Lightweight-Segmentation
Lightweight-Segmentation copied to clipboard
Tramac
Lightweight models for real-time semantic segmentation(include mobilenetv1-v3, shufflenetv1-v2, igcv3, efficientnet).
Acoording to Searching for MobileNetV3, there is a connection from feature 1/8 to the end of the segmentation head. Is it implemented? I did not find a shortcut. 
there is aux=False in network,but it still have problem with log_softmax AttributeError: 'tuple' object has no attribute 'log_softmax'. can you help me ?thank you!
Can you please share it again?
Why the result for mobileNet v3 small/large is significantly worse than those reported in the paper
When I observe the result you get based on your model, I find the best one for MobileNetV3 small is still about 7% worse. Could you let me know what...
I am trying to train my own dataset with two classes ( background and foreground ). I get confused of the output from seg net: ``` class MobileNetV3Seg(BaseModel): def __init__(self,...
I got the error when i use the model of mobilenetv3_small to train,and i used my own dataset like as VOC. Would you give me some advice? And,would you tell...
thanks for your excellent work! why must the data be crop into squares(`768*768`), and the original aspect ratio cannot be maintained?.
Thanks for your excellent work ! I print the shapes of `c2` and `c4` from [here](https://github.com/Tramac/Lightweight-Segmentation/blob/71bf91f3d5b946a046becfd5d8667e8a0f80d630/light/model/mobilenetv3_seg.py#L22), `[1, 112, 64, 128]` and `[1, 960, 64, 128]` respectively.  As shown above,...
for i, (image, target) in enumerate(self.val_loader): image = image.to(self.device) target = target.to(self.device) with torch.no_grad(): outputs = model(image) self.metric.update(outputs[0], target) pixAcc, mIoU = self.metric.get() logger.info("Sample: {:d}, validation pixAcc: {:.3f}, mIoU: {:.3f}".format(...
Hi, Tramac! Your repo is really helpful to do some interesting experiments : ) I'm new in semantic segmentation, and I have some questions w.r.t. training of MobileNetV3+LR-ASPP. Could you...
