Ming-Hsuan-Tu

Any script to generate the architecture?

4

H @sanghoon , pvanet is a very deep network. as resnet, I can find a network description generator (https://github.com/cvjena/cnn-models/blob/master/ResNet_preact/resnet_preact.py) But i can not find the similar script in this repo....

Hi, the last convolution network has 384 channels, how to finetune for 512 channels as in the papers?

Does it support sequence file from pyspark?

1

hi, Recently I use pyspark to write image to sequence file. I Use scikit-image and numpy to convert/restore image data to bytearray, but failed to restore the image from the...

set format in date-range

1

hi, I want to set date-format YYYY-MM-DD in date-range, but does not work. ``` ``` Collect `row.startDay` returns `Sun Mar 27 2016 20:00:00 GMT+0800 (CST)`, not `2016-03-27`. Any suggestions? Thank...

demo code?

1

Any demo code to produce the output image? thank you.

download 0 images?

2

Issue Template ========================================= Please provide what type of issue this is (i.e. bug, suggestion, etc.), your stacktrace (if applicable), and steps taken to try to fix or avoid this bug/issue...

Hi, I have read the paper and wondering what features (meta-embedding or direct feature) did you use as a face recognition embedding. Since megaface is an open set, each meta-embedding...

Dummy forward

2

We should add `forward_dummy` to query flops by mmcv (https://github.com/open-mmlab/mmcv/blob/master/mmcv/cnn/utils/flops_counter.py#L38). Althugh we already have `extract_feat`, but it's not sync with mmdetection(https://github.com/open-mmlab/mmdetection/blob/master/mmdet/models/detectors/single_stage.py#L48). we should sync both projects since many people may...

configure stem_stride in repvgg to train with CIFAR

1

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

add yolof init_cfg

2

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...