train-DeepLab

train-DeepLab copied to clipboard

Hello, how to generate weak annotations?

ccjcv

errors on deeplab.py

1

I use deeplab to do segmentation.when I use deeplab.py I meet this error: ``` Traceback (most recent call last): File "deeplab.py", line 106, in main() File "deeplab.py", line 24, in...

MuseCP

Throwing error when running the "make test" command

3

I am getting the below mentioned error when running the "make test" command and "make runtest" is also giving error. What kind of error is this ? I want to...

vismayaps

Pascal VOC mIOU should ignore `void` labels

2

Hello, At training, the `void` label in Pascal VOC is mapped to the background class `0`. However, for evaluation purposes, it would make sense to ignore pixels corresponding `void` pixels...

bermanmaxim

there is nothing wrong when i make all. but error in make test LD .build_release/src/caffe/test/test_euclidean_loss_layer.o LD .build_release/src/caffe/test/test_mvn_layer.o .build_release/src/caffe/test/test_contrastive_loss_layer.o: In function `caffe::ContrastiveLossLayerTest_TestForward_Test::TestBody()': test_contrastive_loss_layer.cpp:(.text._ZN5caffe41ContrastiveLossLayerTest_TestForward_TestINS_9CPUDeviceIfEEE8TestBodyEv[_ZN5caffe41ContrastiveLossLayerTest_TestForward_TestINS_9CPUDeviceIfEEE8TestBodyEv]+0x307): undefined reference to `caffe::_ContrastiveLossParameter_default_instance_' .build_release/src/caffe/test/test_contrastive_loss_layer.o: In function `caffe::ContrastiveLossLayerTest_TestForward_Test::TestBody()':...

JeffC0628

How to download and install your used caffe version?

2

error: [libprotobuf ERROR google/protobuf/text_format.cc:298] Error parsing text-format caffe.NetParameter: 24:3: Unknown enumeration value of "IMAGE_SEG_DATA" for field "type". F0108 22:52:08.534060 8636 upgrade_proto.cpp:88] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file:...

dxiaosa

Different mean_iou on VOC12

1

I tested resnet-101 successfully, but it's not the same as the author's miou. The result before densecrf on the validation set was 0.7646 and the paper was 0.7635. Strangely, the...

dingfg

In VGG, the first connected layer is 4096 7x7 filters, how to adapt these param to 3x3 1024 or 4x4 4096? Is it just copy parameters in order and remove...

pkuCactus

Training DeepLab on new images

2

I'm trying to train deeplabv2_resnet101 on new images with only 3 labels (background + 2 other classes) so I set `NUM_LABELS=3`. I noticed that during training, the loss would go...

JustinLiang

Cannot do testing on VOC 2012

17

Hi, Thanks for your clear explanation, I could do training successfully. However, I really can't do testing phase on my own. The error always occur and I can't further proceed....

xvbw