Deep learning model processing method and device and electronic equipment
A technology of deep learning and processing methods, applied in neural learning methods, biological neural network models, creating/generating source codes, etc., can solve the problems of cumbersome viewing and modification of neural learning models, lack of editing functions, and lack of editing capabilities
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0097] based on figure 1 The system 10 shown and figure 2 The relevant description of the UI interface 11 shown, such as image 3 As shown, a schematic flowchart of a processing method for a deep learning model provided by an embodiment of the present application, the method includes the following steps:
[0098] Step 301 : The electronic device displays the UI interface 11 in response to the user's opening operation of opening the UI interface 11 .
[0099] The operation in step 301 may be an opening operation for the user to open the application arrangement designer, such as a click operation. It can be understood that the application orchestration designer may be an application program installed in the electronic device, and the operation in step 301 may specifically be a click operation of the user on the application icon of the application orchestration designer displayed on the electronic device, triggering the electronic device to open the application orchestration. ...
Embodiment 2
[0119] According to some embodiments of the present application, the processing method of the deep learning model provided by the present application can open the saved intermediate format file through the above-mentioned application orchestration designer to view the graph of the deep learning model, or the graph of the deep learning model. Make modifications to modify the deep learning model.
[0120] Specifically, as Figure 4 As shown, a schematic flowchart of a method for processing a deep learning model provided by an embodiment of the present application, the method includes the following steps:
[0121] Steps 301 to 305, wherein the specific descriptions of the steps 301 to 305 can be consistent with the descriptions in the foregoing Embodiment 1, and are not repeated here.
[0122] Step 307: In response to the user's operation on the function control 215 of the function selection area 101b in the UI interface 11, the electronic device restores and displays the interm...
Embodiment 3
[0126] In other embodiments, the combination figure 2 ,like Figure 5 As shown, the UI interface 11 also includes a control 213 for supporting the user to customize one or more extension meta nodes, that is, adding one or more nodes to the UI interface 102 of the above-mentioned application orchestration designer to support the user Trigger the electronic device to add a new node.
[0127] Specifically, another method for processing a deep learning model provided in this embodiment of the present application may further include the following step 308 before step 302, step 303 or step 304 in the steps in the foregoing embodiment 1 or embodiment 2 .
[0128] As an example, combining image 3 ,like Image 6 As shown, a schematic flowchart of a method for processing a deep learning model provided by an embodiment of the present application, the method includes the following steps:
[0129] In step 301, the specific description of step 301 can be consistent with the descripti...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com