RRepoGEO

REPOGEO REPORT · LITE

FengQuanLi/ResnetGPT

Default branch master · commit 59818064 · scanned 5/26/2026, 8:38:16 PM

GitHub: 2,973 stars · 749 forks

AI VISIBILITY SCORE
23 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 0 warn · 1 fail
Objective metadata checks
AI knows your name
2 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface FengQuanLi/ResnetGPT, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Reposition README to clarify game AI purpose and deprecation status

    Why:

    CURRENT
    # 基于pytorch框架用resnet101加GPT搭建AI玩王者荣耀
   本源码模型主要用了SamLynnEvans Transformer 的源码的解码部分。以及pytorch自带的预训练模型"resnet101-5d3b4d8f.pth"
# 注意！！！ 
本项目不再更新,由用强化学习训练AI玩王者代替。
    COPY-PASTE FIX
    # 基于pytorch框架用resnet101加GPT搭建AI玩王者荣耀

**⚠️ IMPORTANT: This project is no longer updated.** It has been superseded by a reinforcement learning approach for training AI to play Honor of Kings. 

This repository explores an experimental method for creating an AI agent to play the mobile game Honor of Kings (王者荣耀) using a combination of ResNet101 for visual processing and a GPT-like architecture for decision-making, built on the PyTorch framework. It primarily utilizes the decoding part of SamLynnEvans Transformer and PyTorch's pre-trained ResNet101 model.
  • hightopics#2
    Add relevant topics for game AI and deep learning

    Why:

    CURRENT
    (none)
    COPY-PASTE FIX
    pytorch, resnet, gpt, game-ai, mobile-game-automation, honor-of-kings, android-automation, deep-learning, computer-vision
  • highlicense#3
    Add a LICENSE file to clarify usage rights

    Why:

    CURRENT
    (no LICENSE file detected — the repo has no recognizable license)
    COPY-PASTE FIX
    Create a LICENSE file (e.g., MIT or Apache-2.0) in the repository root, or explicitly state the intended license(s) in the README if a custom license is preferred.

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface FengQuanLi/ResnetGPT
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Appium
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. Appium · recommended 2×
  2. OpenCV · recommended 2×
  3. ADB · recommended 1×
  4. scrcpy · recommended 1×
  5. LabelImg · recommended 1×
  • CATEGORY QUERY
    How to build an AI agent for controlling mobile games using deep learning?
    you: not recommended
    AI recommended (in order):
    1. Appium
    2. OpenCV
    3. ADB
    4. scrcpy
    5. LabelImg
    6. VGG Image Annotator (VIA)
    7. TensorFlow
    8. PyTorch
    9. Keras
    10. ResNet
    11. Inception
    12. EfficientNet
    13. RNNs
    14. LSTMs
    15. Transformers
    16. Deep Q-Networks (DQN)
    17. Proximal Policy Optimization (PPO)
    18. Advantage Actor-Critic (A2C)
    19. Python
    20. ONNX
    21. TensorFlow Lite
    22. PyTorch Mobile

    AI recommended 22 alternatives but never named FengQuanLi/ResnetGPT. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What frameworks exist for creating vision-based AI to automate Android game interactions?
    you: not recommended
    AI recommended (in order):
    1. OpenCV
    2. Appium
    3. SikuliX
    4. UI Automator
    5. ADB (Android Debug Bridge)
    6. Airtest Project

    AI recommended 6 alternatives but never named FengQuanLi/ResnetGPT. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    fail

    Suggestion:

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of FengQuanLi/ResnetGPT?
    pass
    AI did not name FengQuanLi/ResnetGPT — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts FengQuanLi/ResnetGPT in production, what risks or prerequisites should they evaluate first?
    pass
    AI named FengQuanLi/ResnetGPT explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo FengQuanLi/ResnetGPT solve, and who is the primary audience?
    pass
    AI named FengQuanLi/ResnetGPT explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of FengQuanLi/ResnetGPT. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/FengQuanLi/ResnetGPT.svg)](https://repogeo.com/en/r/FengQuanLi/ResnetGPT)
HTML
<a href="https://repogeo.com/en/r/FengQuanLi/ResnetGPT"><img src="https://repogeo.com/badge/FengQuanLi/ResnetGPT.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

FengQuanLi/ResnetGPT — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite