-
Hi Tal Ridnik, Thanks for sharing nice work, I am trying to reproduce the finetuning result using timm. My accuracy is 89.25 which is lesser than reported in paper (i.e., 91.5).
```
python train.py…
-
It's a good paper,but I meet a import error of inplace_abn:
(ml) root@21f2f8c38728:~/anaconda3/lib# /root/anaconda3/envs/ml/bin/python /root/ML_Decoder_o/train.py
Traceback (most recent call last):
…
-
When tried to use moat tagger i got the following error:
```
*** Error completing request
*** Arguments: (, 'WD14 moat tagger v2') {}
Traceback (most recent call last):
File "C:\Users…
-
## 🚀 Feature
Modify `Focus Layer` into `row major` to be compatible with `tf.space_to_depth`.
Just change the blocks order:
from : `torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::…
-
I see a focus layer after the input
```
class Focus(nn.Module):
# Focus wh information into c-space
def __init__(self, c1, c2, k=1):
super(Focus, self).__init__()
self.…
-
Hi, I'm a little confused about the focus layer. Can you tell me what the focus layer does
-
Hi,
Could you also share the checkpoints of the Edgenext models(Edgenext-S specifically) trained on 224X224 images(results were mentioned in the paper)?
I would like to compare the metrics with …
-
### Description
When using the new pretrained weights, the `load_state_dict()` function is looking for a "conv1" in the model to determine the expected input channels to the models. However, only R…
-
Hi, thanks for your work.
I tried to reproduce the mAP result using the mscoco dataset.
I changed only the mscoco 2014 dataset path.
but i get the higher mAP result at only 7 epoch.
Could you …
-
hi，大家好，非常高兴的告诉大家，百度飞桨论文复现赛第七期已经开始了，本次论文复现赛共将有100+篇的经典&前沿论文供大家复现。同时飞桨特色模型挑战赛持续展开，详细信息可以参考[AI Studio 链接](https://aistudio.baidu.com/aistudio/competition/detail/406/0/introduction)，大家是否已经迫不及待了呢~
为了帮助大…