Field	Value
Architecture	Four Conv-BN-ReLU-Pool blocks plus dense classifier
Parameters	2,492,170
Input	RGB image resized to 64 x 64
Output	10 EuroSAT land-use classes
Runtime	CPU-friendly PyTorch inference

Classes:

AnnualCrop, Forest, HerbaceousVegetation, Highway, Industrial, Pasture, PermanentCrop, Residential, River, SeaLake

Usage

python

import torch
from huggingface_hub import hf_hub_download

from model import SimpleNet, CLASS_NAMES

weights = hf_hub_download(
    repo_id="yava-code/eurosat-simplenet",
    filename="simple_net_v1.pth",
)

model = SimpleNet(num_classes=len(CLASS_NAMES))
model.load_state_dict(torch.load(weights, map_location="cpu"))
model.eval()

Training Notes

Dataset: EuroSAT RGB land-use imagery
Optimizer: Adam
Augmentations: flips, rotations, color jitter
Goal: compact educational classifier, not production remote-sensing model

Deployment Notes

For the Build Small Hackathon Space, the same state dict is converted to float16 chunks so the app can be reviewed without Git LFS write permissions in the organization repo. The runtime reconstructs the bytes, casts tensors back to float32, and loads the explicit SimpleNet architecture.

Limits

This model is trained for EuroSAT-style RGB tiles. It should not be used for production geospatial decisions without target-domain validation, calibration, and uncertainty handling.