-
The README for depth_and_motion says that you should supply a checkpoint for the depth model pretrained on imagenet. Can you release such a model checkpoint?
-
https://github.com/MiSTer-devel/SMS_MiSTer/blob/master/SMS.sv#L477-L478
-
You can leave a link in the comments below if you have found some project not in the list. I will add it to the main list.
Comment sample:
- name: QGIS
- website: https://qgis.org
- short desc…
-
我正在对internvl2使用视频数据进行full finetune，显卡为单张32G V100，报错torch.cuda.OutOfMemoryError: CUDA out of memory.
torchrun /cache/InternVL/internvl_chat/internvl/train/internvl_chat_finetune.py \
--model_name…
-
Train: 100
Configurations:
BACKBONE resnet50
BACKBONE_STRIDES [4, 8, 16, 32, 64]
BATCH_SIZE 1
BBOX_STD_DEV [0.1 0.1 0.…
-
(There are a number of things I plan to generalize in the code base as I start working on the GMO implementation in Stan. I'm documenting the issues here so I don't forget.)
See title. We can use the…
-
Hi,
I am trying to work off your paper + code to include learnable hyperparameters in the interpolation matrix W. However, it results in a GPyTorch error "Trying to backward through the graph a secon…
-
# **Describe the bug**
I want to perform multi-node fine-tuning using deepspeed and Llama Factory. I offload my model to cpu-cpu stage3. Using LAN and Thunderbolt for SSH connections, the connectio…
-
@tonyyang-svail
I have some questions on xgboost model train and pred. In "sqlflow/python/sqlflow_submitter/xgboost/train.py", it saves the trained model locally via:
`bst.save_model("my_model")`
…
-
This repo now has no example template to start from