Dakoda Sanders

> --output_layer=model_0/feature_fusion/Conv_7/Sigmoid,model_0/feature_fusion/concat_3 Thank you for this!

Nevermind, I might have been wrong, apologies.

I found something that may hopefully help you. In `aster/protos/train.proto` the 8th defined field around line 35 called `from_detection_checkpoint` is an optional bool that allows you to specify if your...

I used the one in `aster/experiments/demo/config/trainval.prototxt`

Thank you for sharing the output nodes. However, I'm encountering a problem. Those nodes are available when I open the checkpoint graph in `tensorboard` but when I try to access...

@DeepanshuMakkar I encountered the same error `ValueError: No op named GatherTree in defined operations.` and another different one related to string operations after using this method. I was able to...

I was able to get the model to run in a virtual environment with a pre-compiled binary for TF 1.9 (so just a `pip install`ed version). What I had to...

@cbasavaraj I'm running into the same problem. Were you able to resolve it?

To create my own dataset, I modified one of the scripts found in `aster/tools/`. I simply made the script parse my labels the way I had labeled them & then...

@float123 Did you ever find the output node names? I'm able to print all nodes in the graph, but I can't tell which nodes are input and output.