-
## Environment info
- `transformers` version: 4.17.0
- Platform: Linux
- Python version: 3.9.4
- PyTorch version (GPU?): 1.10.2
- Using GPU in script?: Yes
- Using distributed or parallel se…
-
## Environment info
- `transformers` version:
- Platform:
- Python version: 3.7
- PyTorch version (GPU?): GPU
- Tensorflow version (GPU?):
- Using GPU in script?:
- Using distributed or pa…
ddf62 updated
2 years ago
-
From the documentation, it says that the logits shape will be (batch_size, num_labels, height/4, width/4)
I assume that the logits are the output masks of the model (since I'm doing the segmentation…
-
## ❔Question
Why the step of learning rate scheduler after each epoch instead of each batch in [main.py](https://github.com/hustvl/YOLOS/blob/main/main.py#L217)?
Won't the change rate of lr be t…
-
Hello, thanks for your implementation.
I have read the main part of your code, but I didn't find the code that controls the Partial fine-tuning. Could you please tell me where is that part in "run_…
-
In the paper `Augmenting Convolutional networks with attention-based aggregation`, a simple PatchConvNet is presented. But PatchConvNet only output a feature map with 1/16 of original image size, the …
-
On the [training doc](https://github.com/facebookresearch/ConvNeXt/blob/main/TRAINING.md), I believe we need to adjust the batch-size (or the LR) on the single machine commands to maintain the total b…
-
## Environment info
- `transformers` version: 4.18.0.dev0
- Platform: Ubuntu 18.04.6 LTS Linux 4.15.0-167-generic
- Python version: 3.7.11
- PyTorch version (GPU?): 1.11.0 (True)
- Tens…
-
## Environment info
- `transformers` version: 4.17.0
- Platform: Linux-4.14.105-1-tlinux3-0013-x86_64-with-glibc2.17
- Python version: 3.9.2
- PyTorch version (GPU?): 1.10.2+cu113 (True)
- Te…
-
When the model is fine-tuned, I want to fix its parameters and only update the parameters of the classifier. How should i set ？