nahidalam
nahidalam
@krasserm Tensorflow does not have `tf.image.imresize` Instead it has `tf.imge.resize` So I am not sure when you said ``` when using tf.image.imresize(x, ..., ResizeMethod.BICUBIC) I'm getting a PSNR of about...
@manzke what is the version of torch and torchvision you used here?
Can you share it @denddyprod ? It is in some github maybe I can collaborate there?
@FateScript so you are saying YOLOX is trained on `BGR` images? I was looking into [OpenVino](https://docs.openvino.ai/latest/omz_models_model_yolox_tiny.html) and they say that the original YOLOX expects `RGB` input. I guess they are...
Just because I was planning to use it and thought loading from timm is generally easier than torch hub
@loucif01 were you able to solve it. I am trying to train it on a custom dataset and my image of dimension 419 × 612. I am getting same exact...
@lnhutnam what does your `requirements.txt` file look like? I have the below torch/torchvision and getting the same error ``` torch 1.13.1 torchvision 0.14.1 ```
@lnhutnam do you mind sharing your entire `requirements.txt` and the steps you created to build the environment for yolov7? This is how I created my environment, which works fine for...
For anyone looking it in the future, I solved my issue by making sure cuda is on the PATH ``` export PATH="/usr/local/cuda-11.8/bin:$PATH" export LD_LIBRARY_PATH="/usr/local/cuda-11.8/lib64:$LD_LIBRARY_PATH" ```
Are you planning to release the weights?