Training method, use method, device and processing equipment of posture optimization model
A technology for optimizing models and training methods, applied in character and pattern recognition, instruments, calculations, etc., can solve problems such as poor effect, photographers' shooting level cannot fully understand each other's shooting intentions, and photographers can't provide them, so as to improve the shooting effect Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0029] First, refer to figure 1 An example electronic device 100 for implementing the training method, usage method, device and processing device of the posture optimization model according to the embodiment of the present invention will be described.
[0030] like figure 1 A schematic structural diagram of an electronic device is shown, and the electronic device 100 includes one or more processing devices 102 and one or more storage devices 104 . Optionally, figure 1 The illustrated electronic device 100 may also include an input device 106, an output device 108, and a data acquisition device 110, and these components are interconnected by a bus system 112 and / or other forms of connection mechanisms (not shown). It should be noted that figure 1 The components and structure of the electronic device 100 shown are only exemplary, not limiting, and the electronic device may also have other components and structures as required.
[0031] The processing device 102 may be a gate...
Embodiment 2
[0039] According to an embodiment of the present invention, an embodiment of an action recognition method is provided. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and, although A logical order is shown in the flowcharts, but in some cases the steps shown or described may be performed in an order different from that shown or described herein.
[0040] figure 2 is a flow chart of a training method for a posture optimization model according to an embodiment of the present invention, such as figure 2 As shown, the method includes the following steps:
[0041] Step S202, acquiring training samples. Among them, the training samples include images of objects, initial pose information and pose evaluation information. The object can be a person or other living body, and any object that can receive posture optimization suggestions can be used.
[0042]...
Embodiment 3
[0065] Corresponding to the posture optimization model training method provided in Embodiment 2, the embodiment of the present invention provides a posture optimization model training device, see Figure 4 The structural block diagram of the training device of a kind of posture optimization model shown, comprises:
[0066] The first obtaining module 402 is used to obtain training samples, the training samples include images of objects, initial posture information and posture evaluation information;
[0067] The first determination module 404 is used to determine the pose evaluation loss function and the pose change loss function of the pose optimization model;
[0068] The second determination module 406 is used to determine the total loss function according to the pose evaluation loss function and the pose change loss function;
[0069]The model training module 408 is used to train the pose optimization model by using the initial pose information, images and pose evaluation ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More