Comments (6)
Thanks @cocoa-xu
It works 🥳, Thanks.
from tflite_beam.
Hi @dkuku, which version of tflite_elixir
was it in the Notebook dependencies and setup
cell? And could you please let me know if you're on an x86_64 or aarch64 Linux? Thanks!
from tflite_beam.
I was using the latest master on intel. In the deps there is 0.1.5. On cpu it runs fine for me
from tflite_beam.
Oh I kinda know what went wrong here. I haven't added reference counting mechanism to the EdgeTPUContext
and related things. So Erlang dropped some resources while they are meant to live at least as long as the Interpreter
.
I'll fix this in the next version.
With that said, if you would like to test and see if it can communicate with your TPU, then the normal model also works on TPU (but not optimised). For example,
$ mix classify_image --model test/test_data/mobilenet_v2_1.0_224_inat_bird_quant.tflite \
--input test/test_data/parrot.jpeg \
--labels test/test_data/inat_bird_labels.txt \
--use-tpu \
--tpu usb
----INFERENCE TIME----
78.4ms
-------RESULTS--------
Ara macao (Scarlet Macaw): 0.70703
from tflite_beam.
this works 👍🏻
mix classify_image --model test/test_data/mobilenet_v2_1.0_224_inat_bird_quant.tflite \ 1 ✘ 1 ☑ 3
--input test/test_data/parrot.jpeg \
--labels test/test_data/inat_bird_labels.txt \
--use-tpu \
--tpu usb
----INFERENCE TIME----
713.8ms
-------RESULTS--------
Ara macao (Scarlet Macaw): 0.70703
from tflite_beam.
Hi @dkuku, v0.1.6 is out and it should work as expected!
from tflite_beam.
Related Issues (17)
- Add a wrapper layer `TFLite.Backend` for `TfLiteTensor` HOT 1
- Segfault HOT 3
- Missing module/function docs HOT 1
- TFLiteTensor.dims vs out_tensor.shape HOT 2
- cryptic `TFLiteTensor.to_nx/2` error message when no Nx backend provided HOT 3
- Erlang Bindings
- Parse `TFLITE_METADATA`
- Create some high-level modules
- Change name to `tflite_beam`
- Convert from `lib/tflite_beam_nif.ex` to `tflite_beam_nif.erl`
- Port all existing modules to Erlang. HOT 1
- Example: BERT Question and Answer HOT 3
- Implement BERT Tokenizer HOT 1
- rebar3: Add support for using precompiled binaries. HOT 1
- [deps] add support for TensorFlow 2.12.0
- precompile for armv6? HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tflite_beam.