-
The original images for `gt_image_instance` and `gt_image_binary` I generated are in RGB format. Which is why I got this error initially:
> ValueError: Cannot feed value of shape (2, 256, 512, 3) f…
-
在评估训练的模型时，需要将测试的图片转换成test_label.json文件的格式，请问具体怎样做了？
-
I'm trying to train with the TuSimple dataset and I was wondering how many total images you used to train the model.
I looked through the json file and found that there are only 3626 annotated images…
-
I download a vgg16.npy from network.When i train the model ,i get the error .
totalMemory: 10.91GiB freeMemory: 10.75GiB
2018-07-18 16:59:10.664853: I tensorflow/core/common_runtime/gpu/gpu_device.c…
-
I have a problem to train my dataset.
training is stopped with nan
![instance…
-
i was successful in testing the trained model by getting the trained weights you uploaded in Dropbox. However, I want to retrain the model on new training data.
I added one new image for the exist…
-
Thank you for sharing your code! I've formatted the BDD dataset to train your model on, but I keep running into this error:
![image](https://user-images.githubusercontent.com/26938589/41876118-d1e7e…
-
请问怎么获取训练数据，是不是只有参加那个比赛的才可以下载？
cymgq updated
6 years ago
-
hi,
Thanks for sharing your codes. I have encountered a mistake as follows when I was training the net using CULane dataset based on your pre-trained models. Would you please tell me the possible mis…
-
hello, I am learning your work, the organization data set has a problem, I don't understand, your traning_data_example file structure, I want to know, how the images in pictures and gt_image_instance …