def test_hook():
# init hook
hook = ExampleHook()
hook1 = ExampleHook(overwrite=True)
hook2 = IgnoreHook(size=(0.5, 0.5), overwrite=True)
frame_home = os.path.join(PROJECT_PATH, 'frame_save_dir')
hook3 = FrameSaveHook(frame_home)
hook4 = CropHook(
size=(0.5, 0.5),
offset=(0., 0.5),
overwrite=True,
)
hook5 = RefineHook()
hook6 = InvalidFrameDetectHook()
hook7 = TemplateCompareHook({
'amazon': IMAGE_PATH,
})
# --- cutter ---
cutter = VideoCutter(compress_rate=0.8)
# add hook
cutter.add_hook(hook)
cutter.add_hook(hook1)
cutter.add_hook(hook2)
cutter.add_hook(hook3)
cutter.add_hook(hook4)
cutter.add_hook(hook5)
cutter.add_hook(hook6)
cutter.add_hook(hook7)
res = cutter.cut(VIDEO_PATH)
stable, unstable = res.get_range()
assert len(stable) == 2, 'count of stable range is not correct'
data_home = res.pick_and_save(
stable,
5,
)
assert os.path.isdir(data_home), 'result dir not existed'
# --- classify ---
cl = SVMClassifier()
cl.load(data_home)
cl.train()
classify_result = cl.classify(VIDEO_PATH, stable)
# --- draw ---
r = Reporter()
report_path = os.path.join(data_home, 'report.html')
r.draw(
classify_result,
report_path=report_path,
cut_result=res,
)
assert os.path.isfile(report_path)
# hook check
assert os.path.isdir(frame_home)
assert hook6.result
assert hook7.result
def test_default():
# --- classify ---
cl = SVMClassifier()
cl.load(CUTTER_RESULT_DIR)
cl.train()
cl.save_model(MODEL_PATH, overwrite=True)
cl.classify(VIDEO_PATH, boost_mode=False)
def _classify(
video: typing.Union[str, VideoObject],
data_home: str = None,
model: str = None,
# optional: these args below are sent for `cutter`
compress_rate: float = 0.2,
target_size: typing.Tuple[int, int] = None,
limit_range: typing.List[VideoCutRange] = None,
) -> ClassifierResult:
"""
classify a video with some tagged pictures
optional: if you have changed the default value in `cut`, you'd better keep them(offset and limit) equal.
:param video: video path or object
:param data_home: output path (dir)
:param model: LinearSVC model (path)
:param compress_rate: before_pic * compress_rate = after_pic. default to 0.2
:param target_size: (100, 200)
:param limit_range:
:return: typing.List[ClassifierResult]
"""
if isinstance(video, str):
video = VideoObject(video)
assert data_home or model, "classification should based on dataset or trained model"
cl = SVMClassifier(compress_rate=compress_rate, target_size=target_size)
if model:
cl.load_model(model)
else:
cl.load(data_home)
cl.train()
return cl.classify(video, limit_range=limit_range)
def classify(self,
video_path: str,
data_home: str,
output_path: str = None,
compress_rate: float = 0.2,
limit: int = None):
# TODO model?
cut_result_json = os.path.join(data_home, 'cut_result.json')
res = None
stable = None
if os.path.isfile(cut_result_json):
res = VideoCutResult.load(cut_result_json)
stable, _ = res.get_range(limit=limit)
cl = SVMClassifier(compress_rate=compress_rate)
cl.load(data_home)
cl.train()
classify_result = cl.classify(video_path, stable)
# --- draw ---
r = Reporter()
r.add_dir_link(data_home)
r.draw(
classify_result,
report_path=os.path.join(output_path or data_home, 'report.html'),
cut_result=res,
)
def one_step(self,
video_path: str,
output_path: str = None,
threshold: float = 0.95,
frame_count: int = 5,
compress_rate: float = 0.2,
offset: int = 3,
limit: int = None):
"""
one step => cut, classifier, draw
:param video_path: your video path
:param output_path: output path (dir)
:param threshold: float, 0-1, default to 0.95. decided whether a range is stable. larger => more unstable ranges
:param frame_count: default to 5, and finally you will get 5 frames for each range
:param compress_rate: before_pic * compress_rate = after_pic. default to 0.2
:param offset:
it will change the way to decided whether two ranges can be merged
before: first_range.end == second_range.start
after: first_range.end + offset >= secord_range.start
:param limit: ignore some ranges which are too short, 5 means ignore stable ranges which length < 5
:return:
"""
# --- cutter ---
cutter = VideoCutter()
res = cutter.cut(video_path, compress_rate=compress_rate)
stable, unstable = res.get_range(
threshold=threshold,
limit=limit,
offset=offset,
)
data_home = res.pick_and_save(stable, frame_count, to_dir=output_path)
res_json_path = os.path.join(data_home, 'cut_result.json')
res.dump(res_json_path)
# --- classify ---
cl = SVMClassifier(compress_rate=compress_rate)
cl.load(data_home)
cl.train()
classify_result = cl.classify(video_path, stable)
# --- draw ---
r = Reporter()
r.draw(
classify_result,
report_path=os.path.join(data_home, 'report.html'),
cut_result=res,
# kwargs of get_range
# otherwise these thumbnails may become different
threshold=threshold,
limit=limit,
offset=offset,
)
def test_default():
# --- classify ---
cl = SVMClassifier()
cl.load(CUTTER_RESULT_DIR)
cl.train()
cl.save_model(MODEL_PATH, overwrite=True)
classify_result = cl.classify(VIDEO_PATH)
# --- draw ---
_draw_report(classify_result)
def test_hook():
# init hook
hook = ExampleHook()
hook1 = ExampleHook()
hook2 = IgnoreHook(size=(0.5, 0.5))
frame_home = os.path.join(PROJECT_PATH, "frame_save_dir")
hook3 = FrameSaveHook(frame_home)
hook4 = CropHook(size=(0.5, 0.5), offset=(0.0, 0.5))
hook5 = RefineHook()
hook6 = InterestPointHook()
hook7 = TemplateCompareHook({"amazon": IMAGE_PATH})
# --- cutter ---
cutter = VideoCutter(compress_rate=0.9)
# add hook
cutter.add_hook(hook)
cutter.add_hook(hook1)
cutter.add_hook(hook2)
cutter.add_hook(hook3)
cutter.add_hook(hook4)
cutter.add_hook(hook5)
cutter.add_hook(hook6)
cutter.add_hook(hook7)
res = cutter.cut(VIDEO_PATH)
stable, unstable = res.get_range()
assert len(stable) == 2, "count of stable range is not correct"
data_home = res.pick_and_save(stable, 5)
assert os.path.isdir(data_home), "result dir not existed"
# --- classify ---
cl = SVMClassifier()
cl.load(data_home)
cl.train()
classify_result = cl.classify(VIDEO_PATH, stable)
# --- draw ---
r = Reporter()
report_path = os.path.join(data_home, "report.html")
r.draw(classify_result, report_path=report_path, cut_result=res)
assert os.path.isfile(report_path)
# hook check
assert os.path.isdir(frame_home)
assert hook6.result
assert hook7.result
def one_step(self,
video_path: str,
output_path: str = None,
threshold: float = 0.95,
frame_count: int = 5,
compress_rate: float = 0.2,
limit: int = None):
"""
one step => cut, classifier, draw
:param video_path: your video path
:param output_path: output path (dir)
:param threshold: float, 0-1, default to 0.95. decided whether a range is stable. larger => more unstable ranges
:param frame_count: default to 5, and finally you will get 5 frames for each range
:param compress_rate: before_pic * compress_rate = after_pic. default to 0.2
:param limit: ignore some ranges which are too short, 5 means ignore stable ranges which length < 5
:return:
"""
# --- cutter ---
cutter = VideoCutter()
res = cutter.cut(video_path, compress_rate=compress_rate)
stable, unstable = res.get_range(
threshold=threshold,
limit=limit,
)
data_home = res.pick_and_save(stable, frame_count, to_dir=output_path)
res_json_path = os.path.join(data_home, 'cut_result.json')
res.dump(res_json_path)
# --- classify ---
cl = SVMClassifier(compress_rate=compress_rate)
cl.load(data_home)
cl.train()
classify_result = cl.classify(video_path, stable)
# --- draw ---
r = Reporter()
r.add_dir_link(data_home)
r.draw(
classify_result,
report_path=os.path.join(data_home, 'report.html'),
cut_result=res,
)
def classify(
video: typing.Union[str, VideoObject],
data_home: str = None,
model: str = None,
# optional: these args below are sent for `cutter`
compress_rate: float = 0.2,
target_size: typing.Tuple[int, int] = None,
offset: int = 3,
limit: int = None,
threshold: float = 0.95,
) -> ClassifierResult:
"""
classify a video with some tagged pictures
optional: if you have changed the default value in `cut`, you'd better keep them(offset and limit) equal.
:param video: video path or object
:param data_home: output path (dir)
:param model: LinearSVC model (path)
:param compress_rate: before_pic * compress_rate = after_pic. default to 0.2
:param target_size: (100, 200)
:param offset:
it will change the way to decided whether two ranges can be merged
before: first_range.end == second_range.start
after: first_range.end + offset >= secord_range.start
:param limit: ignore some ranges which are too short, 5 means ignore stable ranges which length < 5
:param threshold: cutter threshold
:return: typing.List[ClassifierResult]
"""
if isinstance(video, str):
video = VideoObject(video)
assert data_home or model, "classification should based on dataset or trained model"
cl = SVMClassifier(compress_rate=compress_rate, target_size=target_size)
if model:
cl.load_model(model)
else:
cl.load(data_home)
cl.train()
# re cut
cut_result, _ = cut(video, compress_rate=compress_rate, threshold=threshold)
stable, _ = cut_result.get_range(offset=offset, limit=limit)
return cl.classify(video, stable)
def _train(
data_home: str,
save_to: str,
compress_rate: float = 0.2,
target_size: typing.Tuple[int, int] = None,
):
"""
build a trained model with a dataset
:param data_home: output path (dir)
:param save_to: model will be saved to this path
:param compress_rate: before_pic * compress_rate = after_pic. default to 0.2
:param target_size: (100, 200)
"""
assert os.path.isdir(data_home), f"dir {data_home} not existed"
assert not os.path.isfile(save_to), f"file {save_to} already existed"
cl = SVMClassifier(compress_rate=compress_rate, target_size=target_size)
cl.load(data_home)
cl.train()
cl.save_model(save_to)
def train_model_SVM(_train_picture_path, _model_file_name):
cl = SVMClassifier(
# 默认情况下使用 HoG 进行特征提取
# 你可以将其关闭从而直接对原始图片进行训练与测试：feature_type='raw'
feature_type="hog",
# 默认为0.2，即将图片缩放为0.2倍
# 主要为了提高计算效率
# 如果你担心影响分析效果，可以将其提高
compress_rate=0.2,
# 或者直接指定尺寸
# 当压缩率与指定尺寸同时传入时，优先以指定尺寸为准
# target_size=(200, 400),
)
# 加载待训练数据
cl.load(_train_picture_path)
# 在加载数据完成之后需要先训练
cl.train()
cl.save_model(_model_file_name, overwrite=True)
return cl
def analyse(
video: typing.Union[str, VideoObject],
output_path: str,
pre_load: bool = True,
threshold: float = 0.98,
offset: int = 3,
boost_mode: bool = True,
):
""" designed for https://github.com/williamfzc/stagesepx/issues/123 """
if isinstance(video, str):
video = VideoObject(video, pre_load=pre_load)
cutter = VideoCutter()
res = cutter.cut(video)
stable, unstable = res.get_range(
threshold=threshold,
offset=offset,
)
with tempfile.TemporaryDirectory() as temp_dir:
res.pick_and_save(
stable,
5,
to_dir=temp_dir,
)
cl = SVMClassifier()
cl.load(temp_dir)
cl.train()
classify_result = cl.classify(video, stable, boost_mode=boost_mode)
r = Reporter()
r.draw(
classify_result,
report_path=output_path,
unstable_ranges=unstable,
cut_result=res,
)
def handle(self, video_path: str) -> bool:
super(NormalHandler, self).handle(video_path)
video = VideoObject(video_path)
if self.preload:
video.load_frames()
# --- cutter ---
cutter = VideoCutter()
res = cutter.cut(video)
stable, unstable = res.get_range(threshold=0.98, offset=3)
data_home = res.pick_and_save(stable,
self.frame_count,
to_dir=self.result_path)
# --- classify ---
cl = SVMClassifier()
cl.load(data_home)
cl.train()
self.classifier_result = cl.classify(video, stable)
# --- draw ---
r = Reporter()
r.draw(self.classifier_result, report_path=self.result_report_path)
return True
# 检查最后一个阶段中是否包含图片 person.png
# 这种做法会在阶段中间取一帧进行模板匹配
# 当然，这种做法并不常用，最常用还是用于检测最终结果而不是中间量
# 值得注意，这里的模板匹配会受到压缩率的影响
# 虽然已经做了分辨率拟合，但是如果压缩率过高，依旧会出现图像难以辨认而导致的误判
# 正常来说没什么问题
match_result = stable[-1].contain_image(amazon_image_path,
engine_template_scale=(0.5, 2, 5))
print(match_result)
# 分别输出：最可能存在的坐标、相似度、计算是否正常完成
# {'target_point': [550, 915], 'target_sim': 0.9867244362831116, 'ok': True}
data_home = res.pick_and_save(stable, 5)
cl = SVMClassifier()
cl.load(data_home)
cl.train()
classify_result = cl.classify(video_path, stable, keep_data=True)
result_dict = classify_result.to_dict()
final_result: dict = {}
for each_stage, each_frame_list in result_dict.items():
# 你可以通过对这些阶段进行目标检测，以确认他们符合你的预期
# 注意，如阶段名称为负数，意味着这个阶段是处在变化中，非稳定
# 例如，检测每一个阶段的中间帧是否包含特定图片
middle_id: int = int((len(each_frame_list) - 1) / 2)
# 分别检测 amazon.png 与 phone.png （这两张是手动选出来的标志物）
amazon_image_res = each_frame_list[middle_id].contain_image(
image_path=amazon_image_path,
# 模板匹配依赖了 findit
def run(config: typing.Union[dict, str]):
"""
run with config
:param config: config file path, or a preload dict
:return:
"""
class _VideoUserConfig(BaseModel):
path: str
pre_load: bool = True
fps: int = None
class _CutterUserConfig(BaseModel):
threshold: float = None
frame_count: int = None
offset: int = None
limit: int = None
block: int = None
# common
compress_rate: float = None
target_size: typing.Tuple[int, int] = None
class _ClassifierType(Enum):
SVM = "svm"
KERAS = "keras"
class _ClassifierUserConfig(BaseModel):
boost_mode: bool = None
classifier_type: _ClassifierType = _ClassifierType.SVM
model: str = None
# common
compress_rate: float = None
target_size: typing.Tuple[int, int] = None
class _CalcOperatorType(Enum):
BETWEEN = "between"
DISPLAY = "display"
class _CalcOperator(BaseModel):
name: str
calc_type: _CalcOperatorType
args: dict = dict()
class _CalcUserConfig(BaseModel):
output: str = None
ignore_error: bool = None
operators: typing.List[_CalcOperator] = None
class _ExtraUserConfig(BaseModel):
save_train_set: str = None
class UserConfig(BaseModel):
output: str
video: _VideoUserConfig
cutter: _CutterUserConfig = _CutterUserConfig()
classifier: _ClassifierUserConfig = _ClassifierUserConfig()
calc: _CalcUserConfig = _CalcUserConfig()
extras: _ExtraUserConfig = _ExtraUserConfig()
if isinstance(config, str):
# path
config_path = pathlib.Path(config)
assert config_path.is_file(), f"no config file found in {config_path}"
# todo: support different types in the future
assert config_path.as_posix().endswith(
".json"), "config file should be json format"
with open(config_path, encoding=constants.CHARSET) as f:
config = json.load(f)
config = UserConfig(**config)
logger.info(f"config: {config}")
# main flow
video = VideoObject(
# fmt: off
path=config.video.path,
fps=config.video.fps,
)
if config.video.pre_load:
video.load_frames()
# cut
cutter = VideoCutter(
# fmt: off
compress_rate=config.cutter.compress_rate,
target_size=config.cutter.target_size,
)
res = cutter.cut(
# fmt: off
video=video,
block=config.cutter.block,
)
stable, unstable = res.get_range(
# fmt: off
threshold=config.cutter.threshold,
offset=config.cutter.offset,
)
with tempfile.TemporaryDirectory() as temp_dir:
# classify
if config.classifier.classifier_type is _ClassifierType.SVM:
cl = SVMClassifier(
# fmt: off
compress_rate=config.classifier.compress_rate,
target_size=config.classifier.target_size,
)
elif config.classifier.classifier_type is _ClassifierType.KERAS:
from stagesepx.classifier.keras import KerasClassifier
cl = KerasClassifier(
# fmt: off
compress_rate=config.classifier.compress_rate,
target_size=config.classifier.target_size,
)
# validation has been applied by pydantic
# so no `else`
if config.classifier.model:
# no need to retrain
model_path = pathlib.Path(config.classifier.model)
assert model_path.is_file(), f"file {model_path} not existed"
cl.load_model(model_path)
else:
# train a new model
train_set_dir = config.extras.save_train_set or temp_dir
os.makedirs(train_set_dir, exist_ok=True)
res.pick_and_save(
# fmt: off
stable,
frame_count=config.cutter.frame_count,
to_dir=train_set_dir,
)
cl.train(data_path=train_set_dir)
# start classifying
classify_result = cl.classify(
# fmt: off
video,
stable,
boost_mode=config.classifier.boost_mode,
)
# calc
def _calc_display() -> dict:
# jsonify
return json.loads(classify_result.dumps())
def _calc_between(*, from_stage: str = None, to_stage: str = None) -> dict:
assert classify_result.contain(
from_stage), f"no stage {from_stage} found in result"
assert classify_result.contain(
to_stage), f"no stage {to_stage} found in result"
from_frame = classify_result.last(from_stage)
to_frame = classify_result.first(to_stage)
cost = to_frame.timestamp - from_frame.timestamp
return {
"from": from_frame.frame_id,
"to": to_frame.frame_id,
"cost": cost,
}
_calc_func_dict = {
_CalcOperatorType.BETWEEN: _calc_between,
_CalcOperatorType.DISPLAY: _calc_display,
}
calc_output = config.calc.output
if calc_output:
output_path = pathlib.Path(calc_output)
assert not output_path.is_file(), f"file {output_path} already existed"
result = []
for each_calc in config.calc.operators:
func = _calc_func_dict[each_calc.calc_type]
try:
func_ret = func(**each_calc.args)
except Exception as e:
if not config.calc.ignore_error:
raise
logger.warning(e)
func_ret = traceback.format_exc()
calc_ret = {
"name": each_calc.name,
"type": each_calc.calc_type.value,
"result": func_ret,
}
result.append(calc_ret)
with open(output_path, "w", encoding=constants.CHARSET) as f:
json.dump(result, f)
# draw
r = Reporter()
r.draw(
# fmt: off
classify_result,
report_path=config.output,
)
