-
**Is your feature request related to a problem? Please describe.**
I would like to add TensorFlow roBERTa - Unsupervised Text Selection notebook in the repo.
**Describe the Project you'd like**
t…
-
First of all, I would like to express my respect and gratitude to you for accomplishing such an inspiring work. In the paper, you used a basic triplet loss in the design of the loss function, but used…
-
I wrote a very simple simulation to test the Reinforcement Learning Module. I only set up the current action as input, and the output is "left" or "right". Going right feeds the reward 1 back into the…
-
Both for improving generalization.
-
Hi,
in line 140 in modules.py, if log_pi_stop is negative, then a positive reward would contribute to the loss function. What is the logic behind it?
I am new to reinforcement learning and pyto…
-
### Expected Behavior
fix the issue
### Actual Behavior
### Steps to Reproduce
[ipiv-Morph-img2vid-AnimateD…
ghost updated
2 weeks ago
-
# Problem
DRILL crashes sometimes during its training phase because of an assertion that is not fulfilled.
```
Goal Concept: Q154797 E^+:[3] E^-:[3]
Traceback (most recent call last):…
-
Hi, thank you for your work! But I seem to have some problems reproducing the model's performance. I followed the process you provided step by step, but I always couldn't achieve the optimal results g…
-
### Summary
- Stroma _vs_ epithelium은 구분은 잘하는편
- normal epithelium (N) vs lymphcytes (N) vs cancer은 구분을 못함
### TODO
- [x] : Negative patch oversampling
- [x] : Custom dataset을 생성
- [x…
-
When I train with KTO, the KL value quickly drops to 0, is this normal?
```
{'loss': 0.4173, 'grad_norm': 1.4672807732482507, 'learning_rate': 4.765488274413721e-06, 'rewards/chosen': 1.19
404697…