Robert Remus
Robert Remus
I believe the error that @ianupamsingh describes does not arise while (re-)loading the model, but when actually _using_ the model for inference on a single input (I'm having the same...
Right. I'm experiencing the same thing. I can't reload the saved Keras model as Keras model using ```tf.keras.models.load_model()```.
:+1: I'd really like to see TensorScatterAdd be added to tf2onnx as well.
Try shapely==1.7.1. This works just fine for me with Python 3.9.
See #2 - the ```master``` branch follows the license of [https://github.com/ultralytics/yolov3](https://github.com/ultralytics/yolov3) which is GPL-3.
I'm experiencing the same issue; I'm also trying to train DETR from scratch for the same reason (i.e., to increase the number of object queries). I'm init'ing the model as...