-
微博内容精选
-
Hey István,
congrats on these great results and thanks for providing an easy-to-use way to run your models, exceptional work :)
I really like the result I get and just like everyone else in the is…
-
When I run the following code:
```julia
using Metalhead
using Flux
model = EfficientNet(:b0) |> gpu
data = rand(Float32, 224, 224, 3, 1) |> gpu
output = model(data)
println(output)
```
I ge…
-
If you open a GitHub issue, here is our policy:
It must be a bug, a feature request, or a significant problem with the documentation (for small docs fixes please send a PR instead).
The form below…
innat updated
2 years ago
-
**Is your feature request related to a problem? Please describe.**
So far you have integration for AutoAugment and RandAugment in the repo as well as some settings that seem to be inspired by Uniform…
-
I am trying to replicate your findings with the oidv6 dataset. So far I have managed to load the oidv6 dataset (only about 1.7million valid images) with their labels. I am using a efficientnetV2 backb…
-
Model config for ViT-H-14 not found. Probably easily solvable. FIrst issue tho 😁
`LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 865.91 M params.
making attention of type '…
-
Discovered while trying to benchmack ConvNeXtV2 vs ConvNeXt.
The existing ConvNeXt implementation doesn't train in `keras.applications` and `keras_cv`. The loss is going down, but the accuracy stay…
-
Instantiating a RN50x64 model without pretrained weights fails.
```py
import open_clip
m = open_clip.create_model('RN50x64')
```
```
ERROR:root:Model config for RN50x64 not found; available mode…
lopho updated
2 years ago
-
From the tutorials,
`keras.applications.imagenet_utils.decode_predictions(preds)[0]`
as expected this decode expects 1k classes, and yields error :
`----------------------------------------…