-
### Description of the bug:
I'm trying to convert a MobileNetV4 pytorch model to tflite. I get an error regarding the torch_xla library.
### Actual vs expected behavior:
What I get is:
…
-
In mobilenetv4_conv_small in block_specs there is an error in number of filters and kernel size.
https://github.com/d-li14/mobilenetv4.pytorch/blob/f6c76734417845f1536d1e1065f37b2e4342efba/mobilenet…
-
[MobileNet V4 was published](https://arxiv.org/abs/2404.10518) this summer and the [latest version of timm added support](https://huggingface.co/blog/rwightman/mobilenetv4) for the MobileNet V4 family…
j99ca updated
3 weeks ago
-
**Describe the bug**
I'm trying to use MobileNetV4 model as a feature extractor. Its num_features is 960 but giving output features as 1280.
I can get desired shaped output with convnext_nano and t…
-
I can only find \'MobileNetV4-Conv-Large-fp32.tflite\' in other repos, but it is only for inference.
Do you plan to release the checkpoints, including the un-merged BN parameters.
Thanks!
-
The latest MobileNetV4 hyrid models are not inlcuded. When create the models, it tells "invalid pretrained tag".
-
**Describe the bug**
I am trying to train a classification model using mobilenetv4, however, the accuracy is the same for the first several epoches.(See picture below) and dont know why this happens.…
-
Hello, thanks you very much for adding MobileNetv4 into this repo, excellent job!
But the problem is that I cannot train mobilenetv4 with a good result on cifar10 as the below script，so I would get s…
-
Hello, mobilenetv4 paper is released~~
Is there any plan to add mobilenetv4 into this repo?
https://arxiv.org/pdf/2404.10518
-
### 🚀 The feature
Google has published the mobilenetv4 model. When will pytorch support it and open the pre-trained model?
### Motivation, pitch
I very much hope to use the latest lightweight backb…