Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

TPU-compiled model outputs are broken #2

Closed
maxbbraun opened this issue May 22, 2020 · 0 comments
Closed

TPU-compiled model outputs are broken #2

maxbbraun opened this issue May 22, 2020 · 0 comments
Assignees
@maxbbraun
Labels
bug Something isn't working

Comments

@maxbbraun
Copy link
Owner

Something isn't right with the compiled version of the model.

With thermal_face_automl_edge_l.tflite:

boxes-tflite

With thermal_face_automl_edge_l_edgetpu.tflite:

boxes-edgetpu
@maxbbraun maxbbraun added the bug Something isn't working label May 22, 2020
@maxbbraun maxbbraun self-assigned this May 22, 2020
This was referenced May 22, 2020
Open
Closed
maxbbraun added a commit that referenced this issue Jul 15, 2020
@maxbbraun
Edge TPU model re-compiled with version 14.1
448344c 
This fixes issue #2. Speed-up is still ~2x over TFLite baseline.

Compiler log:

Edge TPU Compiler version 14.1.317412892
Input: thermal_face_automl_edge_fast.tflite
Output: /out/thermal_face_automl_edge_fast_edgetpu.tflite

Operator                       Count      Status

RESHAPE                        12         Tensor has unsupported rank (up to 3 innermost dimensions mapped)
RESHAPE                        32         More than one subgraph is not supported
ADD                            19         More than one subgraph is not supported
ADD                            12         Mapped to Edge TPU
MAX_POOL_2D                    9          More than one subgraph is not supported
MAX_POOL_2D                    6          Mapped to Edge TPU
MEAN                           8          Mapped to Edge TPU
DEPTHWISE_CONV_2D              19         Mapped to Edge TPU
DEPTHWISE_CONV_2D              23         More than one subgraph is not supported
CONV_2D                        23         More than one subgraph is not supported
CONV_2D                        63         Mapped to Edge TPU
LOGISTIC                       6          More than one subgraph is not supported
LOGISTIC                       11         Mapped to Edge TPU
CONCATENATION                  2          More than one subgraph is not supported
PACK                           24         Tensor has unsupported rank (up to 3 innermost dimensions mapped)
CUSTOM                         1          Operation is working on an unsupported data type
REDUCE_MAX                     3          Mapped to Edge TPU
REDUCE_MAX                     5          More than one subgraph is not supported
MUL                            10         Mapped to Edge TPU
MUL                            6          More than one subgraph is not supported
maxbbraun added a commit that referenced this issue Jul 15, 2020
@maxbbraun
Remove README warning about closed issue #2
314bb18
@maxbbraun maxbbraun mentioned this issue Aug 4, 2020
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@maxbbraun maxbbraun

Labels
bug Something isn't working
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@maxbbraun