-
Tasks:
1. Extract **testing set** from data (prefferably data points not close to training data points)
2. Split training data into **training** and **validation** sets (through Dataset methods)…
-
-
### 🚀 The feature, motivation and pitch
Many developers, like myself, use masks in both the prediction output and ground truth to evaluate whether or not an image, for example, is valid for backpro…
-
In the paper, λ is 0.001. The code sets learn_sigma as True and rescale_learned_sigmas as False, so the loss type will be gd.LossType.MSE, in this loss type ,the Lvlb will not multply 0.001. Even if …
-
I am using the following command that is provided by this repo (only difference is the batch_size)
python train.py spacetimeformer solar_energy --context_points 168 --target_points 24 --d_model 100…
-
Hello,
Thanks for your amazing work! I have a few questions about using Featup:
1. How do you use FeatUp to enhance the pixelated features of DINOv2? Is it for a vector n * H * W (n is the dimension…
-
Hi,
After doing fine-tuning, I have checked MSE plots in two tabs: "
offline_metrics_red_cube/text_conditioned" and "training", and they were quite different.
![image](https://github.com/octo-m…
-
### Current Behavior
After a recent update, I can't see the full tag name anymore. This is **extremely** annoying, because I've been using long names for tags based on concatenation of different keyw…
-
Reference: https://github.com/sustainable-computing-io/kepler-metal-ci/blob/main/docs/train-validate-e2e-aws/2024-11-12_04-56-06/AbsPower/BPFOnly/XgboostFitTrainer/report-v0.7.12-35-g82dc44ac.md
Ac…
-
I would appreciate suggestions on how i can improve the MSE and RMSE functions.