-
-
I downloaded your pretrained model. And when i tried to load it.
It gave me the following errors.
_IncompatibleKeys(missing_keys=['mask_token', 'decoder_pos_embed', 'stage1_output_decode.weight', …
-
再跑run_video_demo.sh时遇到的报错,全部报错如下:
Load checkpoint /home/data/MixFormer/models/mixformer_convmae_base_online.pth.tar successfully!
Traceback (most recent call last):
File "tracking/video_demo.py",…
-
执行命令 python /tracking/test.py mixformer_convmae baseline_large --dataset lasot --threads 32 --num_gpus 4 --params__model mixformer_convmae_large_online.pth.tar --params__search_area_scale 4.5 不出现Track…
-
Hello, I have seen that you reference to the ConvMAE pertained based method as MixViT-COnvMAE, but actually, looking at your implementation the backbone is much more similar to the MixCvT layout, with…
-
我在convmae论文的github地址找到了convmae_base.pth文件,但是训练的时候提示所有的权重都丢失了,我去模型里面找到原因,是因为多了一层ckpe[‘model’],改项并未在代码中给出,我项问一下是不是convMae的官方修改了之前的权重文件,还是代码忘记改了。同时,在我修改了相关代码后,仍有missingkey:'pos_embed_s', 'pos_embed_t'.我想…
-
**Describe the feature**
Feature description
**Motivation**
A clear and concise description of the motivation of the feature. Ex1. It is inconvenient when [....]. Ex2. There is a recent paper [..…
-
Hello! I would like to train stage 2 only, where can I find the pertained model for stage 1? Apparently on the drive there are online models only for convmae.
Thank you!
-
Hi ,
we using MixViT-ConvMAE online model testing lasot performance .
But found different with paper (AUC: 73.3%)
lasot | AUC | OP50 | OP75 | Prec…
-
I have tried training the convmae detector (as provided in this repository) with 2 GPUs with each 32GB (V-100). It looks like I can carry out training with only batch size = 2. Going beyond batch-size…