Do get_binding_shape(binding), get_binding_dtype(binding) and binding_is_input(binding) have an equivalent in TensorRT 10.2?

[AriannST]

Hi everyone, i'm checking this code about which allocates all buffers required for an engine:

def allocate_buffers(engine):
    inputs = []
    outputs = []
    bindings = []
    stream = cuda.Stream()
for binding in engine:
    size = trt.volume(engine.get_binding_shape(binding)) * engine.max_batch_size
    dtype = trt.nptype(engine.get_binding_dtype(binding))
    # Allocate host and device buffers
    host_mem = cuda.pagelocked_empty(size, dtype)
    device_mem = cuda.mem_alloc(host_mem.nbytes)
    # Append the device buffer to device bindings.
    bindings.append(int(device_mem))
    # Append to the appropriate list.
    if engine.binding_is_input(binding):
        inputs.append(HostDeviceMem(host_mem, device_mem))
    else:
        outputs.append(HostDeviceMem(host_mem, device_mem))
return inputs, outputs, bindings, stream

My problem is that it works in an environment with TensorRT 8.X., and I'm trying to run it in TensorRT 10.2. where get_binding_shape(binding), get_binding_dtype(binding) and binding_is_input(binding) functions were eliminated. Does equivalents of these functions exist? Or in any case, Is there a way to use tensor functions to obtain the same outputs? Thanks for your attention. Btw the class is tensorrt.ICudaEngine

[lix19937]

#3954 (comment) @AriannST

[kevinch-nv]

Thanks @lix19937 for the comments. You can also see https://docs.nvidia.com/deeplearning/tensorrt/latest/api/migration-guide.html for the proper steps to migrate the API from 8.X -> 10.X.