-
Docker 1.13 adds experimental support for checkpoint/restore, using CRIU (https://criu.org), see [Docker Checkpoint & Restore](https://github.com/docker/docker/blob/v1.13.0-rc4/experimental/checkpoint…
-
python predict_downstream_condition.py --ckpt_path model_name_roberta-base_taskname_qqp_lr_3e-05_seed_42_numsteps_2000_sample_Categorical_schedule_mutual_hybridlambda_0.0003_wordfreqlambda_0.0_fromscr…
-
I used the default setting and run the code with 32 V100, the data was constructed from nvidia scripts.
I was able to reproduce nvidia's results on Squad (F1=90), but failed to reoroduce deepspeed re…
-
I got this error with tensorflow:latest, tensorflow:1.8.0-gpu-py3, 1.14.0-gpu-py3 and 1.14.0-gpu. I got them all via [docker](https://hub.docker.com/r/tensorflow/tensorflow/tags).
```
python trai…
-
I read the code and find that, the training and the test networks are different in structure.
In particular, in training network, the embedding layers are added after the concatenation of the output …
-
请问，为什么在运行 sh scripts/run_image2video.sh之后，提示找不到这么多的参数呢？模型我已经下载了，放在了文档要求的 checkpoint文…
-
zhoulw@zhoulw-Super-Server:~/pixloc$ python3 pixloc/pixlib/train.py pixloc_cmu_reproduce --conf pixloc/pixlib/configs/train_pixloc_cmu.yaml --restore true --distributed true
[11/17/2021 14:27:40 pixl…
-
Im using coco evaluation after training with tensorflow object detection api.
OS: Ubuntu 16
Python3
I saw the issues for installing cocoapi using python3.
- pip3 installed pycocotools
- git cl…
-
Thanks for your great work.
As mentioned other issues, i also find the RVQ FID score(0.02 v.s. 0.06) can't be reproduced even following released opt.txt. I wonder if the results are related to the…
-
when run 'depth_anything = DepthAnything.from_pretrained(pretrained_model_name_or_path='LiheYoung/depth_anything_{}14'.format(args.encoder)).to(DEVICE).eval()', there is a error 'TypeError: __init__()…