-
在train.py中为什么加载数据这里val_pipeline = copy.deepcopy(train_pipeline) 测试集的处理需要复制训练集的处理，这样训练集每次都会随机裁剪尺寸，在evaluation.py里也是这样，
train_dataset = Mydataset(train_datas, train_pipeline)
val_pipeline = c…
-
Hey! I cloned the repo, but i'm facing this error when trying to run training on moisesDB from scratch.
training command: `python3 src/train.py trainer=gpu`
Wandb link: [https://wandb.ai/akhilto…
-
大佬好，我在准备好自己的数据做微调时，数据报错：
`
Traceback (most recent call last):
File "main.py", line 190, in
main(data_name)
File "main.py", line 182, in main
train.train()
File "main.py", line …
-
## 🐛 Bug
I am getting CUDA re-initialize error.
I am using below code to generate synthetic dataset on GPU. To perform distributed training I am using [official PyTorch distributed training help…
-
Hello, may I ask if you can provide the data preprocessing file for this paper? I would like to know the code for your sampling section. This is my email address, 2076085831@qq.com, Thank you.
-
我尝试给yolo_world_v2_l_vlpan_bn_2e-4_80e_8gpus_mask-refine_finetune_coco.py中直接添加
mg_train_dataset = dict(type='YOLOv5MixedGroundingDataset',
data_root='data/mixed_grounding/',
…
-
Hi,
I want to run on my custom dataset and I prepared my data according to the preprocessed ShapeNet data. I got following error for single image reconstruction with onet :
Error occured when …
-
More context: https://github.com/kubeflow/training-operator/pull/2031#discussion_r1526533371.
Currently, we apply [HuggingFace Data Collator](https://huggingface.co/docs/transformers/en/main_classes/…
-
Hi，I want to use batch_size = 2 for training. When using CenterSpatialCropd(keys=["image", "label"],roi_size=(224, 224, 224)), I can train the network, but when I use RandSpatialCropSamplesd(keys=["im…
-
Currently the Support Request stats are tracked via Google Sheets and reported manually in stand up. This ticket is to create the same functionality using GitHub and enable automatic reporting to Slac…