library_name: pytorch
tags:
- astronomy
- supernovae
- transients
- pan-starrs
- cnn
- pytorch
- host-galaxy-identification
datasets:
- PRISM-Astro/h2f_delight_radius_norm_p4
- PRISM-Astro/h2f_delight_test
DELIGHT-Synth
The DELIGHT model (Förster et al. 2022) trained without any real label: the hosts of the DELIGHT training sample, each with synthetic transient positions drawn uniformly in area within three effective radii of its PS1 r-band Sersic ellipse; the number of positions per host, n = max[1, round((R_e / 8 arcsec)^4)], grows with its size (12,610 positions for 7,093 hosts, most hosts with a single one). It locates the host galaxy of a transient from PS1 r-band stamps centred on the transient.
Model
- Backbone: the DELIGHT convolutional backbone (Förster et al. 2022), shared by the five stamp levels.
- Input: PS1 stamps of 30 x 30 pixels at five levels (0.25 arcsec per pixel at level 0, doubling at each level), band(s) r.
- Output: the host offset (x, y).
The host offset is predicted in level-0 pixels of 0.25 arcsec from the stamp centre. Each prediction is the average of the eight rotations and flips of the stamp, transformed back to the original orientation. M is the mean of min(r, 1), with r the residual distance in units of the host's SEP ellipse scaled by three (semi-axes A = 3a, B = 3b); RMSE_d is the root mean square of the residual distance.
Training data and cross-validation
Trained on PRISM-Astro/h2f_delight_radius_norm_p4 with five-fold cross-validation: there is one model per fold, trained on the other four folds and validated on its own fold. The host locators are tested on the real host-transient pairs of PRISM-Astro/h2f_delight_test.
For each fold we keep the checkpoint of the epoch with the lowest validation M.
Validation results
Validation metrics of each fold model on its own validation fold (synthetic transient positions for the models trained on synthetic labels, real hand-labelled pairs for DELIGHT-Real).
| Fold | Epoch | Step | M | RMSE_d (arcsec) |
|---|---|---|---|---|
| 1 | 31 | 7812 | 0.07335 | 1.811 |
| 2 | 31 | 7812 | 0.08089 | 1.815 |
| 3 | 39 | 10023 | 0.07726 | 1.472 |
| 4 | 33 | 7986 | 0.07834 | 1.955 |
| 5 | 36 | 9324 | 0.07808 | 1.228 |
| Mean ± std | 0.07758 ± 0.00244 | 1.656 ± 0.267 |
Files
config.yaml Hydra configuration of the run (model, dataset, training arguments)
selection.json checkpoint, epoch, step and validation metrics of each fold
fold_k/model.safetensors
fold_k/trainer_state.json
Usage
Access is gated: request access on this page and log in (huggingface-cli login or HF_TOKEN) before downloading.
from hydra.utils import instantiate
from huggingface_hub import hf_hub_download
from omegaconf import OmegaConf
from safetensors.torch import load_file
repo = "PRISM-Astro/delight-synth"
cfg = OmegaConf.load(hf_hub_download(repo, "config.yaml"))
model = instantiate(cfg.model, _convert_="partial") # needs the PRISM package
model.load_state_dict(load_file(hf_hub_download(repo, "fold_1/model.safetensors")))
model.eval()
config.yaml is the Hydra configuration of the run, with dataset.fold_idx: null; the model of fold_k was
trained on the other four folds of the dataset's fold column and validated on fold k. All fold models were trained
with an effective batch of 40 stamps (per-device batch times the number of GPUs, which varied between folds), so the
per-device batch size in the file does not apply to every fold.
The input stamps must be preprocessed as in training (band selection and order, inverse hyperbolic sine of the
g band when it is used, five levels); see prism.dataset and scripts/inferencia_test.py in the code.