Minho Kim

`with summary_writer.as_default(): # for tensorboard for epoch in range(start_epoch, training_epochs): for idx, (train_input, train_label) in enumerate(train_dataset): grads = grad(network, train_input, train_label) optimizer.apply_gradients(grads_and_vars=zip(grads, network.variables)) train_loss = loss_fn(network, train_input, train_label) train_accuracy =...

Reverse the color of the buffer tab

1

Thank you for creating a great colorschemes. I'm using the dark themes, but I think it would be better distinguish if the color of the buffer tabs at the top...

Hello, An error occurred while installing torch2trt  My environment is - Ubuntu 18.04 - CUDA 11.7 - CUDNN 8.7.0 - Python 3.9.16 - Torch 1.13.1 (torchvision==0.14.1) - and using...

First of all, thank you for your research with a good idea. While analyzing the code of the ctl model, I left an issue because I was curious. [training_step code](https://github.com/mikwieczorek/centroids-reid/blob/a1825b7a92b2a8d5e223708c7c43ab58a46efbcf/train_ctl_model.py#L62)...

How to fine tune a model to a custom dataset

3

Hi @drinkingcoder, First of all, thank you for your wonderful research. I am interested in training the FlowFormer model in custom data. Currently, it seems that training codes are only...

Thank you for the awesome lecture. While solving (e) of Exercise 2.5, I thought it would be nice to add a solution. This pull request is similar to #37, and...