aviaisr

Hi, Is it possible to train unet model with mobilenet encoder when the input size is 512? As training proceeds, I'm getting empty maps. What can be the problem?

Convert Dense to "FC" instead of "GEMM"

1

Is there a way to convert force the conversion of tf.Densse layer to MatMul + Add instead of GEMM? I'm converting onnx to DLC and GEMM is causing problems.

check_model gives 'Bad node spec' error

2

Hi, I'm trying to convert onnx to pb. The onnx file loading is done successfully. Then, I call prepare (a function of onnx_tf.beckend). This function calls onnx.checker.check_model -> that calls...

Your pretrained models are unavaliable in the GoogleDrive link

2

Can you please share it again?

Trained model

3

Hi, Can you supply a trained model we can use to keep training with our-own datasets? If not, can you supply a link to the required "citys" dataset? Thanks