Home
Forums
New posts
Search forums
What's new
New posts
New profile posts
Latest activity
Members
Current visitors
New profile posts
Search profile posts
Log in
Register
What's new
Search
Search
Search titles only
By:
New posts
New profile posts
Latest activity
Menu
Log in
Register
Install the app
Install
Home
What's new
JavaScript is disabled. For a better experience, please enable JavaScript in your browser before proceeding.
You are using an out of date browser. It may not display this or other websites correctly.
You should upgrade or use an
alternative browser
.
Latest activity
What's new
New posts
New profile posts
Latest activity
A
adarsh_a
replied to the thread
How to access APU in Mediatek chipsets
.
Hi Andrey, Thanks for the response, I forced enabled the Neuron delegate. I am able to benchmark the pre existing models on the app...
Thursday at 5:37 PM
O
operator45
replied to the thread
Can't run very a basic model with GPU delegate. Problem with my conversion?
.
If I remove the initial reshape layer in the MNIST tutorial model, I can run on the GPU successfully:
Mar 17, 2023
O
operator45
replied to the thread
Can't run very a basic model with GPU delegate. Problem with my conversion?
.
If I make the input tensors equal size, the app runs with GPU delegate without errors. But it is not suitable for my model, I would...
Mar 17, 2023
O
operator45
replied to the thread
Can't run very a basic model with GPU delegate. Problem with my conversion?
.
I further removed the split op, but this still gives the following error. So there is no broadcast support for GPU delegate? I tried...
Mar 17, 2023
O
operator45
posted the thread
Can't run very a basic model with GPU delegate. Problem with my conversion?
in
Crashes & Issues
.
Phone Model: Samsung Galaxy S21 APP version: 5.0.3. I also tried the nightly version (24.12.2022). TF version: 2.10, tried 2.12 and 2.5...
Mar 16, 2023
B
bagofwater
posted the thread
Reference for error/accuracy
in
General AI Benchmark Questions
.
From the 2019 AI benchmark paper: "For each corresponding test, the L1 loss is computed between the target and actual outputs produced...
Mar 16, 2023
Andrey Ignatov
replied to the thread
How to access APU in Mediatek chipsets
.
Try force enabling the Neuron delegate in the acceleration settings by pressing > 3 times on this option. The latest Neuron build should...
Mar 16, 2023
A
adarsh_a
posted the thread
How to access APU in Mediatek chipsets
in
General AI Benchmark Questions
.
I am working on Mediatek mobile phones : Mediatek Dimesnity 9000, Dimensity 920, Dimensity 1200. I can access the APU on Mediatek 9000...
Mar 13, 2023
C
Collin80
replied to the thread
Device List
.
I recently got an S23 Ultra and ran the benchmark. The score was 2031K which does blow away anything else on the device list so far. You...
Feb 22, 2023
J
Jarvis Irving
replied to the thread
Real-Time Video Super-Resolution Challenge
.
Dear organizers, thanks for you organizing this interesting challenge. Noticed that the scoring strategy for 2022 has changed compared...
Feb 17, 2023
Andrey Ignatov
replied to the thread
Oculus (Meta) Quest 2
.
Hi @tvkamara, Yes, unfortunately the latest Android versions do not allow the app to access any files without a user picking them up...
Feb 16, 2023
Andrey Ignatov
replied to the thread
Device List
.
Hi @David Kerr, Thanks! We include the majority of devices which scores can be validated to the ranking table. We also observed the...
Feb 16, 2023
D
David Kerr
posted the thread
Device List
in
AI Benchmark Results
.
Hey Andrey its a great site and the application is really useful. The CVPR workshops are very informative as well. What is the process...
Feb 15, 2023
T
tvkamara
replied to the thread
Oculus (Meta) Quest 2
.
Still looking for a solution to this problem. @Andrey Ignatov , do you know if there is a way to benchmark custom models on Meta Quest 2...
Feb 15, 2023
Andrey Ignatov
replied to the thread
Transformer-based architectures not working with GPU delegate
.
TFLite GPU delegate supports only a subset of TFLite / TF ops (mainly related to computer vision), thus it's very common that many NLP...
Feb 6, 2023
Home
What's new
Top