)
roi_input = Input(shape=(C.num_rois, 4))
feature_map_input = Input(shape=input_shape_features)
shared_layers = nn.nn_base(img_input, trainable=True)
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)
print('Loading weights from {}'.format(C.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')
# crop
bbox_threshold = 0.8
crops = []
# img_path = path
# for idx, img_name in enumerate(sorted(os.listdir(img_path))):
# if not img_name.lower().endswith(('.bmp', '.jpeg', '.jpg', '.png', '.tif', '.tiff')):
# continue
print(img_name)
st = time.time()
# filepath = os.path.join(img_path,img_name)
# img = cv2.imread(filepath)
img = cv2.imread(img_name)
X, ratio = format_img(img, C)
if K.image_dim_ordering() == 'tf':
X = np.transpose(X, (0, 2, 3, 1))
[Y1, Y2, F] = model_rpn.predict(X)
R = roi_helpers.rpn_to_roi(Y1,
Y2,
C,
K.image_dim_ordering(),
overlap_thresh=0.7)
R[:, 2] -= R[:, 0]
R[:, 3] -= R[:, 1]
bboxes = {}
probs = {}
# roifs = {}
# scenefs = {}
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
# out_roi_pool = RoiPoolingConv(14, C.num_rois)([feature_map_input, roi_input])
# haha = Model(inputs=[feature_map_input, roi_input], outputs=out_roi_pool)
# all_roifs = haha.predict([F, ROIs])
# [all_scenefs, P_cls, P_regr] = model_classifier_only.predict([F, ROIs
[P_cls, P_regr] = model_classifier_only.predict([F, ROIs])
for ii in range(P_cls.shape[1]):
if np.max(P_cls[0, ii, :]) < bbox_threshold or 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] = []
# roifs[cls_name] = []
# scenefs[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([
C.rpn_stride * x, C.rpn_stride * y, C.rpn_stride * (x + w),
C.rpn_stride * (y + h)
])
probs[cls_name].append(np.max(P_cls[0, ii, :]))
# roifs[cls_name].append(all_roifs[0, ii, :])
# scenefs[cls_name].append(all_scenefs[0, ii, :])
all_dets = []
for key in bboxes:
bbox = np.array(bboxes[key])
prob = np.array(probs[key])
# roif = np.array(roifs[key])
# scenef = np.array(scenefs[key])
# new_boxes, new_probs, new_roifs, new_scenefs = roi_helpers.nmsf(bbox, prob, roif, scenef, overlap_thresh=0.5)
new_boxes, new_probs = roi_helpers.non_max_suppression_fast(
bbox, np.array(probs[key]), overlap_thresh=0.5)
for jk in range(new_boxes.shape[0]):
(x1, y1, x2, y2) = new_boxes[jk, :]
(real_x1, real_y1, real_x2,
real_y2) = get_real_coordinates(ratio, x1, y1, x2, y2)
all_dets.append(
(key, 100 * new_probs[jk], real_x1, real_x2, real_y1, real_y2))
crops.append([])
crops[len(crops) - 1].append(img_name)
for i in range(len(all_dets)):
cropped = img[all_dets[i][4]:all_dets[i][5],
max(0, all_dets[i][2]):all_dets[i][3]]
# croppath = '/home/comp/e4252392/end2end/crops0317'
# croppath = '/users/sunjingxuan/pycharmprojects/end2end/crops0317_cpu'
croppath = '/users/sunjingxuan/desktop/FYP_demo/flask/end2end/crops_demo'
cropname = os.path.join(
croppath,
str(img_name.split(".")[0].split("/")[-1]) + "_cropped" + str(i) +
".jpg")
cv2.imwrite(cropname, cropped)
# append key, cropname
crops[len(crops) - 1].append((all_dets[i][0], cropname))
print('Elapsed time = {}'.format(time.time() - st))
print(all_dets)
return crops
# anchor box ratios
anchor_box_ratios = [[1, 1], [1, 2], [2, 1]]
num_rois = 32
img_input = Input(shape=input_shape_img)
roi_input = Input(shape=(None, 4))
# 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(anchor_box_scales) * len(anchor_box_ratios)
rpn = nn.rpn(shared_layers, num_anchors)
classifier = nn.classifier(shared_layers, roi_input, num_rois, nb_classes=21, trainable=True)
model_rpn = Model(img_input, rpn[:2])
model_classifier = Model([img_input, roi_input], classifier)
# this is a model that holds both the RPN and the classifier, used to load/save weights for the models
model_all = Model([img_input, roi_input], rpn[:2] + classifier)
optimizer = Adam(lr=1e-5)
optimizer_classifier = Adam(lr=1e-5)
model_rpn.compile(optimizer=optimizer, loss=[losses.rpn_loss_cls(num_anchors), losses.rpn_loss_regr(num_anchors)])
model_classifier.compile(optimizer=optimizer_classifier,
loss=[losses.class_loss_cls, losses.class_loss_regr(21-1)],
metrics={'dense_class_{}'.format(21): 'accuracy'})
model_all.compile(optimizer='sgd', loss='mae')
input_shape_img = (None, None, 3)
input_shape_features = (None, None, num_features)
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)
print('Loading weights from {}'.format(C.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 = []
def Detect_old(movie):
sys.setrecursionlimit(40000)
# parser = OptionParser()
# parser.add_option("-p", "--path", dest="test_path", help="Path to test data.")
# parser.add_option("-n", "--num_rois", dest="num_rois",
# help="Number of ROIs per iteration. Higher means more memory use.", default=32)
# 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("--network", dest="network", help="Base network to use. Supports vgg or resnet50.", default='resnet50')
# (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')
# config_output_filename = options.config_filename
config_output_filename = "config.pickle"
with open(config_output_filename, 'rb') as f_in:
C = pickle.load(f_in)
if C.network == 'resnet50':
import keras_frcnn.resnet as nn
elif C.network == 'vgg':
import keras_frcnn.vgg as nn
# 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
def format_img_size(img, C):
""" formats the image size based on config """
img_min_side = float(C.im_size)
(height, width) = img.shape
if width <= height:
ratio = img_min_side / width
new_height = int(ratio * height)
new_width = int(img_min_side)
else:
ratio = img_min_side / height
new_width = int(ratio * width)
new_height = int(img_min_side)
img = Image.fromarray(img)
img = img.resize((new_width, new_height), Image.ANTIALIAS)
img = np.array(img)
#img = cv2.resize(img, (new_width, new_height), interpolation=cv2.INTER_CUBIC)
return img, ratio
def format_img_channels(img, C):
img = img.astype(np.float32)
img -= np.mean(img.flatten())
img /= np.std(img.flatten())
img = img[:, :, np.newaxis]
img = np.transpose(img, (2, 0, 1))
img = np.expand_dims(img, axis=0)
#""" formats the image channels based on config """
#img = img[:, :, (2, 1, 0)]
#img = img.astype(np.float32)
#img[:, :, 0] -= C.img_channel_mean[0]
#img[:, :, 1] -= C.img_channel_mean[1]
#img[:, :, 2] -= C.img_channel_mean[2]
#img /= C.img_scaling_factor
#img = np.transpose(img, (2, 0, 1))
#img = np.expand_dims(img, axis=0)
return img
def format_img(img, C):
""" formats an image for model prediction based on config """
img, ratio = format_img_size(img, C)
img = format_img_channels(img, C)
return img, ratio
# Method to transform the coordinates of the bounding box to its original size
def get_real_coordinates(ratio, x1, y1, x2, y2):
# real_x1 = int(round(x1 // ratio))
# real_y1 = int(round(y1 // ratio))
# real_x2 = int(round(x2 // ratio))
# real_y2 = int(round(y2 // ratio))
real_x1 = x1 / ratio
real_y1 = y1 / ratio
real_x2 = x2 / ratio
real_y2 = y2 / ratio
return (real_x1, real_y1, real_x2, real_y2)
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.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)
C.num_rois = 32
if C.network == 'resnet50':
num_features = 1024
elif C.network == 'vgg':
num_features = 512
if K.image_dim_ordering() == 'th':
input_shape_img = (3, None, None)
input_shape_features = (num_features, None, None)
else:
input_shape_img = (None, None, 1)
input_shape_features = (None, None, num_features)
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)
print('Loading weights from {}'.format(C.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 = []
classes = {}
bbox_threshold = 0.8
#visualise = True
#for idx, img_name in enumerate(sorted(os.listdir(img_path))):
# if not img_name.lower().endswith(('.bmp', '.jpeg', '.jpg', '.png', '.tif', '.tiff')):
# continue
def AddPosAndRadFromCornerCoords(coords, pnr=None):
(x0, y0, x1, y1) = coords
centre = (np.array([x0 + x1, y0 + y1]) / 2)[np.newaxis, :]
rad = np.array([max(x1 - x0, y1 - y0)]) / 2
if pnr is None:
pnr = positions_and_radii(centre, rad)
else:
pnr.positions = np.concatenate((pnr.positions, centre))
pnr.radii = np.concatenate((pnr.radii, rad))
return pnr
print("---\n---")
rois = []
for idx in range(movie.shape[-1]):
st = time.time()
#_, img = data_augment.augment(n=np.random.randint(low=1, high=5))
img = movie[:, :, idx]
X, ratio = format_img(img, C)
X = np.transpose(X, (0, 2, 3, 1))
# tmp = Image.fromarray((img * 255).astype(np.uint8))
# img = Image.new('RGBA', tmp.size)
# img.paste(tmp)
# del tmp
# draw = ImageDraw.Draw(img)
#img = (img * 255).astype(np.uint8)
#img = cv2.cvtColor(img, cv2.COLOR_GRAY2RGB)
[Y1, Y2, F] = model_rpn.predict(X)
R = roi_helpers.rpn_to_roi(Y1,
Y2,
C,
K.image_dim_ordering(),
overlap_thresh=0.7)
R[:, 2] -= R[:, 0]
R[:, 3] -= R[:, 1]
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.max(P_cls[0, ii, :]) < bbox_threshold or 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([
C.rpn_stride * x, C.rpn_stride * y, C.rpn_stride * (x + w),
C.rpn_stride * (y + h)
])
probs[cls_name].append(np.max(P_cls[0, ii, :]))
#all_dets = []
det = None
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=0.2)
for jk in range(new_boxes.shape[0]):
(x1, y1, x2, y2) = new_boxes[jk, :]
(real_x1, real_y1, real_x2,
real_y2) = get_real_coordinates(ratio, x1, y1, x2, y2)
det = AddPosAndRadFromCornerCoords(
(real_x1, real_y1, real_x2, real_y2), det)
#draw.rectangle(xy=[real_x1, real_y1, real_x2, real_y2], outline='red')
#cv2.rectangle(img,(real_x1, real_y1), (real_x2, real_y2), (int(class_to_color[key][0]), int(class_to_color[key][1]), int(class_to_color[key][2])),2)
#textLabel = '{}: {}'.format(key,int(100*new_probs[jk]))
#all_dets.append((key,100*new_probs[jk]))
#(retval,baseLine) = cv2.getTextSize(textLabel,cv2.FONT_HERSHEY_COMPLEX,1,1)
#textOrg = (real_x1, real_y1-0)
#cv2.rectangle(img, (textOrg[0] - 5, textOrg[1]+baseLine - 5), (textOrg[0]+retval[0] + 5, textOrg[1]-retval[1] - 5), (0, 0, 0), 2)
#cv2.rectangle(img, (textOrg[0] - 5,textOrg[1]+baseLine - 5), (textOrg[0]+retval[0] + 5, textOrg[1]-retval[1] - 5), (255, 255, 255), -1)
#cv2.putText(img, textLabel, textOrg, cv2.FONT_HERSHEY_DUPLEX, 1, (0, 0, 0), 1)
if det is None:
det = positions_and_radii(-1 * np.ones((1, 1)), np.array([-1]))
rois.append(det)
sys.stdout.write("Detecting: {0:.2f}%, Elapsed time/frame = {1:.2f}s".
format(100.0 * (idx + 1) / movie.shape[-1],
time.time() - st) + '\r')
sys.stdout.flush()
print("Detecting: {0:.2f}%, Elapsed time/frame = {1:.2f}s".format(
100.0 * (idx + 1) / movie.shape[-1],
time.time() - st) + '\r')
print("---")
return rois
#print('Elapsed time = {}'.format(time.time() - st))
#print(all_dets)
#cv2.imshow('img', img)
#cv2.waitKey(0)
#cv2.imwrite('./results_imgs/{}.png'.format(idx),img)
#img.save('./results_imgs/{}.png'.format(idx))
def main():
cleanup()
sys.setrecursionlimit(40000)
config_output_filename = 'config.pickle'
with open(config_output_filename, 'r') 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
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()}
print(class_mapping)
class_to_color = {class_mapping[v]: np.random.randint(0, 255, 3) for v in class_mapping}
C.num_rois = 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 = []
classes = {}
bbox_threshold = 0.8
visualise = True
print("Converting video to images..")
convert_to_images()
print("anotating...")
list_files = sorted(get_file_names(img_path), key=lambda var:[int(x) if x.isdigit() else x for x in re.findall(r'[^0-9]|[0-9]+', var)])
for img_name in list_files:
if not img_name.lower().endswith(('.bmp', '.jpeg', '.jpg', '.png', '.tif', '.tiff')):
continue
print(img_name)
st = time.time()
filepath = os.path.join(img_path,img_name)
img = cv2.imread(filepath)
X = format_img(img, C)
img_scaled = np.transpose(X.copy()[0, (2, 1, 0), :, :], (1, 2, 0)).copy()
img_scaled[:, :, 0] += 123.68
img_scaled[:, :, 1] += 116.779
img_scaled[:, :, 2] += 103.939
img_scaled = img_scaled.astype(np.uint8)
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=0.7)
# 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.max(P_cls[0, ii, :]) < bbox_threshold or 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 = []
all_objects = []
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=0.5)
for jk in range(new_boxes.shape[0]):
(x1, y1, x2, y2) = new_boxes[jk,:]
cv2.rectangle(img_scaled,(x1, y1), (x2, y2), class_to_color[key],2)
textLabel = '{}: {}'.format(key,int(100*new_probs[jk]))
all_dets.append((key,100*new_probs[jk]))
all_objects.append((key, 1))
(retval,baseLine) = cv2.getTextSize(textLabel,cv2.FONT_HERSHEY_COMPLEX,1,1)
textOrg = (x1, y1-0)
cv2.rectangle(img_scaled, (textOrg[0] - 5, textOrg[1]+baseLine - 5), (textOrg[0]+retval[0] + 5, textOrg[1]-retval[1] - 5), (0, 0, 0), 2)
cv2.rectangle(img_scaled, (textOrg[0] - 5,textOrg[1]+baseLine - 5), (textOrg[0]+retval[0] + 5, textOrg[1]-retval[1] - 5), (255, 255, 255), -1)
cv2.putText(img_scaled, textLabel, textOrg, cv2.FONT_HERSHEY_DUPLEX, 1, (0, 0, 0), 1)
print('Elapsed time = {}'.format(time.time() - st))
height, width, channels = img_scaled.shape
cv2.rectangle(img_scaled, (0,0), (width, 30), (0, 0, 0), -1)
cv2.putText(img_scaled, "Obj count: " + str(list(accumulate(all_objects))), (5, 19), cv2.FONT_HERSHEY_TRIPLEX, 0.5, (255, 255, 255), 1)
cv2.imwrite(os.path.join(output_path, img_name), img_scaled)
print(all_dets)
print("saving to video..")
save_to_video()
def __init__(self,
config_path: str,
model_path: str,
num_rois: int = 4,
bbox_threshold: int = 0.01,
use_horizontal_flips: bool = False,
use_vertical_flips: bool = False,
rot_90: bool = False):
self.model_path = model_path
self.bbox_threshold = bbox_threshold
with open(config_path, 'rb') as f_in:
self.config = pickle.load(f_in)
self.config.use_horizontal_flips = use_horizontal_flips
self.config.use_vertical_flips = use_vertical_flips
self.config.rot_90 = rot_90
self.num_rois = num_rois
self.class_mapping = self.config.class_mapping
if 'bg' not in self.class_mapping:
self.class_mapping['bg'] = len(self.class_mapping)
self.class_mapping = {v: k for k, v in self.class_mapping.items()}
class_to_color = {
self.class_mapping[v]: np.random.randint(0, 255, 3)
for v in self.class_mapping
}
num_features = 1024
if K.image_dim_ordering() == 'th':
input_shape_img = (3, None, None)
input_shape_features = (num_features, None, None)
else:
input_shape_img = (None, None, 3)
input_shape_features = (None, None, num_features)
img_input = Input(shape=input_shape_img)
roi_input = Input(shape=(self.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(self.config.anchor_box_scales) * len(
self.config.anchor_box_ratios)
rpn_layers = nn.rpn(shared_layers, num_anchors)
classifier = nn.classifier(feature_map_input,
roi_input,
self.num_rois,
nb_classes=len(self.class_mapping),
trainable=True)
self.model_rpn = Model(img_input, rpn_layers)
self.model_classifier_only = Model([feature_map_input, roi_input],
classifier)
self.model_classifier = Model([feature_map_input, roi_input],
classifier)
# LOAD WEIGHTS
self.model_rpn.load_weights(self.model_path, by_name=True)
self.model_classifier.load_weights(self.model_path, by_name=True)
self.model_rpn.compile(optimizer='sgd', loss='mse')
self.model_classifier.compile(optimizer='sgd', loss='mse')
input_shape_img = (None, None, 3)
input_shape_features = (None, None, num_features)
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)
print('Loading weights from {}'.format(C.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 = []
def tf_fit_img(img, C,filename):
K.clear_session()
if C.network == 'resnet50':
import keras_frcnn.resnet as nn
elif C.network == 'vgg':
import keras_frcnn.vgg as nn
if C.network == 'resnet50':
num_features = 1024
elif C.network == 'vgg':
num_features = 512
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.items()}
print(class_mapping)
class_to_color = {class_mapping[v]: np.random.randint(0, 255, 3) for v in class_mapping}
if K.image_dim_ordering() == 'th':
input_shape_img = (3, None, None)
input_shape_features = (num_features, None, None)
else:
input_shape_img = (None, None, 3)
input_shape_features = (None, None, num_features)
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)
print('Loading weights from {}'.format(C.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')
bbox_threshold = 0.8
X, ratio = 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
# print(X)
[Y1, Y2, F] = model_rpn.predict(X)
R = roi_helpers.rpn_to_roi(Y1, Y2, C, K.image_dim_ordering(), overlap_thresh=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.max(P_cls[0, ii, :]) < bbox_threshold or 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([C.rpn_stride*x, C.rpn_stride*y, C.rpn_stride*(x+w), C.rpn_stride*(y+h)])
probs[cls_name].append(np.max(P_cls[0, ii, :]))
all_dets = []
detect_imgs = []
for key in bboxes:
bbox = np.array(bboxes[key])
count = 0
newPic_name = "box_{}.jpg".format(str(filename[:-4]+ str(count)))
count += 1
detect_imgs.append(newPic_name)
original_img = cv2.imread('./static/tmp_pic/'+filename)
height, width, _ = original_img.shape
(resized_width, resized_height) = get_new_img_size(width, height, 300)
resize_img = cv2.resize(original_img, (resized_width, resized_height), interpolation=cv2.INTER_CUBIC)
cv2.imwrite("./static/img/doc/" + filename, resize_img)
new_boxes, new_probs = roi_helpers.non_max_suppression_fast(bbox, np.array(probs[key]), overlap_thresh=0.5)
for jk in range(new_boxes.shape[0]):
(x1, y1, x2, y2) = new_boxes[jk,:]
(real_x1, real_y1, real_x2, real_y2) = get_real_coordinates(ratio, x1, y1, x2, y2)
gt_x1, gt_x2 = real_x1 * (resized_width/width), real_x2 * (resized_width/width)
gt_y1, gt_y2 = real_y1 * (resized_height/height), real_y2 * (resized_height/height)
gt_x1, gt_y1, gt_x2, gt_y2 = int(gt_x1), int(gt_y1), int(gt_x2), int(gt_y2)
color = (0, 255, 0)
result_img = cv2.rectangle(resize_img, (gt_x1, gt_y1), (gt_x2, gt_y2), color, 2)
cv2.imwrite("./static/img/doc/" + newPic_name, result_img)
textLabel = '{}: {}'.format(key,int(100*new_probs[jk]))
all_dets.append((key,100*new_probs[jk]))
(retval,baseLine) = cv2.getTextSize(textLabel,cv2.FONT_HERSHEY_COMPLEX,1,1)
textOrg = (real_x1, real_y1-0)
cv2.rectangle(img, (textOrg[0] - 5, textOrg[1]+baseLine - 5), (textOrg[0]+retval[0] + 5, textOrg[1]-retval[1] - 5), (0, 0, 0), 2)
cv2.rectangle(img, (textOrg[0] - 5,textOrg[1]+baseLine - 5), (textOrg[0]+retval[0] + 5, textOrg[1]-retval[1] - 5), (255, 255, 255), -1)
cv2.putText(img, textLabel, textOrg, cv2.FONT_HERSHEY_DUPLEX, 1, (0, 0, 0), 1)
# print('Elapsed time = {}'.format(time.time() - st))
print(all_dets)
if len(detect_imgs) > 0:
print(detect_imgs[0])
return detect_imgs[0], all_dets
else:
return "Can not detect"
