-
Notifications
You must be signed in to change notification settings - Fork 77
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Barracuda with savedmodel file format #326
Comments
ONNX is required. You can convert a PyTorch saved model to ONNX like shown below. I include the ONNX checker, it should confirm everything worked:
|
Not sure if Tensorflow savedmodel is any different, but I use this code to convert my TF savedmodels to ONNX: import tensorflow as tf
import tf2onnx
input_path = "../data/models/"
model_name = "simple_upsampler_bilinear"
file_type = ''
output_path = "../data/models/onnx_models/"
#load the model.
pre_model = tf.keras.models.load_model(input_path + model_name + file_type)
# Convert h5 to onnx.
tf2onnx.convert.from_keras(pre_model, output_path = output_path + model_name + ".onnx", opset = 9) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Can I use barracuda with the savedModel format instead of Onnx
The text was updated successfully, but these errors were encountered: