Could you provide the mobilevit_xs weight? thank you!

import torch
import models

model = models.MobileViT_S()
PATH = "./MobileVit-S.pth.tar"
weights = torch.load(PATH, map_location=lambda storage, loc: storage)
model.load_state_dict(weights['state_dict'])
model.eval()
torch.save(model, './model.pt')

• I try to load the pre-train weight to test one demo; but the network structure does not seem to match the weights, is there any solution?

I really appreciate your efforts in implementing this model in pytorch. Here, I have one concern about the training settings. If what I understand is correct, you just trained the model for less than 5 epoches.

In addition, the hyper-parameters you adopted is different from that in the original article. For instance, in the original manuscript, authors train mobilevit using AdamW optimizer, label smoothing cross-entry and multi-scale sampler. The training phase has a warmup stage.

I also found that the classificaion accuracy provided here is much lower than that in the original version.

I conjecture that the gab between accuracies are caused by different training settings.

I wanted to load the MobileViT_S() model and use the pre-trained weights, but I have got some errors in my code. To make it easier and help others, I will share my solution (in case there will be someone who is beginner like me):

def load_mobilevit_weights(model_path):
  # Create an instance of the MobileViT model
  net = MobileViT_S()
  
  # Load the PyTorch state_dict
  state_dict = torch.load(model_path, map_location=torch.device('cpu'))['state_dict']
  
  # Since there is a problem in the names of layers, we will change the keys to meet the MobileViT model architecture
  for key in list(state_dict.keys()):
    state_dict[key.replace('module.', '')] = state_dict.pop(key)
  
  # Once the keys are fixed, we can modify the parameters of MobileViT
  net.load_state_dict(state_dict)
  
  return net

net = load_mobilevit_weights("MobileViT_S_model_best.pth.tar")

Thanks for your wonderful work！

I prepare to try MobileVit on small dataset, such as MNIST, and I need adjust the network structure. Before this work, I want to know if MobileVit has a better performance than other networks on small dataset.

I notice "get_cifar10_dataset" in utils.py. Have you tested MobileVit on cifar-10? If you have, could you please show me the accuracy and inference time result?

Hi!

I am using this implementation to train a MobileViT using my own dataset. Using PyTorch the training went well, but when I wanted to converted the trained model to a CoreML model using coremltools, I have got an error. Do you have any suggestions to replace this function using any built-in function or any other function ?

Thank you in advance!

A problem has been bothering me. the learning rate, optimizer, batch_size, L2 regularization, label smoothing and epochs are inconsistent with the paper. How should I modify the code?

I appreciate your effort. It helps me a lot :)

It would be very helpful if you could share the pretrained model file for XS or XXS.

thank you,