MagicSource

can not get the world output even optimziation process runed

1

  output is empty

Speed shrink down exponential when input size larger

25

I trained the input like this: ``` test_pipeline = [ dict(type='LoadImageFromFile'), # dict(type='LoadAnnotations', with_bbox=True, with_mask=True), dict( type='MultiScaleFlipAug', img_scale=(1280, 768), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), # dict(type='RandomFlip'), dict(type='Normalize', **img_norm_cfg), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor',...

Upgrade to mmdetection 2.0?

3

Does there any plan upgrade your code to mmdetection 2.0?

Any comparasion with CondInst and MEInst and BlendMask?

1

These instance segmentation also based on fcos architecture.

官网机器人建议加个混淆

1


如何搜索？

3

csv里面的文件如何搜索呢？如何才能做到示例图的效果呢？

same input as example, but got this error: ``` convcrf/convcrf.py", line 598, in inference prediction = (self.unary_weight - self.weight) * lg_unary + \ RuntimeError: The size of tensor a (512)...

I though cRF is a post process for un-pure network prediction, why using label for CRF? what's the meaning?

Hi, really hoping the v2 version codes, the paper has been updated into v2 version, when will the codes release anyway?

Training resnet50 backbone on 2 GPUs

1

what's your loss will to be? I trained all loss to 1.0 but the result is totally wrong:  Also the category seems totally miss classified. Do u know which...