视觉的一个小bug
Answers checklist.
- [x] I have read the documentation XiaoZhi AI Programming Guide and the issue is not addressed there.
- [x] I have updated my firmware to the latest version and checked that the issue is present there.
- [x] I have searched the issue tracker for a similar issue and not found a similar issue.
XiaoZhi AI firmware version.
1.6.5
Operating System used.
Windows
How did you build your project?
Command line with CMake
If you are using Windows, please specify command line type.
None
Power Supply used.
USB
What is the expected behavior?
I (40602) Application: STATE: listening I (45412) Application: STATE: speaking I (45412) Application: >> 你看下这是什么角色。 I (45652) Application: << 使用工具 self.camera.take_photo... I (46982) EspHttp: Opening HTTP connection to http://api.xiaozhi.me/mcp/vision/explain I (55042) SystemInfo: free sram: 22903 minimal sram: 19679 I (56222) Application: << 哎呀,拍照超时了,没拍成。 I (58722) Esp32Camera: Explain image size=640x480, compressed size=21877, question=这是什么角色? {"success":true,"text":"这张图片中的角色是《火影忍者》中的“晓”组织成员之一——飞段(Hidan)。飞段是晓组织的成员之一,以其不死身和独特的战斗风格著称。他头上标志性的红色“晓”组织图案是其 身份的重要标志之一。飞段的不死身能力使他在战斗中极具威胁,常常以极端和疯狂的方式进行战斗。"} I (59322) Application: << 你能不能描述一下,或者换个角度让我看看? I (62942) Application: STATE: listening
视觉超时时间可能短了点 或者没有处理好一种情况 就是拍照成功了也上传成功了 也解析成功了 但是整个过程超时了, 然后系统播报拍照失败. 没有播报解析内容 但是后台有文字下发
What is the actual behavior?
I (40602) Application: STATE: listening I (45412) Application: STATE: speaking I (45412) Application: >> 你看下这是什么角色。 I (45652) Application: << 使用工具 self.camera.take_photo... I (46982) EspHttp: Opening HTTP connection to http://api.xiaozhi.me/mcp/vision/explain I (55042) SystemInfo: free sram: 22903 minimal sram: 19679 I (56222) Application: << 哎呀,拍照超时了,没拍成。 I (58722) Esp32Camera: Explain image size=640x480, compressed size=21877, question=这是什么角色? {"success":true,"text":"这张图片中的角色是《火影忍者》中的“晓”组织成员之一——飞段(Hidan)。飞段是晓组织的成员之一,以其不死身和独特的战斗风格著称。他头上标志性的红色“晓”组织图案是其 身份的重要标志之一。飞段的不死身能力使他在战斗中极具威胁,常常以极端和疯狂的方式进行战斗。"} I (59322) Application: << 你能不能描述一下,或者换个角度让我看看? I (62942) Application: STATE: listening
视觉超时时间可能短了点 或者没有处理好一种情况 就是拍照成功了也上传成功了 也解析成功了 但是整个过程超时了, 然后系统播报拍照失败. 没有播报解析内容 但是后台有文字下发
Steps to reproduce.
- Step
- Step
- Step ...
Debug Logs.
More Information.
No response
另外 在看视频的时候开着小智 官方服务器 官方客户端, 时间长点会出现卡顿情况, 客户端有警告:
W (813592) MQTT: Received audio packet with wrong sequence: 2195, expected: 2194 W (813882) MQTT: Received audio packet with wrong sequence: 2200, expected: 2199 W (814132) MQTT: Received audio packet with wrong sequence: 2204, expected: 2203 W (814662) MQTT: Received audio packet with wrong sequence: 2213, expected: 2210 W (815202) MQTT: Received audio packet with wrong sequence: 2222, expected: 2221 W (815322) MQTT: Received audio packet with wrong sequence: 2224, expected: 2223 W (815742) MQTT: Received audio packet with wrong sequence: 2233, expected: 2232 W (816042) MQTT: Received audio packet with wrong sequence: 2236, expected: 2235 W (816172) MQTT: Received audio packet with wrong sequence: 2239, expected: 2238 W (816172) MQTT: Received audio packet with wrong sequence: 2241, expected: 2240 W (816232) MQTT: Received audio packet with wrong sequence: 2244, expected: 2243 W (816652) MQTT: Received audio packet with wrong sequence: 2249, expected: 2245 W (817242) MQTT: Received audio packet with wrong sequence: 2256, expected: 2251 W (817362) MQTT: Received audio packet with wrong sequence: 2258, expected: 2257 W (817482) MQTT: Received audio packet with wrong sequence: 2262, expected: 2261 I (817492) Application: << 可以根据不同需求进行调整。 W (817782) MQTT: Received audio packet with wrong sequence: 2265, expected: 2264 W (817962) MQTT: Received audio packet with wrong sequence: 2268, expected: 2267 W (818262) MQTT: Received audio packet with wrong sequence: 2273, expected: 2272 W (818382) MQTT: Received audio packet with wrong sequence: 2275, expected: 2274 W (818632) MQTT: Received audio packet with wrong sequence: 2281, expected: 2278 W (818742) MQTT: Received audio packet with wrong sequence: 2283, expected: 2282 W (818932) MQTT: Received audio packet with wrong sequence: 2286, expected: 2285 W (818982) MQTT: Received audio packet with wrong sequence: 2290, expected: 2289 W (819402) MQTT: Received audio packet with wrong sequence: 2292, expected: 2291 W (819472) MQTT: Received audio packet with wrong sequence: 2298, expected: 2297 W (820182) MQTT: Received audio packet with wrong sequence: 2307, expected: 2305 I (820192) Application: << 这样灵活性挺高的,能满足更多用户的需求。 W (820732) MQTT: Received audio packet with wrong sequence: 2319, expected: 2311 W (821142) MQTT: Received audio packet with wrong sequence: 2321, expected: 2320 W (821262) MQTT: Received audio packet with wrong sequence: 2323, expected: 2322 W (821562) MQTT: Received audio packet with wrong sequence: 2328, expected: 2324 W (821632) MQTT: Received audio packet with wrong sequence: 2331, expected: 2329 W (821862) MQTT: Received audio packet with wrong sequence: 2333, expected: 2332 I (822042) SystemInfo: free sram: 27139 minimal sram: 19679 W (822172) MQTT: Received audio packet with wrong sequence: 2338, expected: 2334 W (822402) MQTT: Received audio packet with wrong sequence: 2342, expected: 2339 W (822532) MQTT: Received audio packet with wrong sequence: 2346, expected: 2343 W (822942) MQTT: Received audio packet with wrong sequence: 2351, expected: 2349 W (823012) MQTT: Received audio packet with wrong sequence: 2354, expected: 2353 W (823012) MQTT: Received audio packet with wrong sequence: 2356, expected: 2355 W (823422) MQTT: Received audio packet with wrong sequence: 2359, expected: 2357 W (823602) MQTT: Received audio packet with wrong sequence: 2362, expected: 2360 W (823722) MQTT: Received audio packet with wrong sequence: 2364, expected: 2363 W (824022) MQTT: Received audio packet with wrong sequence: 2369, expected: 2365 W (824142) MQTT: Received audio packet with wrong sequence: 2372, expected: 2371 I (824142) Application: << 你对这些了解得真透彻。 I (826722) Application: << 还有啥想聊的吗? W (827562) MQTT: Received audio packet with wrong sequence: 2433, expected: 2432 W (828162) MQTT: Received audio packet with wrong sequence: 2438, expected: 2437
可以更新到新版本。