Experiment Configuration#
Field |
value_type |
description |
default_value |
valid_min |
valid_max |
valid_options |
automl_enabled |
|---|---|---|---|---|---|---|---|
|
string |
Backend name that |
sparse4d |
||||
|
string |
Parent directory for the output of an action; TAO Deploy
writes to its |
|||||
|
collection |
Model dimensions that both actions share. Refer to Model Configuration. |
FALSE |
||||
|
collection |
Plugin library that both actions load. Refer to Plugin Configuration. |
FALSE |
||||
|
collection |
Settings for the |
FALSE |
||||
|
collection |
Settings for the |
FALSE |
Model Configuration#
Field |
value_type |
description |
default_value |
valid_min |
valid_max |
valid_options |
automl_enabled |
|---|---|---|---|---|---|---|---|
|
int |
Number of cameras in each frame; the engine profile fixes
this value, so use the same value for |
6 |
1 |
|||
|
int |
Height of each camera image in pixels; the |
256 |
1 |
|||
|
int |
Width of each camera image in pixels; together with
|
448 |
1 |
|||
|
int |
Number of object queries in the exported model;
|
900 |
1 |
|||
|
int |
Number of queries that TAO Deploy caches from one frame to
the next; the value cannot exceed |
600 |
1 |
|||
|
int |
Channel width of each query feature; |
256 |
1 |
|||
|
ordered_int |
Number of components in each anchor box, including the 3D velocity; TAO Deploy supports only 11. |
11 |
11 |
|||
|
int |
Number of classes in the |
7 |
1 |
Plugin Configuration#
Field |
value_type |
description |
default_value |
valid_min |
valid_max |
valid_options |
automl_enabled |
|---|---|---|---|---|---|---|---|
|
string |
Absolute path to a trusted plugin library. |
|||||
|
string |
Required SHA-256 hash of the file at |
TensorRT Engine Generation Configuration#
Field |
value_type |
description |
default_value |
valid_min |
valid_max |
valid_options |
automl_enabled |
|---|---|---|---|---|---|---|---|
|
string |
Directory that receives |
|||||
|
int |
Index of the GPU that builds the engine; TAO Deploy
exports it as |
0 |
0 |
|||
|
string |
Path to the ONNX file that the Sparse4D |
|||||
|
string |
Path of the new engine file; TAO Deploy also writes the
sidecar file |
|||||
|
categorical |
Precision of the engine; the build disables TensorFloat-32
(TF32) for both values, and |
fp32 |
fp32,fp16 |
|||
|
float |
Workspace memory pool limit for the build in gibibytes (GiB); the value must be finite and greater than zero. |
4.0 |
0.1 |
Inference Configuration#
Field |
value_type |
description |
default_value |
valid_min |
valid_max |
valid_options |
automl_enabled |
|---|---|---|---|---|---|---|---|
|
string |
Directory that receives the output files; if empty, TAO
Deploy uses the |
|||||
|
ordered_int |
Number of GPUs; the launcher always runs inference on one GPU. |
1 |
1 |
|||
|
list |
Indices of the GPUs that the launcher exposes as
|
[0] |
FALSE |
|||
|
string |
Path to the engine that |
|||||
|
string |
Path to the JSON manifest of prepared NPZ frames. |
|||||
|
int |
Number of queries per frame that TAO Deploy decodes, taken
in descending order of class probability; the value must
be greater than zero and at most |
300 |
1 |
|||
|
float |
Minimum raw class probability for a detection; the comparison uses the probability before quality weighting, and the value must be from 0 to 1. |
0.05 |
0.0 |
1.0 |
||
|
float |
Minimum raw class probability at which a query that has no instance ID receives a new one; the value must be from 0 to 1. |
0.2 |
0.0 |
1.0 |
||
|
float |
Multiplier for the confidence that a cached query had in the previous frame; the larger of the decayed value and the current confidence ranks the query for the next cache; the value must be from 0 to 1. |
0.8 |
0.0 |
1.0 |
||
|
float |
Largest time gap in seconds between consecutive frames of one scene that keeps the cache; a larger gap resets the temporal state; the value must be finite and greater than zero. |
2.0 |
0.0 |
|||
|
bool |
Whether to write the raw engine outputs of every frame to
the |
False |