-
Hi there,
If I want to use the model you have and further train it on some data that I have collected, what is the best (i.e. fast) way to label the raw images that I collected and in what format s…
-
I want to use CUlane dataset to train another model, and I need instance segmentation label.
Thanks much.
-
An error seems trace back to `line 70 in tools/test_lanenet.py: binary_seg_ret, instance_seg_ret = net.inference(input_tensor=input_tensor, name='lanenet_loss')`
My command is `python3 tools/test_…
-
I want to test the model with a Jetson TX2. My config is:
Set the GPU resource used during testing process
__C.TEST.GPU_MEMORY_FRACTION = 0.9
Set the GPU allow growth parameter during tensorflow …
-
Hello, I have some questions after tracing and running your code
1. In "down to top" and "right to left" of message passing in vgg_encoder.py, what's the meaning of the number 8 in length = int(CF…
-
您好，请问我在使用自己制作的数据集进行训练的时候，出现了loss=nan的问题，请问为什么会出现这样的情况呢，一般会是哪里出错呀？
出错信息如下：
…
-
Hi,
May I know why are u using tensorflow 1.3 here instead of other high version?
Best regards,
ZX
-
我使用culane数据集，把他们转成了要求的3种图像（原始，黑白二分类，黑白灰实例分割），但是训练的时候，第一个训练epoch正常，第一个验证集却报错nan。后来我只取了10张对应的三种culane图片，只利用这30张图片观察训练，设批量大小为1，每次只计算一张图片，还是这个错误，请问谁能帮下忙吗？
-
**Tim:**
- Filip Baturan @FilipBaturan, SW 9/2015
- Igor Tica @itacca , SW14/2015
- Filip Basara @filipbasara0, SW36/2015
- Aleksandar Varga @aleksandar-varga, SW40/2015
**Motivacija:**
- …
-
@cardwing hello, I am coming again. I have retrained your pre-train-model in CULane data. In the training process, I think the train is normal. Like accuracy is 70% to 80 %, accuracy-back is 90% to …