# Architecture Checker (Experimental)

Architecture checker is a tool made for models running with HTP
backend, including quantized 8-bit, quantized 16-bit and FP16
models. It outputs a list of issues in the model that keep the
model from getting better performance while running on the HTP
backend. Architecture checker tool can be invoked with the
modifier feature which will apply the recommended modifications
for these issues. This will help in visualizing the changes that can be
applied to the model to make it a better fit on the HTP backend.

X86-Linux/ WSL usage: snpe-architecture-checker [-h] -i INPUT_DLC [-o OUTPUT_PATH] [-m MODIFY]
    
    X86-Windows/ Windows on Snapdragon usage: python snpe-architecture-checker [-h] -i INPUT_DLC [-o OUTPUT_PATH] [-m MODIFY]
    
    required arguments:
      -i INPUT_DLC, --input_dlc INPUT_DLC
                            Path to a DLC file
    
    optional arguments:
      -o OUTPUT_PATH, --output_path OUTPUT_PATH
                            Path where the output csv should be saved. If not
                            specified, the output csv will be written to the same
                            path as the input dlc file
      -m MODIFY, --modify MODIFY
                         The query to select the modifications to apply.
                         --modify or --modify show - To see all the possible modifications. Display list of rule names and details of the modifications.
                         --modify all - To apply all the possible modifications found for the model.
                         --modify apply=rule_name1,rule_name2 - To apply modifications for specified rule names. The list of rules should be comma separated without spaces
    Copy to clipboard

**Note:**

SNPE\_ROOT environment variable must be configured before running the tool.

The output is a csv file and will be saved as
<OUTPUT\_PATH>\_architecture\_checker.csv.

model_architecture_checker.csv

|  | Graph / Layer name | Issue | Recommendation | Type | Input\_tensor\_name:[dims] | Output\_tensor\_name:[dims] | Parameters | Previous layer | Next layers | Modification | Modification\_info |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | Graph | This model uses 16-bit activation data.<br>16-bit activation data takes twice the<br>amount of memory than 8-bit activation data does. | Try to use a smaller datatype to get<br>better performance. E.g., 8-bit | N/A | N/A | N/A | N/A | N/A | N/A | N/A | N/A |
| 2 | Layer\_name\_1 | The number of channels in the input/output tensor<br>of this convolution is low (smaller than 32). | Try increasing the number of channels in<br>the input/output tensor to 32 or greater<br>to get better performance. | Conv2d | input\_1:[1, 250, 250, 3],<br>\_\_param\_ 1:[5, 5, 3, 32],<br>convolution\_0\_bias:[32] | output\_1:[1, 123, 123, 32] | {‘dilation’:’[1, 1]’,<br>‘group’:1,<br>‘pad\_amount’:’[[1, 1], [1, 1]]’,<br>‘stride’: ‘[1, 1]’} | [‘previous\_layer\_name’] | [‘next\_layer\_name1’,<br>‘next\_layer\_name2’] | N/A | N/A |

**How to read the example output csv?**

Row 1: This is an issue on the graph, the graph is using
16-bit activation data, as said in the recommendation,
changing the activation from 16 bit to 8 bit gives better
performance.

Row 2: The issue is on the layer with name
“Layer\_name\_1”. This layer has three inputs: input\_1,
\_\_param\_1 and convolution\_0\_bias where the dimensions are
[1, 250, 250, 3], [5, 5, 3, 32] and [32] respectively. This
layer has one output with tensor name output\_1 and the
dimension of this tensor is [1, 123, 123, 32]. The issue for
this layer is the channel of the input tensor is low, as the
channel is smaller than 32, would recommend to increase the
channel to at least 32 to get better performance on HTP
backend. Currently the input dimension is [1, 250, 250, 3]
and ideally have that to be [1, x, x, 32]. The Modification
and Modification\_info columns provide details about the
modifications applied to the layer. If the Architecture Checker
is not invoked with modifier or if there aren’t any modifications
applicable, then these value will be N/A.

**Is the layer/tensor name the same in the original model?**

It might not be the same but should be similar. The input
tensor, output tensor, parameters and previous/next layers
are avaliable in the output csv file to help locate the
correct node inside the original model.

**Sample Command**

snpe-architecture-checker --input_dlc ./model.dlc
                   --output_path ./archCheckerOutput
    Copy to clipboard

**Architecture Checker - Model Modifier**

For appying modifications to the model, the Architecture Checker can be invoked
with “–modify” or “–modify show” which will display a list of possible modifications.
In this case, the Architecture Checker tool will only show the rule names and modification detail.
It will run without making any changes to the model and generate the csv output.
Using the rule names from the above run, the Architecture Checker can be invoked with
“–modify all” or “–modify apply=rule\_name1,rule\_name2”. In this case, the rule specific changes
will be applied to the model and the changes can be viewed in the updated model.
Additionally, the output csv will also contain information related to the modifications.

Consider the below csv output generated after applying “–modify apply=elwisediv” modification on an example model.

model_architecture_checker.csv

|  | Graph / Layer name | Issue | Recommendation | Type | Input\_tensor\_name:[dims] | Output\_tensor\_name:[dims] | Parameters | Previous layer | Next layers | Modification | Modification\_info |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | Layer\_name\_1 | ElementWiseDivide usually has poor performance<br>compared to ElementWiseMultiply | Try replacing ElementWiseDivide with<br>ElementWiseMultiply using the reciprocal<br>value to get better performance | Eltwise\_Binary | input\_1:[1, 52, 52, 6],<br>input\_2:[1] | output\_1:[1, 52, 52, 6] | {‘eltwise\_type’: ‘ElementWiseDivide’} | [‘previous\_layer\_name’] | [‘next\_layer\_name1’,<br>‘next\_layer\_name2’] | Done | ElementWiseDivide has been replaced<br>by ElementWiseMultiply using<br>the reciprocal value |
| 2 | Layer\_name\_2 | The number of channels in the input/output tensor<br>of this convolution is low (smaller than 32). | Try increasing the number of channels in<br>the input/output tensor to 32 or greater<br>to get better performance. | Conv2d | input\_3:[1, 250, 250, 3],<br>\_\_param\_1:[5, 5, 3, 32],<br>convolution\_1\_bias:[32] | output\_2:[1, 123, 123, 32] | {‘dilation’:’[1, 1]’,<br>‘group’:1,<br>‘pad\_amount’:’[[1, 1], [1, 1]]’,<br>‘stride’: ‘[1, 1]’} | [‘previous\_layer\_name’] | [‘next\_layer\_name1’,<br>‘next\_layer\_name2’] | N/A | N/A |

**How to read the example output csv?**

Row 1: The issue is on the layer with name “Layer\_name\_1”.
It has element wise divide which gives a poor performance
as compared to elementwise multipy. After invoking architecture checker
with “–modify apply=elwisediv”, the modifications have been successfully applied
i.e. the element wise divide is replaced by element wise multiply with a reciprocal value.
This information is available in the Modification and Modification\_info columns.

Row 2: The issue is on the layer with name “Layer\_name\_2”. The number of channels
of the input tensor is less than 32. Its recommended to increase the number of channels
to 32 or greater for better performance. For this issue, the modification through the tool
is not applicable hence the Modification and Modification\_info columns are N/A.

After modifying the model, the above run will generate updated model along with the csv output.
Running the Architecture Checker on the updated model will no longer show the element wise divide issue on Layer\_name\_1.

Following are the commands to invoke Architecture Checker with Modifier to display list of modifications:

**Sample Command**

snpe-architecture-checker --input_dlc ./model.dlc
                   --output_path ./archCheckerOutput
                   --modify
    Copy to clipboard

**Sample Command**

snpe-architecture-checker --input_dlc ./model.dlc
                   --output_path ./archCheckerOutput
                   --modify show
    Copy to clipboard

Following are the commands to apply the modifications either on all possible modifications or specific rules:

**Sample Command**

snpe-architecture-checker --input_dlc ./model.dlc
                   --output_path ./archCheckerOutput
                   --modify all
    Copy to clipboard

**Sample Command**

snpe-architecture-checker --input_dlc ./model.dlc
                   --output_path ./archCheckerOutput
                   --modify apply=prelu,elwisediv
    Copy to clipboard

**Note:**

The Architecture Checker with modifier is an enchancement to help visualize the changes
that can be applied on the model to better fit it on the HTP.
To see the actual performance improvements, the model may require retraining/redesigning.

Last Published: Oct 02, 2025

[Previous Topic
Debug Tools](https://docs.qualcomm.com/bundle/publicresource/80-63442-2/topics/usergroup11.md) [Next Topic
Accuracy Debugger (Experimental)](https://docs.qualcomm.com/bundle/publicresource/80-63442-2/topics/debug_tools_snpe-accuracy-debugger.md)