TFlite (一）yolov4 / yolov4-tiny 模型转化
环境：
- python 3.6.8
依赖：
- tensorflow-gpu 2.3.0rc0
- opencv-python 4.1.1.26
- lxml
- tqdm
- absl-py
- matplotlib
- easydict
- pillow
步骤：
Weights ---> TF ---> TFlite
一、下载模型与参数
- yolov4.weights:下载
- yolov4.cfg:下载
- yolov4-tiny.weights:下载
- yolov4-tiny.cfg:下载
二、WEIGHTS 转 TF
import tensorflow as tf
from absl import app, flags, logging
from absl.flags import FLAGS
from core.yolov4 import YOLO, decode, filter_boxes
import core.utils as utils
# from core.config import cfg
flags.DEFINE_string('weights', './weights/yolov4-tiny.weights', 'path to weights file')
flags.DEFINE_string('output', './checkpoints/yolov4-tiny-416.tflite', 'path to output')
flags.DEFINE_boolean('tiny', True, 'is yolo-tiny or not')
flags.DEFINE_integer('input_size', 416, 'define input size of export model')
flags.DEFINE_float('score_thres', 0.2, 'define score threshold')
flags.DEFINE_string('framework', 'tflite', 'define what framework do you want to convert (tf, trt, tflite)')
flags.DEFINE_string('model', 'yolov4', 'yolov3 or yolov4')
def save_tf():
STRIDES, ANCHORS, NUM_CLASS, XYSCALE = utils.load_config(FLAGS)
input_layer = tf.keras.layers.Input([FLAGS.input_size, FLAGS.input_size, 3])
feature_maps = YOLO(input_layer, NUM_CLASS, FLAGS.model, FLAGS.tiny)
bbox_tensors = []
prob_tensors = []
if FLAGS.tiny:
for i, fm in enumerate(feature_maps):
if i == 0:
output_tensors = decode(fm, FLAGS.input_size // 16, NUM_CLASS, STRIDES, ANCHORS, i, XYSCALE, FLAGS.framework)
else:
output_tensors = decode(fm, FLAGS.input_size // 32, NUM_CLASS, STRIDES, ANCHORS, i, XYSCALE, FLAGS.framework)
bbox_tensors.append(output_tensors[0])
prob_tensors.append(output_tensors[1])
else:
for i, fm in enumerate(feature_maps):
if i == 0:
output_tensors = decode(fm, FLAGS.input_size // 8, NUM_CLASS, STRIDES, ANCHORS, i, XYSCALE, FLAGS.framework)
elif i == 1:
output_tensors = decode(fm, FLAGS.input_size // 16, NUM_CLASS, STRIDES, ANCHORS, i, XYSCALE, FLAGS.framework)
else:
output_tensors = decode(fm, FLAGS.input_size // 32, NUM_CLASS, STRIDES, ANCHORS, i, XYSCALE, FLAGS.framework)
bbox_tensors.append(output_tensors[0])
prob_tensors.append(output_tensors[1])
pred_bbox = tf.concat(bbox_tensors, axis=1)
pred_prob = tf.concat(prob_tensors, axis=1)
if FLAGS.framework == 'tflite':
pred = (pred_bbox, pred_prob)
else:
boxes, pred_conf = filter_boxes(pred_bbox, pred_prob, score_threshold=FLAGS.score_thres, input_shape=tf.constant([FLAGS.input_size, FLAGS.input_size]))
pred = tf.concat([boxes, pred_conf], axis=-1)
model = tf.keras.Model(input_layer, pred)
utils.load_weights(model, FLAGS.weights, FLAGS.model, FLAGS.tiny)
model.summary()
model.save(FLAGS.output)
def main(_argv):
save_tf()
if __name__ == '__main__':
try:
app.run(main)
except SystemExit:
pass
三、TF 转 TFlite
import tensorflow as tf
from absl import app, flags, logging
from absl.flags import FLAGS
import numpy as np
import cv2
from core.yolov4 import YOLOv4, YOLOv3, YOLOv3_tiny,YOLOv4_tiny, decode
import core.utils as utils
import os
from core.config import cfg
flags.DEFINE_string('weights', './checkpoints/yolov4-tiny-416.tflite', 'path to weights file')
flags.DEFINE_string('output', './checkpoints/yolov4-416-fp32.tflite', 'path to output')
flags.DEFINE_integer('input_size', 416, 'path to output')
flags.DEFINE_string('quantize_mode', 'float32', 'quantize mode (int8, float16, float32)')
flags.DEFINE_string('dataset', "/Volumes/Elements/data/coco_dataset/coco/5k.txt", 'path to dataset')
def representative_data_gen():
fimage = open(FLAGS.dataset).read().split()
for input_value in range(10):
if os.path.exists(fimage[input_value]):
original_image=cv2.imread(fimage[input_value])
original_image = cv2.cvtColor(original_image, cv2.COLOR_BGR2RGB)
image_data = utils.image_preprocess(np.copy(original_image), [FLAGS.input_size, FLAGS.input_size])
img_in = image_data[np.newaxis, ...].astype(np.float32)
print("calibration image {}".format(fimage[input_value]))
yield [img_in]
else:
continue
def save_tflite():
converter = tf.lite.TFLiteConverter.from_saved_model(FLAGS.weights)
if FLAGS.quantize_mode == 'float16':
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.target_spec.supported_types = [tf.compat.v1.lite.constants.FLOAT16]
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS]
converter.allow_custom_ops = True
elif FLAGS.quantize_mode == 'int8':
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS, tf.lite.OpsSet.SELECT_TF_OPS]
converter.allow_custom_ops = True
converter.representative_dataset = representative_data_gen
tflite_model = converter.convert()
open(FLAGS.output, 'wb').write(tflite_model)
logging.info("model saved to: {}".format(FLAGS.output))
def demo():
interpreter = tf.lite.Interpreter(model_path=FLAGS.output)
interpreter.allocate_tensors()
logging.info('tflite model loaded')
input_details = interpreter.get_input_details()
print(input_details)
output_details = interpreter.get_output_details()
print(output_details)
input_shape = input_details[0]['shape']
input_data = np.array(np.random.random_sample(input_shape), dtype=np.float32)
interpreter.set_tensor(input_details[0]['index'], input_data)
interpreter.invoke()
output_data = [interpreter.get_tensor(output_details[i]['index']) for i in range(len(output_details))]
print(output_data)
def main(_argv):
save_tflite()
demo()
if __name__ == '__main__':
try:
app.run(main)
except SystemExit:
pass
四、测试
import time
import tensorflow as tf
physical_devices = tf.config.experimental.list_physical_devices('GPU')
if len(physical_devices) > 0:
tf.config.experimental.set_memory_growth(physical_devices[0], True)
from absl import app, flags, logging
from absl.flags import FLAGS
import core.utils as utils
from core.yolov4 import filter_boxes
from tensorflow.python.saved_model import tag_constants
from PIL import Image
import cv2
import numpy as np
from tensorflow.compat.v1 import ConfigProto
from tensorflow.compat.v1 import InteractiveSession
flags.DEFINE_string('framework', 'tflite', '(tf, tflite, trt')
flags.DEFINE_string('weights', './checkpoints/yolov4-416-fp32.tflite',
'path to weights file')
flags.DEFINE_integer('size', 416, 'resize images to')
flags.DEFINE_boolean('tiny', False, 'yolo or yolo-tiny')
flags.DEFINE_string('model', 'yolov4', 'yolov3 or yolov4')
flags.DEFINE_string('video', './t1.mp4', 'path to input video')
flags.DEFINE_float('iou', 0.45, 'iou threshold')
flags.DEFINE_float('score', 0.25, 'score threshold')
def main(_argv):
config = ConfigProto()
config.gpu_options.allow_growth = True
session = InteractiveSession(config=config)
STRIDES, ANCHORS, NUM_CLASS, XYSCALE = utils.load_config(FLAGS)
input_size = FLAGS.size
video_path = FLAGS.video
print("Video from: ", video_path )
vid = cv2.VideoCapture(video_path)
if FLAGS.framework == 'tflite':
interpreter = tf.lite.Interpreter(model_path=FLAGS.weights)
interpreter.allocate_tensors()
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()
print(input_details)
print(output_details)
else:
saved_model_loaded = tf.saved_model.load(FLAGS.weights, tags=[tag_constants.SERVING])
infer = saved_model_loaded.signatures['serving_default']
while True:
return_value, frame = vid.read()
if return_value:
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
image = Image.fromarray(frame)
else:
raise ValueError("No image! Try with another video format")
frame_size = frame.shape[:2]
image_data = cv2.resize(frame, (input_size, input_size))
image_data = image_data / 255.
image_data = image_data[np.newaxis, ...].astype(np.float32)
prev_time = time.time()
if FLAGS.framework == 'tflite':
interpreter.set_tensor(input_details[0]['index'], image_data)
interpreter.invoke()
pred = [interpreter.get_tensor(output_details[i]['index']) for i in range(len(output_details))]
if FLAGS.model == 'yolov3' and FLAGS.tiny == True:
boxes, pred_conf = filter_boxes(pred[1], pred[0], score_threshold=0.25,
input_shape=tf.constant([input_size, input_size]))
else:
boxes, pred_conf = filter_boxes(pred[0], pred[1], score_threshold=0.25,
input_shape=tf.constant([input_size, input_size]))
else:
batch_data = tf.constant(image_data)
pred_bbox = infer(batch_data)
for key, value in pred_bbox.items():
boxes = value[:, :, 0:4]
pred_conf = value[:, :, 4:]
boxes, scores, classes, valid_detections = tf.image.combined_non_max_suppression(
boxes=tf.reshape(boxes, (tf.shape(boxes)[0], -1, 1, 4)),
scores=tf.reshape(
pred_conf, (tf.shape(pred_conf)[0], -1, tf.shape(pred_conf)[-1])),
max_output_size_per_class=50,
max_total_size=50,
iou_threshold=FLAGS.iou,
score_threshold=FLAGS.score
)
pred_bbox = [boxes.numpy(), scores.numpy(), classes.numpy(), valid_detections.numpy()]
image = utils.draw_bbox(frame, pred_bbox)
curr_time = time.time()
exec_time = curr_time - prev_time
result = np.asarray(image)
info = "time: %.2f ms" %(1000*exec_time)
print(info)
cv2.namedWindow("result", cv2.WINDOW_AUTOSIZE)
result = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
cv2.imshow("result", result)
if cv2.waitKey(1) & 0xFF == ord('q'): break
if __name__ == '__main__':
try:
app.run(main)
except SystemExit:
pass
其他模块代码：下载