TensorRT
TensorRT copied to clipboard
🐛 Check for the casting of the unary operations in conversion/impl/unary/ops.py
The following lines-
if (isinstance(input_val, TRTTensor)) and (
input_val.dtype == trt.int8 or input_val.dtype == trt.int32
):
input_val = cast_trt_tensor(ctx, input_val, trt.float32, name)
are present in almost all the unary ops. Check its requirement