Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
This is a warehouse for MobileNetV4-Pytorch-model, can be used to train your image-datasets for vision tasks.
| Date | Stars |
|---|---|
| 2026-07-24 | 264 |
| 2026-07-25 | 264 |
| 2026-07-28 | 264 |
| 2026-07-30 | 264 |
| 2026-08-06 | 264 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<h1 align='center'>MobileNetV4</h1>
# [MobileNetV4 -- Universal Models for the Mobile Ecosystem](https://arxiv.org/abs/2404.10518)
## This project is implemented in PyTorch, can be used to train your image-datasets for vision tasks.
## [official source code](https://github.com/tensorflow/models/blob/master/official/vision/modeling/backbones/mobilenet.py)
## For segmentation tasks, please refer this [github warehouse](https://github.com/jiaowoguanren0615/Segmentation_Factory/blob/main/models/backbones/mobilenetv4.py)
## For detection tasks(___Based on DETR Detector architecture___), please refer this [github warehouse](https://github.com/jiaowoguanren0615/Detection-Factory/blob/main/configs/salience_detr_mobilenetv4_medium_800_1333.py)
## Preparation
### Create conda virtual-environment
```bash
conda env create -f environment.yml
```
### Download the dataset:
[flower_dataset](https://www.kaggle.com/datasets/alxmamaev/flowers-recognition).
## Project Structure
```
├── datasets: Load datasets
├── my_dataset.py: Customize reading data sets and define transforms data enhancement methods
├── split_data.py: Define the function to read the image dataset and divide the training-set and test-set
├── threeaugment.py: Additional data augmentation methods
├── models: MobileNetV4 Model
├── build_mobilenet_v4.py: Construct MobileNetV4 models
├── extra_attention_block.py: MultiScaleAttentionGate module
├── util:
├── engine.py: Function code for a training/validation process
├── losses.py: Knowledge distillation loss, combined with teacher model (if any)
├── optimizer.py: Define Sophia/MARS optimizer
├── samplers.py: Define the parameter of "sampler" in DataLoader
├── utils.py: Record various indicator information and output and distributed environment
├── estimate_model.py: Visualized evaluation indicators ROC curve, confusion matrix, classification report, etc.
└── train_gpu.py: Training model startup file (including infer process)
```
## Precautions
Before you use the code to train your own data set, please first enter the ___train_gpu.py___ file and modify the ___data_root___, ___batch_size___, ___num_workers___ and ___nb_classes___ parameters. If you want to draw the confusion matrix and ROC curve, you only need to set the ___predict___ parameter to __True__.
If you want to add an extra MSAG(MultiScaleAttentionGate) module, set the __extra_attention_block__ parameter to True.
Moreover, you can set the ___opt_auc___ parameter to True if you want to optimize your model for a better performance(maybe~).
## Use Sophia Optimizer (in util/optimizer.py)
You can use anther optimizer sophia, just need to change the optimizer in ___train_gpu.py___, for this training sample, can achieve better results
```
# optimizer = create_optimizer(args, model_without_ddp)
optimizer = SophiaG(model.parameters(), lr=2e-4, betas=(0.965, 0.99), rho=0.01, weight_decay=args.weight_decay)
```
## Train this model
### Parameters Meaning:
```
1. nproc_per_node: <The number of GPUs you want to use on each node (machine/server)>
2. CUDA_VISIBLE_DEVICES: <Specify the index of the GPU corresponding to a single node (machine/server) (starting from 0)>
3. nnodes: <number of nodes (machine/server)>
4. node_rank: <node (machine/server) serial number>
5. master_addr: <master node (machine/server) IP address>
6. master_port: <master node (machine/server) port number>
```
### Transfer Learning:
Step 1: Download the [pretrained-weights](https://huggingface.co/timm/mobilenetv4_conv_large.e500_r256_in1k#model-comparison)
Step 2: Write the ___pre-training weight path___ into the ___args.finetune___ in string format. Adjust ___args.input_size___ parameter based on the model pre-trained on images of different sizes.
Step 3: Modify the ___args.freeze_layers___ according to your own GPU memory. If you don't have enough memorExcerpt of 7,115 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:993a4eb3df2f3c47, topic:pytorch, readme:pre-training
matched fp:993a4eb3df2f3c47, topic:computer-vision