def encode_label(image, gt_boxes):
target_scores = np.zeros(shape=[45, 60, 9,
2]) # 0: background, 1: foreground, ,
target_bboxes = np.zeros(shape=[45, 60, 9, 4]) # t_x, t_y, t_w, t_h
target_masks = np.zeros(
shape=[45, 60, 9]) # negative_samples: -1, positive_samples: 1
for i in range(45): # y: height
for j in range(60): # x: width
for k in range(9):
center_x = j * grid_width + grid_width * 0.5
center_y = i * grid_height + grid_height * 0.5
xmin = center_x - wandhG[k][0] * 0.5
ymin = center_y - wandhG[k][1] * 0.5
xmax = center_x + wandhG[k][0] * 0.5
ymax = center_y + wandhG[k][1] * 0.5
# print(xmin, ymin, xmax, ymax)
# ignore cross-boundary anchors
if (xmin > -5) & (ymin > -5) & (xmax < (image_width + 5)) & (
ymax < (image_height + 5)):
anchor_boxes = np.array([xmin, ymin, xmax, ymax])
anchor_boxes = np.expand_dims(anchor_boxes, axis=0)
# compute iou between this anchor and all ground-truth boxes in image.
ious = compute_iou(anchor_boxes, gt_boxes)
positive_masks = ious > pos_thresh
negative_masks = ious < neg_thresh
if np.any(positive_masks):
plot_boxes_on_image(image, anchor_boxes, thickness=1)
print("=> encode: %d, %d, %d" % (i, j, k))
cv2.circle(image,
center=(int(0.5 * (xmin + xmax)),
int(0.5 * (ymin + ymax))),
radius=1,
color=[255, 0, 0],
thickness=4)
target_scores[i, j, k, 1] = 1.
target_masks[i, j,
k] = 1 # labeled as a positive sample
# find out which ground-truth box matches this anchor
max_iou_idx = np.argmax(ious)
selected_gt_boxes = gt_boxes[max_iou_idx]
target_bboxes[i, j, k] = compute_regression(
selected_gt_boxes, anchor_boxes[0])
if np.all(negative_masks):
target_scores[i, j, k, 0] = 1.
target_masks[i, j,
k] = -1 # labeled as a negative sample
cv2.circle(image,
center=(int(0.5 * (xmin + xmax)),
int(0.5 * (ymin + ymax))),
radius=1,
color=[0, 0, 0],
thickness=4)
Image.fromarray(image).show()
return target_scores, target_bboxes, target_masks
import os
import cv2
import numpy as np
import tensorflow as tf
from PIL import Image
from rpn import RPNplus
from utils import decode_output, plot_boxes_on_image, nms
synthetic_dataset_path ="./synthetic_dataset/synthetic_dataset"
prediction_result_path = "./prediction"
if not os.path.exists(prediction_result_path): os.mkdir(prediction_result_path)
model = RPNplus()
fake_data = np.ones(shape=[1, 720, 960, 3]).astype(np.float32)
model(fake_data) # initialize model to load weights
model.load_weights("./RPN.h5")
for idx in range(8000, 8200):
image_path = os.path.join(synthetic_dataset_path, "image/%d.jpg" %(idx+1))
raw_image = cv2.imread(image_path)
image_data = np.expand_dims(raw_image / 255., 0)
pred_scores, pred_bboxes = model(image_data)
pred_scores = tf.nn.softmax(pred_scores, axis=-1)
pred_scores, pred_bboxes = decode_output(pred_bboxes, pred_scores, 0.9)
pred_bboxes = nms(pred_bboxes, pred_scores, 0.5)
plot_boxes_on_image(raw_image, pred_bboxes)
save_path = os.path.join(prediction_result_path, str(idx)+".jpg")
print("=> saving prediction results into %s" %save_path)
Image.fromarray(raw_image).save(save_path)
from PIL import Image
from rpn import RPNplus
from utils import compute_iou, plot_boxes_on_image, wandhG, load_gt_boxes, compute_regression
pos_thresh = 0.5
neg_thresh = 0.1
iou_thresh = 0.5
grid_width = grid_height = 16
image_height, image_width = 720, 960
wandhG = np.array(wandhG)
image_path = "/Users/yangyun/synthetic_dataset/image/1.jpg"
gt_boxes = load_gt_boxes("/Users/yangyun/synthetic_dataset/imageAno/1.txt")
raw_image = cv2.imread(image_path)
image_with_gt_boxes = np.copy(raw_image)
plot_boxes_on_image(image_with_gt_boxes, gt_boxes)
Image.fromarray(image_with_gt_boxes).show()
encoded_image = np.copy(raw_image)
target_scores = np.zeros(shape=[45, 60, 9,
2]) # 0: background, 1: foreground, ,
target_bboxes = np.zeros(shape=[45, 60, 9, 4]) # t_x, t_y, t_w, t_h
target_masks = np.zeros(shape=[45, 60,
9]) # negative_samples: -1, positive_samples: 1
################################### ENCODE INPUT #################################
for i in range(45):
for j in range(60):
for k in range(9):
center_x = j * grid_width + grid_width * 0.5
from utils import compute_iou, plot_boxes_on_image, wandhG, load_gt_boxes, compute_regression, decode_output
pos_thresh = 0.5
neg_thresh = 0.1
iou_thresh = 0.5
grid_width = 16
grid_height = 16
image_height = 720
image_width = 960
image_path = "./synthetic_dataset/image/1.jpg"
label_path = "./synthetic_dataset/imageAno/1.txt"
gt_boxes = load_gt_boxes(label_path)
raw_image = cv2.imread(image_path)
image_with_gt_boxes = np.copy(raw_image)
plot_boxes_on_image(image_with_gt_boxes, gt_boxes)
Image.fromarray(image_with_gt_boxes).show()
encoded_image = np.copy(raw_image)
target_scores = np.zeros(shape=[45, 60, 9,
2]) # 0: background, 1: foreground, ,
target_bboxes = np.zeros(shape=[45, 60, 9, 4]) # t_x, t_y, t_w, t_h
target_masks = np.zeros(shape=[45, 60,
9]) # negative_samples: -1, positive_samples: 1
################################### ENCODE INPUT #################################
for i in range(45):
for j in range(60):
for k in range(9):
center_x = j * grid_width + grid_width * 0.5
# selected_boxes = pred_boxes
selected_boxes = []
while len(pred_boxes) > 0:
max_idx = np.argmax(pred_score)
selected_box = pred_boxes[max_idx]
selected_boxes.append(selected_box)
pred_boxes = np.concatenate(
[pred_boxes[:max_idx], pred_boxes[max_idx + 1:]])
pred_score = np.concatenate(
[pred_score[:max_idx], pred_score[max_idx + 1:]])
ious = compute_iou(selected_box, pred_boxes)
iou_mask = ious <= 0.1
pred_boxes = pred_boxes[iou_mask]
pred_score = pred_score[iou_mask]
selected_boxes = np.array(selected_boxes)
plot_boxes_on_image(raw_image, selected_boxes)
Image.fromarray(np.uint8(raw_image)).show()
grid_size = [45, 60]
grid_x = tf.range(grid_size[0], dtype=tf.int32)
grid_y = tf.range(grid_size[1], dtype=tf.int32)
a, b = tf.meshgrid(grid_x, grid_y)
x_offset = tf.reshape(a, (-1, 1))
y_offset = tf.reshape(b, (-1, 1))
xy_offset = tf.concat([x_offset, y_offset], axis=-1)
xy_offset = tf.reshape(x_y_offset, [grid_size[0], grid_size[1], 1, 2])
xy_offset = tf.cast(x_y_offset, tf.float32)
pos_thresh = 0.5
neg_thresh = 0.1
iou_thresh = 0.5
grid_width = 16 # 网格的长宽都是16，因为从原始图片到 feature map 经历了16倍的缩放
grid_height = 16
image_height = 900
image_width = 900
wnum, hnum = math.floor(image_width / grid_width), math.floor(image_height /
grid_height)
image_path = "IMG_1278.jpg"
label_path = "test.txt"
gt_boxes = load_gt_boxes(label_path) # 把 ground truth boxes 的坐标读取出来
raw_image = cv2.imread(image_path) # 将图片读取出来 (高，宽，通道数)
image_with_gt_boxes = np.copy(raw_image) # 复制原始图片
plot_boxes_on_image(image_with_gt_boxes,
gt_boxes) # 将 ground truth boxes 画在图片上
Image.fromarray(image_with_gt_boxes).show() # 展示画了 ground truth boxes 的图片
## 因为得到的 feature map 的长宽都是原始图片的 1/16，所以这里 wnum=720/16，hnum=960/16。
target_scores = np.zeros(shape=[wnum, hnum, 9,
2]) # 0: background, 1: foreground, ,
target_bboxes = np.zeros(shape=[wnum, hnum, 9, 4]) # t_x, t_y, t_w, t_h
target_masks = np.zeros(shape=[wnum, hnum,
9]) # negative_samples: -1, positive_samples: 1
################################### ENCODE INPUT #################################
## 将 feature map 分成 wnum*hnum 个小块
for i in range(wnum):
for j in range(hnum):
for k in range(9):
center_x = j * grid_width + grid_width * 0.5 # 计算此小块的中心点横坐标
center_y = i * grid_height + grid_height * 0.5 # 计算此小块的中心点纵坐标
xmin = center_x - wandhG[k][
