-
confused with Augmented SBERT training procedure in train_sts_indomain_semantic.py:
Is it possible to skip first step completely (training a cross-encoder (BERT) model from scratch for small STS ben…
-
In notebook 3,
every model training process where
`.fit(train_data_augmented_shuffled, # we're fitting on augmented and shuffled data now
epochs=5,
…
-
I have noticed that the code provided for data processing, model training, and inference all apply to feature-based datasets. I am very interested in the performance of GenRT on Retrieval-augmented LL…
-
Hi,
Solid and fantastic work!
You presented the augmented test set. I am wondering if you constructed the corresponding training/developing sets as well?
If yes, will they be available?
-
### Objectives
Train fine-tuned versions of gLM2:
- [x] Version 0 (v0): Initial fine-tuning and qualitative eval (completed).
- [x] Version 1 (v1): Fine-tuning with augmented training data accoun…
-
Hello, in your description, you mentioned that ‘the dataset was collected using two 360° cameras in a top-bottom setup and a LiDAR sensor, and it includes accurate depth and disparity labels by projec…
-
Hi, looking at the captions I noticed some things:
Some captions contain raw probabilities, check for "0." or "(", numbers in brackets (together about 6%) or "probability" (about 2.5%) or "label" (4.…
-
Hi,
I have fine-tuned my model using `supervised` mode on my custom data. However, when I switch to `selfsupervised_kmeans` and add the mask file, I notice that the output shapes of the data from t…
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and fou…
-
@daniel-j-h Hello! I am working with Sentinel-2 data and successfully trained with 0.56 accuracy. Now I want to increase training data so I am trying data augmentation (rotation, zooming). I rotated a…