# 无法在OpenMV IDE中导入自己训练的tflite模型

**URL:** <https://forums.openmv.io/t/openmv-ide-tflite/7536>\
**Category:** Chinese 中文\
**Created:** [September 28, 2022, 6:48am UTC](https://forums.openmv.io/t/openmv-ide-tflite/7536 "2022-09-28T06:48:39Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![colinzwang](https://avatars.discourse-cdn.com/v4/letter/c/71e660/32.png) [@colinzwang](https://forums.openmv.io/u/colinzwang)\
**Post date:** [September 28, 2022, 6:48am UTC](https://forums.openmv.io/t/openmv-ide-tflite/7536/1 "2022-09-28T06:48:39Z")

</div>

我用google collab训练了一个tflite模型，但当我试着在OpenMV IDE里导入这个模型时每次都会报错。当我把这个android.tflite换成系统自带的trained.tflite的时候就不会报错。我想知道为什么会导致这个情况。以下是我导入模型时使用的代码。

```auto
try:
    net = tf.load("android.tflite", load_to_fb=uos.stat('android.tflite')[6] > (gc.mem_free() - (64*1024)))
except Exception as e:
    raise Exception('Failed to load "trained.tflite", did you copy the .tflite and labels.txt file onto the mass-storage device? (' + str(e) + ')')
```

---

<div class="post-metadata">

**Author:** ![johnson](https://yyz1.discourse-cdn.com/flex029/user_avatar/forums.openmv.io/johnson/32/2765_2.png) [@johnson](https://forums.openmv.io/u/johnson)\
**Post date:** [March 24, 2023, 12:17pm UTC](https://forums.openmv.io/t/openmv-ide-tflite/7536/2 "2023-03-24T12:17:27Z")

</div>

请问您训练的是图像分类模型还是目标检测模型？openmv目前只支持int8量化的模型，另外我想知道为啥我一导入我自己用tensorflow训练并量化的目标检测tflite模型，openmv就会直接断开连接，我想知道你是怎么量化模型的。谢谢你的回复

---

<div class="post-metadata">

**Author:** ![Eilic](https://avatars.discourse-cdn.com/v4/letter/e/ce7236/32.png) [@Eilic](https://forums.openmv.io/u/Eilic)\
**Post date:** [July 10, 2023, 6:09am UTC](https://forums.openmv.io/t/openmv-ide-tflite/7536/3 "2023-07-10T06:09:51Z")

</div>

我也有这个问题，啊啊啊啊啊，请问你们解决了吗？