@FrozenGene I tried your TFLite tutorial. The compilation failed (it started to
happen after PR 3141.) Details:
https://discuss.tvm.ai/t/tflite-an-internal-invariant-was-violated-while-typechecking-your-program/2784/3
--
You are receiving this because you are subscribed to this thread.
Reply
I tried to compile `mobilenet_v1_1.0_224.tflite` model for ARM Mali GPU using
the latest code from the tutorial. The compilation failed -
`topi/arm_cpu/conv2d.py _decl_spatial_pack Only support NCHW`
--
You are receiving this because you are subscribed to this thread.
Reply to this email direc
The same issue exist with arm_cpu, e.g. `tvm.target.arm_cpu('rk3399')`
```
File
"/usr/local/lib/python3.5/dist-packages/topi-0.6.dev0-py3.5.egg/topi/arm_cpu/conv2d.py",
line 76, in conv2d_arm_cpu
num_tile=2)
File
"/usr/local/lib/python3.5/dist-packages/topi-0.6.dev0-py3.5.egg/topi/arm_cp
After `NCHW` support was removed from `tflite.py` 3 weeks ago #3141 all TFLite
models can not be compiled for ARM cpu and Mali GPU.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/issues/2351#issu
Hi Ramana
REDUCE_MAX op was recently added to tflite frontend.
Are your models open-sourced? Can we download the models?
---
[Visit Topic](https://discuss.tvm.ai/t/missing-tflite-operators/3150/2) to
respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe fr
Anyone interested in adding PRELU (id 54) to tflite frontend?
I have custom tflite model which uses it.
http://tracking.discuss.tvm.ai/tracking/click?d=O5itvT09mHlu_F8ZIICX09Depp-8XgNXxc6Hc2IknD8bmKSO9aybJj4w1XPzynxo4H4xTrmXLS1MKf92oZ8x6nwnys-xR7-T48a5LHvHuMmXdmHm8KiDT-GfCVL-uCHTOZFQME2tcH9ehUr
