Edit model card

FPN Model Card

Table of Contents:

Load trained model

import segmentation_models_pytorch as smp

model = smp.FPN.from_pretrained("glanacles_v1")

Model init parameters

model_init_params = {
    "encoder_name": "resnet34",
    "encoder_depth": 5,
    "encoder_weights": "imagenet",
    "decoder_pyramid_channels": 256,
    "decoder_segmentation_channels": 128,
    "decoder_merge_policy": "add",
    "decoder_dropout": 0.2,
    "in_channels": 3,
    "classes": 1,
    "activation": None,
    "upsampling": 4,
    "aux_params": None
}

Model metrics

[
    {
        "test_per_image_iou": 0.6357604265213013,
        "test_dataset_iou": 0.6359941959381104
    }
]

Dataset

Dataset name: CALFIN

More Information

This model has been pushed to the Hub using the PytorchModelHubMixin

Downloads last month
4
Safetensors
Model size
23.2M params
Tensor type
F32
·
Inference Examples
Inference API (serverless) does not yet support segmentation-models-pytorch models for this pipeline type.