Refitter(self: tensorrt.tensorrt.Refitter, engine: tensorrt.tensorrt.ICudaEngine, logger: tensorrt.tensorrt.ILogger) → None¶
Updates weights in an
- engine – The engine to refit.
- logger – The logger to use.
get_all(self: tensorrt.tensorrt.Refitter) → Tuple[List[str], List[tensorrt.tensorrt.WeightsRole]]¶
Get description of all weights that could be refit.
Returns: The names of layers with refittable weights, and the roles of those weights.
get_missing(self: tensorrt.tensorrt.Refitter) → Tuple[List[str], List[tensorrt.tensorrt.WeightsRole]]¶
Get description of missing weights.
For example, if some Weights have been set, but the engine was optimized in a way that combines weights, any unsupplied Weights in the combination are considered missing.
Returns: The names of layers with missing weights, and the roles of those weights.
refit_cuda_engine(self: tensorrt.tensorrt.Refitter) → bool¶
Updates associated engine. Return
Failure occurs if
get_missing()!= 0 before the call.
set_weights(self: tensorrt.tensorrt.Refitter, layer_name: str, role: tensorrt.tensorrt.WeightsRole, weights: tensorrt.tensorrt.Weights) → bool¶
Specify new weights for a layer of given name. Possible reasons for rejection are:
- There is no such layer by that name.
- The layer does not have weights with the specified role.
- The number of weights is inconsistent with the layer’s original specification.
Modifying the weights before
refit_cuda_engine()completes will result in undefined behavior.
- layer_name – The name of the layer.
- role – The role of the weights. See
WeightsRolefor more information.
- weights – The weights to refit with.
Trueon success, or
Falseif new weights are rejected.