duplicate ff_hex_to_data() function from avformat and rename it to
hex_to_data() as static function.
Reviewed-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Limin Wang <lance.lmwang@gmail.com>
Different function type of model requires different parameters, for
example, object detection detects lots of objects (cat/dog/...) in
the frame, and classifcation needs to know which object (cat or dog)
it is going to classify.
The current interface needs to add a new function with more parameters
to support new requirement, with this change, we can just add a new
struct (for example DNNExecClassifyParams) based on DNNExecBaseParams,
and so we can continue to use the current interface execute_model just
with params changed.
There's one task item for one function call from dnn interface,
there's one request item for one call to openvino. For classify,
one task might need multiple inference for classification on every
bounding box, so add InferenceItem.
please use tools/python/tf_sess_config.py to get the sess_config after that.
note the byte order of session config is in normal order.
bump the MICRO version for the config change.
Signed-off-by: Limin Wang <lance.lmwang@gmail.com>
It can't; these are just remnants of commit
3c7cad69f2 which let the worker threads
do the reallocation.
Reviewed-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>
If an error happens when preparing the output data buffer, an already
allocated array would leak. Fix this by postponing its allocation.
Fixes Coverity issue #1473531.
Reviewed-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>
Also fixes a memleak in single-threaded mode when an error happens
in preparing the output data buffer; and also removes an unchecked
allocation.
Reviewed-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>
asserts should not be used instead of ordinary input checks.
Yet the native DNN backend did it: get_input_native() asserted that
the first dimension was one, despite this value coming directly from
the input file without having been sanitized.
Reviewed-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>
So the backend knows the usage of model is for frame processing,
detect, classify, etc. Each function type has different behavior
in backend when handling the input/output data of the model.
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
once we mark done for the task in function infer_completion_callback,
the task is possible to be release in function ff_dnn_get_async_result_ov
in another thread just after it, so we need to record request queue
first, instead of using task->ov_model->request_queue later.
Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Limin Wang
Ting Fu
Guo, Yejun
Shubhanshu Saxena
Wenlong Ding
Andreas Rheinhardt
Mark Thompson