cellmap/nuc-unetiso-setup-55

nuc_unetiso_setup_55

Nuclei (nuc) from FIB-SEM at 128 nm, isotropic 3D U-Net (BatchNorm, MaxPool, ConvTranspose), exp_mito setup_55 at 330000 iterations. Valid convolutions (88 voxels of context per axis); outputs raw logits. ONNX web version: cellmap/onnx-web-models/setup_55.

Model Details

Architecture	Unet3dIso
Framework	torch
Spatial Dims	3
Input Channels	1
Output Channels	1
Channel Names	nuc
Iteration	330000
Input Voxel Size	128, 128, 128 nm
Output Voxel Size	128, 128, 128 nm
Inference Input Shape	300, 300, 300
Inference Output Shape	212, 212, 212
Input Normalization	{"max": 1.0, "method": "min_max", "min": -1.0}
Inference Output Activation	{"apply_after_model": true, "name": "sigmoid"}

Available Formats

File	Format	Usage
model.pt2	torch.export	torch.export.load("model.pt2") (trainable via CellmapModel.train())
model.ts	TorchScript	torch.jit.load("model.ts")
model.onnx (+ model.onnx.data)	ONNX	onnxruntime.InferenceSession("model.onnx")
metadata.json	JSON	Model metadata

Usage

pip install cellmap-models

from cellmap_models.model_export.cellmap_model import CellmapModel

model = CellmapModel("path/to/model/folder")

# Inference
output = model.ts_model(input_tensor)

# Finetuning
trainable_model = model.train()

Or download from this repo and load directly:

from huggingface_hub import snapshot_download
from cellmap_models.model_export.cellmap_model import CellmapModel

path = snapshot_download(repo_id="cellmap/nuc-unetiso-setup-55")
model = CellmapModel(path)

Author

Marwan Zouinkhi

Links

• cellmap-models
• CellMap Project