neural_compressor.adaptor.tf_utils.util¶
Tensorflow Utils Helper functions.
Module Contents¶
Functions¶
|
Check if version1 is less than version2. |
|
Check if version1 is greater than version2. |
|
Check if version1 is equal to version2. |
|
Check if version1 is greater than or equal to version2. |
|
Check if version1 is less than or equal to version2. |
|
A Decorator to disable tf random seed. |
|
Reads input graph file as GraphDef. |
|
Write output graphDef to file. |
|
Check the model_path format is ckpt or not. |
|
Check the model_path format is saved_model or not. |
|
Get the graph of the estimator. |
|
Get the tensor by name. |
|
Run the graph that have iterator integrated in the graph. |
|
Collate tbe prediction results. |
|
Get the input node name and output node name of the graph_def. |
|
Fix ref type of the graph_def. |
|
Strip unused nodes of the graph_def. |
|
Strip nodes with the same input and attr. |
|
Get the model's graph_def. |
|
Get the inout shape of the input model. |
Get the tensor value for given node name. |
|
|
Reverse int8 node name. |
|
Tensorflow diagnosis helper function. |
|
Generate feed dict helper function. |
- neural_compressor.adaptor.tf_utils.util.version1_lt_version2(version1, version2)¶
Check if version1 is less than version2.
- neural_compressor.adaptor.tf_utils.util.version1_gt_version2(version1, version2)¶
Check if version1 is greater than version2.
- neural_compressor.adaptor.tf_utils.util.version1_eq_version2(version1, version2)¶
Check if version1 is equal to version2.
- neural_compressor.adaptor.tf_utils.util.version1_gte_version2(version1, version2)¶
Check if version1 is greater than or equal to version2.
- neural_compressor.adaptor.tf_utils.util.version1_lte_version2(version1, version2)¶
Check if version1 is less than or equal to version2.
- neural_compressor.adaptor.tf_utils.util.disable_random(seed=1)¶
A Decorator to disable tf random seed.
- neural_compressor.adaptor.tf_utils.util.read_graph(in_graph, in_graph_is_binary=True)¶
Reads input graph file as GraphDef.
- Parameters:
in_graph – input graph file.
in_graph_is_binary – whether input graph is binary, default True.
- Returns:
input graphDef.
- neural_compressor.adaptor.tf_utils.util.write_graph(out_graph_def, out_graph_file)¶
Write output graphDef to file.
- Parameters:
out_graph_def – output graphDef.
out_graph_file – path to output graph file.
- Returns:
None.
- neural_compressor.adaptor.tf_utils.util.is_ckpt_format(model_path)¶
Check the model_path format is ckpt or not.
- Parameters:
model_path (string) – the model folder path
- Returns:
return the ckpt prefix if the model_path contains ckpt format data else None.
- Return type:
string
- neural_compressor.adaptor.tf_utils.util.is_saved_model_format(model_path)¶
Check the model_path format is saved_model or not.
- Parameters:
model_path (string) – the model folder path
- Returns:
return True if the model_path contains saved_model format else False.
- Return type:
bool
- neural_compressor.adaptor.tf_utils.util.get_estimator_graph(estimator, input_fn)¶
Get the graph of the estimator.
- Parameters:
estimator – tf estimator model
input_fn – input function
- Returns:
graph
- neural_compressor.adaptor.tf_utils.util.get_tensor_by_name(graph, name, try_cnt=3)¶
Get the tensor by name.
Considering the ‘import’ scope when model may be imported more then once, handle naming format like both name:0 and name.
- Parameters:
graph (tf.compat.v1.GraphDef) – the model to get name from
name (string) – tensor of tensor_name:0 or tensor_name without suffixes
try_cnt – the times to add ‘import/’ to find tensor
- Returns:
tensor got by name.
- Return type:
tensor
- neural_compressor.adaptor.tf_utils.util.iterator_sess_run(sess, iter_op, feed_dict, output_tensor, iteration=-1, measurer=None)¶
Run the graph that have iterator integrated in the graph.
- Parameters:
sess (tf.compat.v1.Session) – the model sess to run the graph
iter_op (Operator) – the MakeIterator op
feed_dict (dict) – the feeds to initialize a new iterator
output_tensor (list) – the output tensors
iteration (int) – iterations to run, when -1 set, run to end of iterator
- Returns:
the results of the predictions
- Return type:
preds
- neural_compressor.adaptor.tf_utils.util.collate_tf_preds(results)¶
Collate tbe prediction results.
- neural_compressor.adaptor.tf_utils.util.get_input_output_node_names(graph_def)¶
Get the input node name and output node name of the graph_def.
- neural_compressor.adaptor.tf_utils.util.fix_ref_type_of_graph_def(graph_def)¶
Fix ref type of the graph_def.
- neural_compressor.adaptor.tf_utils.util.strip_unused_nodes(graph_def, input_node_names, output_node_names)¶
Strip unused nodes of the graph_def.
The strip_unused_nodes pass is from tensorflow/python/tools/strip_unused_lib.py of official tensorflow r1.15 branch
- neural_compressor.adaptor.tf_utils.util.strip_equivalent_nodes(graph_def, output_node_names)¶
Strip nodes with the same input and attr.
- neural_compressor.adaptor.tf_utils.util.get_graph_def(model, outputs=[], auto_input_output=False)¶
Get the model’s graph_def.
- neural_compressor.adaptor.tf_utils.util.get_model_input_shape(model)¶
Get the inout shape of the input model.
- neural_compressor.adaptor.tf_utils.util.get_tensor_val_from_graph_node(graph_node_name_mapping, node_name)¶
Get the tensor value for given node name.
- Parameters:
graph_node_name_mapping – key: node name, val: node
node_name – query node
- Returns:
numpy array
- Return type:
tensor_val
- neural_compressor.adaptor.tf_utils.util.int8_node_name_reverse(node)¶
Reverse int8 node name.
- neural_compressor.adaptor.tf_utils.util.tf_diagnosis_helper(fp32_model, quan_model, tune_cfg, save_path)¶
Tensorflow diagnosis helper function.
- neural_compressor.adaptor.tf_utils.util.generate_feed_dict(input_tensor, inputs)¶
Generate feed dict helper function.