Vladyslav Shpihanovych

### 💡 Your Question Hi, I've seen that you recently removed cache options (cache and cache_dir) from DetectionDataset. What was the reason behind this? I thought that this offered a...

Transorms error in imagenet_efficientnet_train dalaoader,

2

### 🐛 Describe the bug Consider the following code: ``` train_data = imagenet_efficientnet_train( dataset_params={ 'root': config.TRAIN_DIR, }, dataloader_params=config.DATALOADER_PARAMS ) val_data = imagenet_efficientnet_val( dataset_params={ 'root': config.VAL_DIR, }, dataloader_params=config.DATALOADER_PARAMS ) ``` If...

Bug in teacher weights calculation

4

Hi, your code implementation contains error in updating teacher weights. Basically, current code implementation for `WeightEMA` at `utils/torch_utils.py` breaks statistics, which are saved in model for batch norm, if I...