PytorchInsight
PytorchInsight copied to clipboard
implus
a pytorch lib with state-of-the-art architectures, pretrained models and real-time updated results
When I was running the python tools/test.py script, I encountered the following error. How can I solve it? Thanks! $ python tools/test.py local_configs/cascade_rcnn_r50_fpn_20e.py checkpoints/cascade_rcnn_fpn_20e_old_resnet50.pth Traceback (most recent call last): File...
Could you please upload the Pytorch version of SK-ResNeXt and hence we can reproduce the paper performance of it. Thank you:)
Hi, Thank you for sharing code! I write a simple code for testing an image: import mmcv from mmcv.parallel import MMDataParallel, collate, scatter from mmcv.runner import load_checkpoint from mmdet.apis import...
Hi, Thank you for sharing your code and models. It's hard to download from Baidu. Is it possible to upload the following models on google drive or dropbox? - SGE-ResNet50...
I use pytorch 1.0.0, when I do ./compile.sh, I meet this problem.
SRM net
Hi, cool repository! Can you consider adding to comparison SRM net from "SRM : A Style-based Recalibration Module for Convolutional Neural Networks" (https://arxiv.org/abs/1903.10829) which looks very promising. You can use...
As paper said，group conv of different group channel can extract different part features of an object.I wonder the improvement of performance come from group conv or attention mudule. Do you...
Hi, thank you for this repository it's a very good idea. Would it be possible to have the pre-trained architectures cited in this [paper](https://arxiv.org/pdf/1904.05049v2.pdf) that seem very interesting. The results...
背景噪音的position对应的特征向量往往有很多元素没被激活，对向量所有元素相加的话，通常value会很小。而SGE用的是加权平均，权重大小是对应特征的Global Average（GAP越大就说明这个特征越显著/越高频）。 我感觉这样解释会比原文更容易理解
