geoexploring

@zerollzeng ，thank you for your attention，here's the model: [random_param_4_nvidia_test_2e3_2e3.onnx](https://myswjtueducn-my.sharepoint.com/:u:/g/personal/wenhwu_my_swjtu_edu_cn/EWjgbpb4FldLnKTBtLmRoFwB_SiOxTAbN0CVenWjsIMpgA?e=VW3sxa), please download. thanks again

The ImageNet's pre-trained model only has 3 channels, Is this suitable for multi-channel(>3) training of remote sensing images? @sshuair Thanks!

This solution is interesting and may be a compromise to train multi-channel satellite images using ImageNet pre-trained models. Thanks for this excellent work , @sshuair

@xxdm ，您好，我遇见类似的问题， 我将模型导出成ONNX模型时，设定`--input_shape_dict "{'x': [1, 3, 512, 512]}`，然后用opencv调时也是`[1, 3, 512, 512]`的图片输入，但是会报`opencv-python\opencv\modules\dnn\include\opencv2/dnn/shape_utils.hpp:171: error: (-215:Assertion failed) start

@NBd-hub 好的，谢谢！ Deeplabv3+不支持，很奇怪。

@jiangjiajun ，感谢！ 请问您指的`导出来的模型`，就是类似Paddle训练生成的`best model`文件夹下的文件吗？

@jiangjiajun , 好的，我将模型发送到您的邮箱里。