You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm having trouble using the converted model in onnxjs. I used the pretrained D0 model and the demo convert command:
python3 convert/convert_onnx.py
After successfull export, this simple Javascript code:
const myOnnxSession = new onnx.InferenceSession();
myOnnxSession.loadModel("./efficientdet-d0.onnx");
produces following error:
Uncaught (in promise) TypeError: int64 is not supported
f tensor.ts:388
p tensor.ts:420
fromProto tensor.ts:245
getValue attribute.ts:147
e attribute.ts:34
s graph.ts:110
buildGraph graph.ts:260
t graph.ts:139
from graph.ts:77
load model.ts:25
initialize session.ts:85
event instrument.ts:294
initialize session.ts:81
loadModel session.ts:63
u onnx.min.js:14
u onnx.min.js:14
a onnx.min.js:14
Did anyone try to run the converted model with onnxjs?
The text was updated successfully, but these errors were encountered:
Hey there,
I'm having trouble using the converted model in onnxjs. I used the pretrained D0 model and the demo convert command:
After successfull export, this simple Javascript code:
produces following error:
Did anyone try to run the converted model with onnxjs?
The text was updated successfully, but these errors were encountered: