Giters
sail-sg
/
volo
VOLO: Vision Outlooker for Visual Recognition
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
916
Watchers:
21
Issues:
43
Forks:
94
sail-sg/volo Issues
Ablation study and official code problem
Updated
2 years ago
RuntimeError: The size of tensor a (28) must match the size of tensor b (14) at non-singleton dimension 2
Updated
2 years ago
Comments count
2
Question about computational complexity formulation of Outlooker Attention
Updated
2 years ago
The Equ.5 and the operate `fold` in the paper do not seem to be consistent.
Updated
2 years ago
Comments count
6
volo-d1 training without token label data
Updated
2 years ago
Comments count
1
pre trained model file is broken.
Updated
2 years ago
Comments count
1
AttributeError: 'tuple' object has no attribute 'log_softmax'
Updated
3 years ago
Comments count
2
size mismatch for pos_embed: copying a param with shape torch.Size([1, 14, 14, 768]) from checkpoint, the shape in current model is torch.Size([1, 14, 14, 512]).
Updated
3 years ago
Comments count
1
Increasing GPU memory in every epoch when running volo-d2 without token labeling.
Updated
3 years ago
Comments count
2
When training own dataset, an error occurs when changing numberclasses to the corresponding category. If it is the default, it will report an error
Updated
3 years ago
The code for Semantic Segmentation?
Updated
3 years ago
is the order of v_pj(x) result in algoritm1 correct ?
Updated
3 years ago
Any plans for a tensorflow implementation
Closed
3 years ago
Comments count
2
May you provide the FLOPs calculation script ?
Updated
3 years ago
SystemError: returned NULL without setting an error
Updated
3 years ago
run_error
Updated
3 years ago
Comments count
1
Could you share the training script for training volo_d5 ↑512?
Updated
3 years ago
Will you release the codes for Semantic Segmentation?
Updated
3 years ago
Balanced class weight
Updated
3 years ago
Comments count
1
Finetune with 512 image size
Closed
3 years ago
Comments count
2
Colab Notebook doesn't work & gives wrong results.
Closed
3 years ago
Comments count
4
TypeError: forward() takes 1 positional argument but 2 were given
Closed
3 years ago
Comments count
2
Some thoughts about volo
Updated
3 years ago
Halonets declare a SOTA in CVPR, any contribution to conference?
Updated
3 years ago
Compare to DynamicConv
Updated
3 years ago
Comments count
3
AttributeError: 'tuple' object has no attribute 'log_softmax'
Closed
3 years ago
Comments count
2
batch-size error
Updated
3 years ago
Comments count
1
Token Labeling
Updated
3 years ago
Comments count
9
What's the difference between `x_cls` and `x_aux`?
Updated
3 years ago
Comments count
1
intuition behind Outlook Attention Generation seems does not make sense
Updated
3 years ago
Comments count
13
how to interference images or videos?
Updated
3 years ago
Comments count
3
outlook forward pass example
Updated
3 years ago
Comments count
1
volo on object detection with detectron2?
Updated
3 years ago
Comments count
5
Could you please provide imagenet 22k pretrain ?
Updated
3 years ago
Comments count
1
Confusion in class OutlookAttention moduel
Closed
3 years ago
Comments count
1
colab
Closed
3 years ago
Comments count
1
password of token labeling 's Baidu Yun
Closed
3 years ago
Main diference between "outlook attention" and "Involution".
Closed
3 years ago
Comments count
7
UnboundLocalError: local variable 'input' referenced before assignment
Closed
3 years ago
Comments count
1
AttributeError: 'tuple' object has no attribute 'max'
Closed
3 years ago
Comments count
2
There is a problem when loading the pretrained weights
Closed
3 years ago
Comments count
1
Could you please release an ablation study that compares LV-VIT with / without outlook
Closed
3 years ago
Comments count
4
semantic segmentation
Closed
3 years ago
Comments count
3