def optimize_fp16_onnx_no_cast(input_onnx_path, optimized_onnx_path, epsilon):
m = onnx.load(input_onnx_path)
onnx_model = OnnxModel(m)
nodes_to_remove = onnx_model.nodes()
node_to_add = onnx.helper.make_node(
"LayerNormalization",
["input", "layer_norm.weight", "layer_norm.bias"], ["output"],
"layer_norm",
epsilon=epsilon)
onnx_model.remove_nodes(nodes_to_remove)
onnx_model.add_node(node_to_add)
onnx_model.prune_graph()
onnx_model.save_model_to_file(optimized_onnx_path)
def optimize_fp16_onnx_no_cast(input_onnx_path, optimized_onnx_path, epsilon):
m = onnx.load(input_onnx_path)
onnx_model = OnnxModel(m)
weight_name = get_weight(onnx_model)
bias_name = get_bias(onnx_model)
nodes_to_remove = [n for n in onnx_model.nodes() if n.output[0] != weight_name and n.output[0] != bias_name]
nodes_to_remove = onnx_model.nodes()
node_to_add = onnx.helper.make_node("LayerNormalization", ["input", weight_name, bias_name], ["output"],
"layer_norm",
epsilon=epsilon)
onnx_model.remove_nodes(nodes_to_remove)
onnx_model.add_node(node_to_add)
onnx_model.prune_graph()
onnx_model.save_model_to_file(optimized_onnx_path)