train_torchvision_mnasnet

Training process for MnasNet convolutional network.

🚀 Use with Ikomia API

1. Install Ikomia API

We strongly recommend using a virtual environment. If you're not sure where to start, we offer a tutorial here.

pip install ikomia

2. Create your workflow

from ikomia.dataprocess.workflow import Workflow

# Init your workflow
wf = Workflow()    

# Add dataset loader
data_loader = wf.add_task(name="dataset_classification")

data_loader.set_parameters({"dataset_folder": "path/to/dataset/folder"}) 

# Add train algorithm 
train = wf.add_task(name="train_torchvision_mnasnet", auto_connect=True)

# Launch your training on your data
wf.run()

☀️ Use with Ikomia Studio

Ikomia Studio offers a friendly UI with the same features as the API.

• If you haven't started using Ikomia Studio yet, download and install it from this page.

• For additional guidance on getting started with Ikomia Studio, check out this blog post.

📝 Set algorithm parameters

• model_name (str) - default 'resnet18': Name of the pre-trained model.
  • There are over 700 timm models. You can list them using: timm.list_models()
• input_size (int) - default '224': Size of the input image.
• epochs (int) - default '15': Number of complete passes through the training dataset.
• batch_size (int) - default '8': Number of samples processed before the model is updated.
• learning_rate (float) - default '0.001': Step size at which the model's parameters are updated during training.
• output_folder (str, optional): path to where the model will be saved.
• num_workers (int) - default '0': How many parallel subprocesses you want to activate when you are loading all your data during your training or validation.
• weight_decay (float) - default '1e-4': Amount of weight decay, regularization method.
• export_pth (bool) - default 'True'
• export_onnx (bool) - default 'False'

Parameters should be in strings format when added to the dictionary.

from ikomia.dataprocess.workflow import Workflow

# Init your workflow
wf = Workflow()    

# Add dataset loader
data_loader = wf.add_task(name="dataset_classification")

data_loader.set_parameters({"dataset_folder": "path/to/dataset/folder"}) 

# Add train algorithm 
train = wf.add_task(name="train_torchvision_mnasnet", auto_connect=True)
train.set_parameters({
    "batch_size": "8",
    "epochs": "5",
    "input_size": "240",
    "momentum": "0.9",
    "learning_rate": "0.001",
    "weight_decay": "1e-4",
    "export_pth": "True",
    "export_onnx": "False",
}) 

# Launch your training on your data
wf.run()