Downloads · 30 days
0
cuibinge/marine-ecological-feature-weights
marine-ecological-feature-weights is a machine learning model from cuibinge. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This repository stores model checkpoints for the typical marine ecological environment feature recognition project.
Downloads · 30 days
0
Access
Public
Updated Jul 4, 2026
Repo size
3.7 GB
Likes
0
Public
Click a slice to open those files.
.part000537 MB · 15%
From the Hugging Face model README
This repository stores model checkpoints for the typical marine ecological environment feature recognition project.
Legacy prototype checkpoint:
green_tide_dinov3_deeplabv3plus_best_checkpoint.pth
The checkpoint is split into 512 MiB parts under:
green_tide_dinov3_deeplabv3plus_best_checkpoint.parts/
This checkpoint is the DINOv3 + DeepLabV3+ green-tide prototype trained for one epoch on pseudo labels. Treat it as a candidate-region generator, not as the final multi-element model.
Windows PowerShell:
Get-ChildItem .\green_tide_dinov3_deeplabv3plus_best_checkpoint.parts\*.part* | Sort-Object Name | ForEach-Object { Get-Content $_.FullName -Encoding Byte -ReadCount 0 } | Set-Content .\green_tide_dinov3_deeplabv3plus_best_checkpoint.pth -Encoding Byte
Windows cmd:
copy /b green_tide_dinov3_deeplabv3plus_best_checkpoint.parts\*.part* green_tide_dinov3_deeplabv3plus_best_checkpoint.pth
Linux/macOS:
cat green_tide_dinov3_deeplabv3plus_best_checkpoint.parts/*.part* > green_tide_dinov3_deeplabv3plus_best_checkpoint.pth
Expected size: 3689754229 bytes.