def predict_single_image(img_path, model_rpn, model_classifier_only,
class_mapping):
img = cv2.imread(img_path)
if img is None:
print('reading image failed.')
exit(0)
X, ratio = format_img(img)
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)
result = rpn_to_roi(Y1, Y2, K.image_dim_ordering(), overlap_thresh=0.7)
# convert from (x1,y1,x2,y2) to (x,y,w,h)
result[:, 2] -= result[:, 0]
result[:, 3] -= result[:, 1]
bbox_threshold = 0.7
# apply the spatial pyramid pooling to the proposed regions
boxes = dict()
for jk in range(result.shape[0] // 32 + 1):
rois = np.expand_dims(result[32 * jk:32 * (jk + 1), :], axis=0)
if rois.shape[1] == 0:
break
if jk == result.shape[0] // 32:
# pad R
curr_shape = rois.shape
target_shape = (curr_shape[0], 32, 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_num = np.argmax(p_cls[0, ii, :])
if cls_num not in boxes.keys():
boxes[cls_num] = []
(x, y, w, h) = rois[0, ii, :]
try:
(tx, ty, tw, th) = p_regr[0, ii, 4 * cls_num:4 * (cls_num + 1)]
tx /= 8.0
ty /= 8.0
tw /= 4.0
th /= 4.0
x, y, w, h = apply_regr(x, y, w, h, tx, ty, tw, th)
except Exception as e:
print(e)
pass
boxes[cls_num].append([
16 * x, 16 * y, 16 * (x + w), 16 * (y + h),
np.max(p_cls[0, ii, :])
])
# add some nms to reduce many boxes
for cls_num, box in boxes.items():
boxes_nms = non_max_suppression_fast(box, overlap_thresh=0.5)
boxes[cls_num] = boxes_nms
#print(class_mapping[cls_num] + ":")
for b in boxes_nms:
b[0], b[1], b[2], b[3] = get_real_coordinates(
ratio, b[0], b[1], b[2], b[3])
f.write(",".join([
img_path.split("/")[-1].split(".")[0], class_mapping[cls_num],
str(b[-1]),
str(b[0]),
str(b[1]),
str(b[2]),
str(b[3])
]) + "\n")
img = draw_boxes_and_label_on_image_cv2(img, class_mapping, boxes)
result_path = './resnet_aug_results_images/{}.jpg'.format(
os.path.basename(img_path).split('.')[0])
cv2.imwrite(result_path, img)
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)
R = roi_helpers.rpn_to_roi(P_rpn[0],
P_rpn[1],
C,
K.image_dim_ordering(),
use_regr=True,
overlap_thresh=0.7,
max_boxes=300)
# note: calc_iou converts from (x1,y1,x2,y2) to (x,y,w,h) format
X2, Y1, Y2 = roi_helpers.calc_iou(R, img_data, C,
class_mapping)
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 = []
def detect_predict(pic,
C,
model_rpn,
model_classifier,
model_classifier_only,
class_mapping,
class_to_color,
print_dets=False):
"""
Detect and predict object in the picture
:param pic: picture numpy array
:param C: config object
:params model_*: models from get_models function
:params class_*: mapping and colors, need to be loaded to keep the same colors/classes
:return: picture with bounding boxes
"""
img = pic
X, ratio = 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 = {}
# print(class_mapping)
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=overlap_thresh)
jk = np.argmax(new_probs)
if new_probs[jk] > 0.55:
(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)
# To avoid putting text outside the frame
# replace the legende if the box is outside the image
if real_y1 < 20 and real_y2 < img.shape[0]:
textOrg = (real_x1, real_y2 + 5)
elif real_y1 < 20 and real_y2 > img.shape[0]:
textOrg = (real_x1, img.shape[0] - 10)
else:
textOrg = (real_x1, real_y1 + 5)
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 print_dets:
print(all_dets)
return img
print(img_name)
st = time.time()
filepath = os.path.join(test_base_path, img_name)
img = cv2.imread(filepath)
X, ratio = format_img(img, C)
X = np.transpose(X, (0, 2, 3, 1))
# Getting feature-maps F & output layer Y1, Y2 from RPN
[Y1, Y2, F] = model_rpn.predict(X)
# Getting boxes by applying NMS -> R.shape = (300, 4)
R = roi_helpers.rpn_to_roi(Y1, Y2, C, K.image_dim_ordering(), overlap_thresh = 0.7)
# Conversion from (x1,x2,y1,y2) to (x,y,w,h)
R[:, 2] -= R[:, 0]
R[:, 3] -= R[:, 1]
# Spatial pyramid pooling to 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:
def train():
num_rois = 32
epochs = 250
model = "model_trained/frcnn_resnet.hdf5"
ground_truth = "MIO-TCD-Localization/gt_train.csv"
pretrained_model = "model/resnet50_weights_tf_dim_ordering_tf_kernels.h5"
# load filenames and class mappings
images, label_dict = parse_data(ground_truth)
map1 = parse_mapping(ground_truth)
# shuffle the data
shuffle(images)
# create train and validation data split
train_data = []
val_data = []
# randomly choosing train and test
for image in images:
if np.random.randint(0, 6) == 0:
val_data.append(image)
else:
train_data.append(image)
print("Num train samples", len(train_data))
print("Num val samples", len(val_data))
data_gen_train = get_anchor_gt(train_data,
label_dict,
rn.get_img_output_length,
K.image_dim_ordering(),
mode='train')
data_gen_val = get_anchor_gt(val_data,
label_dict,
rn.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
shared_layers = rn.nn_base(img_input, trainable=True)
# define the RPN using the base layers
num_anchors = 3 * 3 # 3 for number of scales and 3 number of aspect ratios
rpn = rn.rpn(shared_layers, num_anchors)
classifier = rn.classifier(shared_layers,
roi_input,
num_rois,
nb_classes=len(label_dict),
trainable=True)
model_rpn = Model(img_input, rpn[:2])
model_classifier = Model([img_input, roi_input], classifier)
# this model holds both the RPN and the classifier
model_all = Model([img_input, roi_input], rpn[:2] + classifier)
print("Loading pretrained weights from", pretrained_model)
model_rpn.load_weights(pretrained_model, by_name=True)
model_classifier.load_weights(pretrained_model, by_name=True)
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(label_dict) - 1)
],
metrics={'dense_class_{}'.format(len(label_dict)): 'accuracy'})
model_all.compile(optimizer='sgd', loss='mae')
epoch_length = 250
losses = np.zeros((epoch_length, 5))
best_loss = np.inf
iteration = 0
for epoch in range(epochs):
print("Epoch ", epoch + 1)
# Training on Train Dataset
X, Y, img_data = next(data_gen_train)
P_rpn = model_rpn.predict_on_batch(X)
result = rpn_to_roi(P_rpn[0], P_rpn[1], K.image_dim_ordering(), True,
0.7, 300)
X2, Y1, Y2, IouS = calc_iou(result, img_data, map1)
pos_samples = np.where(Y1[0, :, -1] == 0)
if len(pos_samples) == 0:
pos_samples = []
else:
pos_samples = pos_samples[0]
neg_samples = np.where(Y1[0, :, -1] == 1)
if len(neg_samples) == 0:
neg_samples = []
else:
neg_samples = neg_samples[0]
if num_rois > 1:
if len(pos_samples) < num_rois // 2:
selected_pos_samples = pos_samples.tolist()
else:
selected_pos_samples = np.random.choice(
pos_samples, num_rois // 2, replace=False).tolist()
try:
selected_neg_samples = np.random.choice(
neg_samples,
num_rois - len(selected_pos_samples),
replace=False).tolist()
except:
selected_neg_samples = np.random.choice(
neg_samples,
num_rois - len(selected_pos_samples),
replace=True).tolist()
sel_samples = selected_pos_samples + selected_neg_samples
else:
if np.random.randint(0, 2) == 0:
sel_samples = choice(pos_samples)
else:
sel_samples = choice(neg_samples)
model_classifier.train_on_batch(
[X, X2[:, sel_samples, :]],
[Y1[:, sel_samples, :], Y2[:, sel_samples, :]])
# Testing on Validation Dataset
X, Y, img_data = next(data_gen_val)
P_rpn = model_rpn.predict_on_batch(X)
result = rpn_to_roi(P_rpn[0], P_rpn[1], K.image_dim_ordering(), True,
0.7, 300)
X2, Y1, Y2, IouS = calc_iou(result, img_data, map1)
pos_samples = np.where(Y1[0, :, -1] == 0)
if len(pos_samples) == 0:
pos_samples = []
else:
pos_samples = pos_samples[0]
neg_samples = np.where(Y1[0, :, -1] == 1)
if len(neg_samples) == 0:
neg_samples = []
else:
neg_samples = neg_samples[0]
if num_rois > 1:
if len(pos_samples) < num_rois // 2:
selected_pos_samples = pos_samples.tolist()
else:
selected_pos_samples = np.random.choice(
pos_samples, num_rois // 2, replace=False).tolist()
try:
selected_neg_samples = np.random.choice(
neg_samples,
num_rois - len(selected_pos_samples),
replace=False).tolist()
except:
selected_neg_samples = np.random.choice(
neg_samples,
num_rois - len(selected_pos_samples),
replace=True).tolist()
sel_samples = selected_pos_samples + selected_neg_samples
else:
if np.random.randint(0, 2):
sel_samples = choice(neg_samples)
else:
sel_samples = choice(pos_samples)
loss_class = model_classifier.test_on_batch(
[X, X2[:, sel_samples, :]],
[Y1[:, sel_samples, :], Y2[:, sel_samples, :]])
losses[iteration, 2] = loss_class[1]
losses[iteration, 3] = loss_class[2]
losses[iteration, 4] = loss_class[3]
if iteration == epoch_length * (epoch + 1):
rpn_cls_loss = np.mean(losses[:, 0])
rpn_regr_loss = np.mean(losses[:, 1])
class_cls_loss = np.mean(losses[:, 2])
class_regr_loss = np.mean(losses[:, 3])
class_acc = np.mean(losses[:, 4])
print("Classifier accuracy for bounding boxes from RPN:",
class_acc)
print("Loss RPN classifier:", rpn_cls_loss)
print("Loss RPN regression:", rpn_regr_loss)
print("Loss Detector classifier:", class_cls_loss)
print("Loss Detector regression:", class_regr_loss)
total_loss = rpn_cls_loss + rpn_regr_loss + class_cls_loss + class_regr_loss
if total_loss < best_loss:
best_loss = total_loss
model_all.save_weights(model)
iteration += 1
