def detect(model_name, weight_path, input_size, image_path):
assert model_name in ['yolov3_tiny']
NUM_CLASS = len(utils.read_class_names(cfg.YOLO.CLASSES))
STRIDES = np.array(cfg.YOLO.STRIDES_TINY)
ANCHORS = utils.get_anchors(cfg.YOLO.ANCHORS_TINY, tiny=True)
original_image = cv2.imread(image_path)
original_image = cv2.cvtColor(original_image, cv2.COLOR_BGR2RGB)
original_image_size = original_image.shape[:2]
image_data = utils.image_preprocess(np.copy(original_image),
[input_size, input_size])
image_data = image_data[np.newaxis, ...].astype(np.float32)
input_layer = tf.keras.layers.Input([input_size, input_size, 3])
if model_name == 'yolov3_tiny':
feature_maps = YOLOv3_tiny(input_layer, NUM_CLASS)
bbox_tensors = []
for i, fm in enumerate(feature_maps):
bbox_tensor = ops.decode(fm, NUM_CLASS)
bbox_tensors.append(bbox_tensor)
model = tf.keras.Model(input_layer, bbox_tensors)
else:
raise ValueError
if weight_path:
if model_name == 'yolov3_tiny':
weight = np.load(weight_path, allow_pickle=True)
model.set_weights(weight)
else:
raise ValueError
print('Restoring weights from: %s ' % weight_path)
# model.summary()
start_time = time.time()
pred_bbox = model.predict(image_data)
print(time.time() - start_time)
pred_bbox = utils.postprocess_bbbox(pred_bbox, ANCHORS, STRIDES)
bboxes = utils.postprocess_boxes(pred_bbox, original_image_size,
input_size, 0.5)
bboxes = utils.nms(bboxes, 0.3, method='nms')
image = visualize.draw_bbox(original_image,
bboxes,
classes=utils.read_class_names(
cfg.YOLO.CLASSES))
image = Image.fromarray(image)
image.show()
def detect_tflite(model_name, weight_path, input_size, image_path):
assert model_name in ['yolov3_tiny']
STRIDES = np.array(cfg.YOLO.STRIDES_TINY)
ANCHORS = utils.get_anchors(cfg.YOLO.ANCHORS_TINY, True)
original_image = cv2.imread(image_path)
original_image = cv2.cvtColor(original_image, cv2.COLOR_BGR2RGB)
original_image_size = original_image.shape[:2]
image_data = utils.image_preprocess(np.copy(original_image),
[input_size, input_size])
image_data = image_data[np.newaxis, ...].astype(np.float32)
# Load TFLite model and allocate tensors.
interpreter = tf.lite.Interpreter(model_path=weight_path)
interpreter.allocate_tensors()
# Get input and output tensors.
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()
print(input_details)
print(output_details)
interpreter.set_tensor(input_details[0]['index'], image_data)
start_time = time.time()
interpreter.invoke()
pred_bbox = [
interpreter.get_tensor(output_details[i]['index'])
for i in range(len(output_details))
]
print(time.time() - start_time)
pred_bbox = utils.postprocess_bbbox(pred_bbox, ANCHORS, STRIDES)
bboxes = utils.postprocess_boxes(pred_bbox, original_image_size,
input_size, 0.5)
bboxes = utils.nms(bboxes, 0.3, method='nms')
image = visualize.draw_bbox(original_image,
bboxes,
classes=utils.read_class_names(
cfg.YOLO.CLASSES))
image = Image.fromarray(image)
image.show()
def detect(image_path, weight_path, input_size):
STRIDES = np.array(cfg.YOLO.STRIDES)
ANCHORS = utils.get_anchors(cfg.YOLO.ANCHORS, tiny=False)
original_image = cv2.imread(image_path)
original_image = cv2.cvtColor(original_image, cv2.COLOR_BGR2RGB)
original_image_size = original_image.shape[:2]
image_data = utils.image_preprocess(np.copy(original_image),
[input_size, input_size])
image_data = image_data[np.newaxis, ...].astype(np.float32)
NUM_CLASS = len(utils.read_class_names(cfg.YOLO.CLASSES))
input_layer = tf.keras.layers.Input([input_size, input_size, 3])
feature_maps = YOLOv3(input_layer, NUM_CLASS)
bbox_tensors = []
for i, fm in enumerate(feature_maps):
bbox_tensor = ops.decode(fm, NUM_CLASS)
bbox_tensors.append(bbox_tensor)
model = tf.keras.Model(input_layer, bbox_tensors)
if weight_path:
weight = np.load(weight_path, allow_pickle=True)
model.set_weights(weight)
print('Restoring weights from: %s ' % weight_path)
pred_bbox = model.predict(image_data)
pred_bbox = utils.postprocess_bbbox(pred_bbox, ANCHORS, STRIDES)
bboxes = utils.postprocess_boxes(pred_bbox, original_image_size,
input_size, 0.25)
bboxes = utils.nms(bboxes, 0.2, method='nms')
image = visualize.draw_bbox(original_image,
bboxes,
classes=utils.read_class_names(
cfg.YOLO.CLASSES))
image = Image.fromarray(image)
image.show()
def detect(model_name, weight_path, input_size, image_path, framework):
assert model_name in ['yolov3_tiny', 'yolov3', 'yolov4']
if model_name == 'yolov3_tiny':
STRIDES = np.array(cfg.YOLO.STRIDES_TINY)
ANCHORS = utils.get_anchors(cfg.YOLO.ANCHORS_TINY, True)
elif model_name == 'yolov3':
STRIDES = np.array(cfg.YOLO.STRIDES)
ANCHORS = utils.get_anchors(cfg.YOLO.ANCHORS_V3, False)
elif model_name == 'yolov4':
STRIDES = np.array(cfg.YOLO.STRIDES)
ANCHORS = utils.get_anchors(cfg.YOLO.ANCHORS, False)
else:
raise ValueError
NUM_CLASS = len(utils.read_class_names(cfg.YOLO.CLASSES))
XYSCALE = cfg.YOLO.XYSCALE
original_image = cv2.imread(image_path)
original_image = cv2.cvtColor(original_image, cv2.COLOR_BGR2RGB)
original_image_size = original_image.shape[:2]
image_data = utils.image_preprocess(np.copy(original_image),
[input_size, input_size])
image_data = image_data[np.newaxis, ...].astype(np.float32)
if framework == 'tf':
input_layer = tf.keras.layers.Input([input_size, input_size, 3])
if model_name == 'yolov3_tiny':
feature_maps = YOLOv3_tiny(input_layer, NUM_CLASS)
bbox_tensors = []
for i, fm in enumerate(feature_maps):
bbox_tensor = ops.decode(fm, NUM_CLASS)
bbox_tensors.append(bbox_tensor)
model = tf.keras.Model(input_layer, bbox_tensors)
elif model_name == 'yolov3':
feature_maps = YOLOv3(input_layer, NUM_CLASS)
bbox_tensors = []
for i, fm in enumerate(feature_maps):
bbox_tensor = ops.decode(fm, NUM_CLASS)
bbox_tensors.append(bbox_tensor)
model = tf.keras.Model(input_layer, bbox_tensors)
elif model_name == 'yolov4':
feature_maps = YOLOv4(input_layer, NUM_CLASS)
bbox_tensors = []
for i, fm in enumerate(feature_maps):
bbox_tensor = ops.decode(fm, NUM_CLASS)
bbox_tensors.append(bbox_tensor)
model = tf.keras.Model(input_layer, bbox_tensors)
else:
model = None
raise ValueError
if weight_path.split(".")[-1] == "weights":
if model_name == 'yolov3_tiny':
utils.load_weights_tiny(model, weight_path)
# utils.extract_weights_tiny(model, weight_path)
print('load yolo tiny 3')
elif model_name == 'yolov3':
utils.load_weights_v3(model, weight_path)
print('load yolo 3')
elif model_name == 'yolov4':
utils.load_weights(model, weight_path)
print('load yolo 4')
else:
raise ValueError
elif weight_path.split(".")[-1] == "npy":
if model_name == 'yolov3_tiny':
# utils.load_weights_tiny_npy(model, weight_path)
print('load yolo tiny 3 npy')
else:
model.load_weights(weight_path)
print('Restoring weights from: %s ' % weight_path)
# weight = np.load('D:\\coursera\\YoLoSerirs\\checkpoint\\yolo3_tiny.npy', allow_pickle=True)
# model.set_weights(weight)
# model.summary()
start_time = time.time()
pred_bbox = model.predict(image_data)
print(time.time() - start_time)
else:
# Load TFLite model and allocate tensors.
interpreter = tf.lite.Interpreter(model_path=weight_path)
interpreter.allocate_tensors()
# Get input and output tensors.
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()
print(input_details)
print(output_details)
interpreter.set_tensor(input_details[0]['index'], image_data)
start_time = time.time()
interpreter.invoke()
pred_bbox = [
interpreter.get_tensor(output_details[i]['index'])
for i in range(len(output_details))
]
print(time.time() - start_time)
if model_name == 'yolov4':
pred_bbox = utils.postprocess_bbbox(pred_bbox, ANCHORS, STRIDES,
XYSCALE)
else:
pred_bbox = utils.postprocess_bbbox(pred_bbox, ANCHORS, STRIDES)
bboxes = utils.postprocess_boxes(pred_bbox, original_image_size,
input_size, 0.5)
bboxes = utils.nms(bboxes, 0.3, method='nms')
image = visualize.draw_bbox(original_image, bboxes)
image = Image.fromarray(image)
image.show()
import numpy as np
from Utils import visualize
import matplotlib.pyplot as plt
import os
data_dir = 'D:\\DataSet\\coco_val2017\\val2017'
with open('D:\\coursera\\YoLoSerirs\\data\\val2017.txt', 'r') as f:
data = f.readlines()
inds = np.random.randint(0, len(data), 20)
for ind in inds:
img_data = data[ind].split(' ')
path = img_data[0]
image_path = os.path.join(data_dir, path.split('/')[-1])
if os.path.exists(image_path) == False:
raise ValueError
bboxes = []
for line in img_data[1:]:
x1, y1, x2, y2, label = line.split(',')
bboxes.append([int(x1), int(y1), int(x2), int(y2), 1.0, int(label)])
labels = label
bboxes = np.array(bboxes)
original_image = cv2.imread(image_path)
original_image = cv2.cvtColor(original_image, cv2.COLOR_BGR2RGB)
img = visualize.draw_bbox(original_image, bboxes)
plt.imshow(img)
plt.show()
def video_fps(model_name, weight_path, input_size, framework):
assert model_name in ['yolov3_tiny']
STRIDES = np.array(cfg.YOLO.STRIDES_TINY)
ANCHORS = utils.get_anchors(cfg.YOLO.ANCHORS_TINY, True)
XYSCALE = [1.0, 1.0, 1.0]
classes = utils.read_class_names(cfg.YOLO.CLASSES)
if framework == 'tf':
model = load_model(model_name, weight_path, input_size)
else:
model, input_details, output_details = load_model_lite(weight_path)
video_path = 'D:\\coursera\\YoLoSerirs\\dataset\\test.mp4'
vcapture = cv2.VideoCapture(video_path)
width = int(vcapture.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(vcapture.get(cv2.CAP_PROP_FRAME_HEIGHT))
fps = vcapture.get(cv2.CAP_PROP_FPS)
fourcc = cv2.VideoWriter_fourcc('m', 'p', '4', 'v')
start = time.time()
count = 0
success = True
while success:
success, image = vcapture.read()
if success:
original_image = image
original_image = cv2.cvtColor(original_image, cv2.COLOR_BGR2RGB)
original_image_size = original_image.shape[:2]
image_data = utils.image_preprocess(np.copy(original_image),
[input_size, input_size])
image_data = image_data[np.newaxis, ...].astype(np.float32)
if framework == 'tf':
pred_bbox = model.predict(image_data)
else:
model.set_tensor(input_details[0]['index'], image_data)
model.invoke()
pred_bbox = [
model.get_tensor(output_details[i]['index'])
for i in range(len(output_details))
]
pred_bbox = utils.postprocess_bbbox(pred_bbox, ANCHORS, STRIDES,
XYSCALE)
bboxes = utils.postprocess_boxes(pred_bbox, original_image_size,
input_size, 0.6)
bboxes = utils.nms(bboxes, 0.2, method='nms')
image = visualize.draw_bbox(original_image,
bboxes,
classes=classes)
image = image[:, :, [2, 1, 0]]
cv2.imshow('cap video', image)
# plt.imshow(image)
# plt.show()
if cv2.waitKey(40) & 0xFF == ord('q'):
break
count += 1
print("FPS of the video is {:5.2f}".format(
(time.time() - start) / count))
def video_fps(model_name, weight_path, input_size, framework):
assert model_name in ['yolov3_tiny', 'yolov3', 'yolov4']
if model_name == 'yolov3_tiny':
STRIDES = np.array(cfg.YOLO.STRIDES_TINY)
ANCHORS = utils.get_anchors(cfg.YOLO.ANCHORS_TINY, True)
elif model_name == 'yolov3':
STRIDES = np.array(cfg.YOLO.STRIDES)
ANCHORS = utils.get_anchors(cfg.YOLO.ANCHORS_V3, False)
elif model_name == 'yolov4':
STRIDES = np.array(cfg.YOLO.STRIDES)
ANCHORS = utils.get_anchors(cfg.YOLO.ANCHORS, False)
else:
raise ValueError
if model_name == 'yolov4':
XYSCALE = cfg.YOLO.XYSCALE
else:
XYSCALE = [1.0, 1.0, 1.0]
model = load_model(model_name, weight_path, input_size, framework)
video_path = 'D:\\coursera\\YoLoSerirs\\dataset\\test.mp4'
vcapture = cv2.VideoCapture(video_path)
width = int(vcapture.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(vcapture.get(cv2.CAP_PROP_FRAME_HEIGHT))
fps = vcapture.get(cv2.CAP_PROP_FPS)
fourcc = cv2.VideoWriter_fourcc('m', 'p', '4', 'v')
start = time.time()
count = 0
success = True
while success:
success, image = vcapture.read()
if success:
original_image = image
original_image = cv2.cvtColor(original_image, cv2.COLOR_BGR2RGB)
original_image_size = original_image.shape[:2]
image_data = utils.image_preprocess(np.copy(original_image),
[input_size, input_size])
image_data = image_data[np.newaxis, ...].astype(np.float32)
pred_bbox = model.predict(image_data)
pred_bbox = utils.postprocess_bbbox(pred_bbox, ANCHORS, STRIDES,
XYSCALE)
bboxes = utils.postprocess_boxes(pred_bbox, original_image_size,
input_size, 0.5)
bboxes = utils.nms(bboxes, 0.3, method='nms')
image = visualize.draw_bbox(original_image, bboxes)
image = image[:, :, [2, 1, 0]]
cv2.imshow('cap video', image)
# plt.imshow(image)
# plt.show()
if cv2.waitKey(40) & 0xFF == ord('q'):
break
count += 1
print("FPS of the video is {:5.2f}".format(
(time.time() - start) / count))