Willy Fitra Hendria
Willy Fitra Hendria
Following are the results of my execution using your code (no modification in the hyperparameter and model): model at 40 epoch, (train) bin_accuracy: 0.9577 val_bin_accuracy: 0.9514 test_accuracy : 0.5724729895591736 model...
In this code, https://github.com/microsoft/UniVL/blob/main/main_task_caption.py#L143-L145 , the value of `n_gpu` is determined by the actual number of GPUs present in the system. However, there are scenarios where utilizing only a single...
## 📝 Description This PR is based on the closed PR #1635 , which adds the implementation of MVTec LOCO AD dataset [[Paper](https://link.springer.com/article/10.1007/s11263-022-01578-9#Fn1)] along with the sPRO metric. 🛠️ Fixes...
## 📝 Description This PR is based on the close PR #1628: - when val_split_mode is 'NONE' , skip the validation stage by setting `config.trainer.limit_val_batches` to 0.0 - when test_split_mode...
### Describe the bug - When val_split_mode is set to none > Error: datamodule object has no attribute 'val_data' - When test_split_mode is set to none > the test stage...
In your paper, you conducted experiments for 5 epochs. In reference to this issue (https://github.com/ArrowLuo/CLIP4Clip/issues/36), it is mentioned that you reported performance based on the best scores on the validation...
Hello, Just in case anyone looking for the implementation of CLIP4Caption, I provided an unofficial implementation of the model (and the pre-trained model) in this repository: https://github.com/willyfh/clip4caption Thank you!
Hello, are you planning to release the training code soon?
I tried to reproduce your paper, but it's not clear how to adopt the Two-View Transformer in your framework. For the pretrained Faster R-CNN (ResNext-101), did you use the original...
I tried to create the training code myself, but the results don't match the paper. Perhaps I missed something, but I'm not sure. I followed the exact hyperparameters and procedures...