-
sorry for this issue.
I can't find the SS_N implementation. Did you haven't realized this part yet?
-
步骤：稀疏化训练
```
ssh://root@127.0.0.1:8026/usr/local/bin/python -u /project/pytorch-yolov3/train_prune.py --data=data/person_1cls.data --batch-size=4 --cfg=cfg/yolov3-spp-1cls-a2.cfg --weights=weights…
mozpp updated
4 years ago
-
- [x] Kubernetets cluster env @ Almaren 200
- [x] [Jenkins Slave and Kubernetes client env](http://10.112.231.51:18888/view/BigDL-2.0-NB/job/BigDL-NB-K8s-ExampleTests/)
- [x] [Hyper Zoo Doicker imag…
-
# 活动介绍
大家好，第一期 OpenMMLab 超级视客营实训活动开始啦！超级视客营实训活动提供十七个方向、上百个不同难度的任务供大家选择，不管你是初涉 AI 的新…
-
### 🐛 Describe the bug
```python
# either
torch.hub.load('pytorch/vision', 'resnet50', pretrained=True)
# or
from torchvision.models.resnet import resnet50
resnet50(pretrained=True)
```
B…
-
Whether the meta-validation data classes are consistent with the meta-train data classes in one task? For meta-validation during meta-train, the meta_lr is 0 which means ss_weights and fc_weights wi…
-
Would be useful to have examples demonstrating how to use [fastai](https://docs.fast.ai/index.html) and transfer learning to train models as this would most likely be the starting place for new learne…
-
Hi!
I tried the example and felt very cool!
But when I trained my model, an error occurred in batch = [1501/20695].
The content is as follows:
--------------- ------------------ ------------------…
-
### 🐛 Describe the bug
## Background
The `torch.optim.Optimizer.add_param_group` method is often used with transfer learning in order to unfreeze layers during training. For example, this is the …
idfah updated
2 years ago
-
# 本周完成的工作
1. 日常阅读一篇gan的文章，在网上记录了一个博客，DCGAN，BEGAN，等gan都进行了分析，但是还没写好，存在草稿里，将内容放在草稿箱里，在完成胡老师的任务之后，再进行下一次编辑。
2. 胡老师布置的CAM方法，是一个分类网络，在分类网络的最后一层中，将原来的Dense操作改为了Global average pool，我重新查看了一下几个pool，发现没有，经…