Issues
- 0
请问该如何训练自己的数据集
#59 opened by llyyccccc - 2
- 0
custom dataset tutorial
#58 opened by MSEwantCS - 4
- 2
dataset folder structure
#39 opened by svenikea - 2
Cannot run main.py in test mode - 1only batches of spatial targets supported (3D tensors)
#56 opened by rashedkoutayni - 2
Question about the params and FLOPs of ENet
#44 opened by mrzhouxixi - 1
Unable to use pre-trained models
#55 opened by rdthrow - 1
Skip connections
#54 opened by A7F - 3
the question about torch.load()
#52 opened by UnderTheMangoTree - 1
question about testing the model on an image
#53 opened by Lee2s - 9
the question about output shape
#48 opened by lucky26418 - 4
a question about UpsamplingBottleneck block
#50 opened by cedricgsh - 0
- 2
save all the images
#49 opened by Robinxin123 - 5
Problems while using different dataset
#45 opened by robsoncsantiago - 1
the question with output
#47 opened by littlelionly - 2
- 3
Training with two classes
#42 opened by PatrickNa - 2
How do I save the segmented images ?
#41 opened by VivekMahesh - 1
test IoU is nan
#40 opened by ykk136 - 1
Ignore index is not looping over indices
#38 opened by HansBambel - 5
something wrong with mIoU
#37 opened by isalirezag - 2
Can we pass Single image or a video file to the model to test the semantic Segmentation results.
#30 opened by prasadpant - 4
Wrong about test
#33 opened by ChaosNN - 1
what happened to unlabeled or void classes?
#36 opened by isalirezag - 0
Wrong about train.
#34 opened by JamesZhangjp - 1
- 1
How to use the 960x720 CamVid dataset?
#16 opened by MrLinNing - 4
About Training
#25 opened by LinRui9531 - 1
Test on video
#28 opened by xxxxxxxiao - 2
There are total 13 classes in camvid.py, but the outputs generated via pre-trained model in "./save/CamVid" have only 12 dimensions.
#29 opened by veophi - 5
- 8
Details in training on Camvid
#12 opened by herleeyandi - 5
Training the network on a binary mask
#10 opened by murhafh - 1
ENet returns a tensor with Nans as an output
#20 opened by kushnir95 - 1
How do I save the output file?
#22 opened by Taeuk-Jang - 3
Training with arbitrary sized images
#17 opened by TillChima - 2
- 2
About the cityscape dataset 1024*512.
#24 opened by 100sby - 2
Evaluation code
#23 opened by dagap - 1
Resize of Label with categorical classes
#21 opened by josueortc - 1
How to run trained network on own images?
#18 opened by cborelc - 1
memory cost and performance on cityscapes
#19 opened by chenxiaoyu523 - 2
- 1
Single picture test time
#9 opened by BobiAce - 1
- 1
- 2
mean of empty slice
#8 opened by yuyangyg - 1
Working in real time
#7 opened by DenisN03