RFBNet issues

FileNotFoundError

Loading base network... Initializing weights... Loading Dataset... Traceback (most recent call last): File "train_RFB.py", line 257, in train() File "train_RFB.py", line 165, in train dataset = VOCDetection(VOCroot, train_sets, preproc( File...

Lixia1221

Force the nms build process.

This is a fix for #131. I faced a similar error when I tried to build the `nms` extension. This solution worked for me. Hence this PR.

aalekhpatel07

fail to run ./make.sh

4

c_type’? tstate->exc_type = local_type; ^~~~~~~~ curexc_type pycocotools/_mask.c:14327:13: error: ‘PyThreadState {aka struct _ts’ has no member named ‘exc_value’; did you mean ‘curexc_value’? tstate->exc_value = local_value; ^~~~~~~~~ curexc_value pycocotools/_mask.c:14328:13: error: ‘PyThreadState {aka...

KrystalCWT

the time test on coco is much larger than voc

2

when i use the RFBNet300_VOC_80_7.pth to eval voc images(4952)，the total test time is 190s，but when i use the RFB_vgg_COCO_30.3.pth to eval minival2014 (5000 images)，the total test time is 1000s, why...

hust-kevin

Training on custom dataset

5

Can we train RFBNet on custom images? It would be helpful if theres some explanation about it in README

glitzflitz

BasicSepConv 这里面的卷积是深度可分离卷积吗？

class BasicSepConv(nn.Module): def __init__(self, in_planes, kernel_size, stride=1, padding=0, dilation=1, groups=1, relu=True, bn=True, bias=False): super(BasicSepConv, self).__init__() self.out_channels = in_planes self.conv = nn.Conv2d(in_planes, in_planes, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, groups = in_planes, bias=bias)...

getr1ch

Question about Random Crop transformation parameters

Hi! First of all thanks for your great job and contribution! I was checking the code of the data augmentation transforms, specifically the `_crop` function. But, I have found that...

mkmenta