Hugging Face's logo

Renesas
/
RetinaNet-R101-ONNX

Object Detection
ONNX
computer-vision
renesas
x5h
retinanet
resnet101
detection
Model card Files
xet
 Community
Artem Plastinkin commited on
Commit
625da35
·
1 Parent(s): 8697afc

Add --enable-opt

Browse files
Files changed (5) hide show
  1. int8/benchmarks/x5h_mwmx_npu_apm80_12core.yaml +1 -1
  2. int8/benchmarks/x5h_mwmx_npu_apm80_1core.yaml +1 -1
  3. int8/benchmarks/x5h_mwmx_npu_apm80_3core.yaml +1 -1
  4. int8/benchmarks/x5h_mwmx_npu_apm80_4core.yaml +1 -1
  5. int8/benchmarks/x5h_mwmx_npu_apm80_6core.yaml +1 -1
int8/benchmarks/x5h_mwmx_npu_apm80_12core.yaml CHANGED
@@ -58,7 +58,7 @@ reproduce:
58
  command: hf download Renesas/RetinaNet-R101-ONNX --repo-type model --include "fp32/*" "compile_config/*" --local-dir ./RetinaNet-R101-ONNX-fp32
59
  - title: Compile with the NNAC toolchain (INT8 auto-cast from the FP32 graph)
60
  command: |
61
- python3 nnac_frontend/legalize.py -d binary/nnx ./RetinaNet-R101-ONNX-fp32/fp32/retinanet-9.onnx --num-core 12 --network-config ./RetinaNet-R101-ONNX-fp32/compile_config/network_config.yaml
62
  - title: Set up the R-Car X5H board
63
  command: Configure the board per the AI Compiler (NNAC) "Getting Started" guide, section 3.4 (host TFTP/NFS setup, bootloader flashing, U-Boot, Linux boot, login) -- exact steps depend on your board/network setup.
64
  kind: note
 
58
  command: hf download Renesas/RetinaNet-R101-ONNX --repo-type model --include "fp32/*" "compile_config/*" --local-dir ./RetinaNet-R101-ONNX-fp32
59
  - title: Compile with the NNAC toolchain (INT8 auto-cast from the FP32 graph)
60
  command: |
61
+ python3 nnac_frontend/legalize.py -d binary/nnx ./RetinaNet-R101-ONNX-fp32/fp32/retinanet-9.onnx --num-core 12 --network-config ./RetinaNet-R101-ONNX-fp32/compile_config/network_config.yaml --enable-opt
62
  - title: Set up the R-Car X5H board
63
  command: Configure the board per the AI Compiler (NNAC) "Getting Started" guide, section 3.4 (host TFTP/NFS setup, bootloader flashing, U-Boot, Linux boot, login) -- exact steps depend on your board/network setup.
64
  kind: note
int8/benchmarks/x5h_mwmx_npu_apm80_1core.yaml CHANGED
@@ -57,7 +57,7 @@ reproduce:
57
  command: hf download Renesas/RetinaNet-R101-ONNX --repo-type model --include "fp32/*" "compile_config/*" --local-dir ./RetinaNet-R101-ONNX-fp32
58
  - title: Compile with the NNAC toolchain (INT8 auto-cast from the FP32 graph)
59
  command: |
60
- python3 nnac_frontend/legalize.py -d binary/nnx ./RetinaNet-R101-ONNX-fp32/fp32/retinanet-9.onnx --num-core 1 --network-config ./RetinaNet-R101-ONNX-fp32/compile_config/network_config_1core.yaml
61
  - title: Set up the R-Car X5H board
62
  command: Configure the board per the AI Compiler (NNAC) "Getting Started" guide, section 3.4 (host TFTP/NFS setup, bootloader flashing, U-Boot, Linux boot, login) -- exact steps depend on your board/network setup.
63
  kind: note
 
57
  command: hf download Renesas/RetinaNet-R101-ONNX --repo-type model --include "fp32/*" "compile_config/*" --local-dir ./RetinaNet-R101-ONNX-fp32
58
  - title: Compile with the NNAC toolchain (INT8 auto-cast from the FP32 graph)
59
  command: |
60
+ python3 nnac_frontend/legalize.py -d binary/nnx ./RetinaNet-R101-ONNX-fp32/fp32/retinanet-9.onnx --num-core 1 --network-config ./RetinaNet-R101-ONNX-fp32/compile_config/network_config_1core.yaml --enable-opt
61
  - title: Set up the R-Car X5H board
62
  command: Configure the board per the AI Compiler (NNAC) "Getting Started" guide, section 3.4 (host TFTP/NFS setup, bootloader flashing, U-Boot, Linux boot, login) -- exact steps depend on your board/network setup.
63
  kind: note
int8/benchmarks/x5h_mwmx_npu_apm80_3core.yaml CHANGED
@@ -57,7 +57,7 @@ reproduce:
57
  command: hf download Renesas/RetinaNet-R101-ONNX --repo-type model --include "fp32/*" "compile_config/*" --local-dir ./RetinaNet-R101-ONNX-fp32
58
  - title: Compile with the NNAC toolchain (INT8 auto-cast from the FP32 graph)
59
  command: |
60
- python3 nnac_frontend/legalize.py -d binary/nnx ./RetinaNet-R101-ONNX-fp32/fp32/retinanet-9.onnx --num-core 3 --network-config ./RetinaNet-R101-ONNX-fp32/compile_config/network_config.yaml
61
  - title: Set up the R-Car X5H board
62
  command: Configure the board per the AI Compiler (NNAC) "Getting Started" guide, section 3.4 (host TFTP/NFS setup, bootloader flashing, U-Boot, Linux boot, login) -- exact steps depend on your board/network setup.
63
  kind: note
 
57
  command: hf download Renesas/RetinaNet-R101-ONNX --repo-type model --include "fp32/*" "compile_config/*" --local-dir ./RetinaNet-R101-ONNX-fp32
58
  - title: Compile with the NNAC toolchain (INT8 auto-cast from the FP32 graph)
59
  command: |
60
+ python3 nnac_frontend/legalize.py -d binary/nnx ./RetinaNet-R101-ONNX-fp32/fp32/retinanet-9.onnx --num-core 3 --network-config ./RetinaNet-R101-ONNX-fp32/compile_config/network_config.yaml --enable-opt
61
  - title: Set up the R-Car X5H board
62
  command: Configure the board per the AI Compiler (NNAC) "Getting Started" guide, section 3.4 (host TFTP/NFS setup, bootloader flashing, U-Boot, Linux boot, login) -- exact steps depend on your board/network setup.
63
  kind: note
int8/benchmarks/x5h_mwmx_npu_apm80_4core.yaml CHANGED
@@ -57,7 +57,7 @@ reproduce:
57
  command: hf download Renesas/RetinaNet-R101-ONNX --repo-type model --include "fp32/*" "compile_config/*" --local-dir ./RetinaNet-R101-ONNX-fp32
58
  - title: Compile with the NNAC toolchain (INT8 auto-cast from the FP32 graph)
59
  command: |
60
- python3 nnac_frontend/legalize.py -d binary/nnx ./RetinaNet-R101-ONNX-fp32/fp32/retinanet-9.onnx --num-core 4 --network-config ./RetinaNet-R101-ONNX-fp32/compile_config/network_config.yaml
61
  - title: Set up the R-Car X5H board
62
  command: Configure the board per the AI Compiler (NNAC) "Getting Started" guide, section 3.4 (host TFTP/NFS setup, bootloader flashing, U-Boot, Linux boot, login) -- exact steps depend on your board/network setup.
63
  kind: note
 
57
  command: hf download Renesas/RetinaNet-R101-ONNX --repo-type model --include "fp32/*" "compile_config/*" --local-dir ./RetinaNet-R101-ONNX-fp32
58
  - title: Compile with the NNAC toolchain (INT8 auto-cast from the FP32 graph)
59
  command: |
60
+ python3 nnac_frontend/legalize.py -d binary/nnx ./RetinaNet-R101-ONNX-fp32/fp32/retinanet-9.onnx --num-core 4 --network-config ./RetinaNet-R101-ONNX-fp32/compile_config/network_config.yaml --enable-opt
61
  - title: Set up the R-Car X5H board
62
  command: Configure the board per the AI Compiler (NNAC) "Getting Started" guide, section 3.4 (host TFTP/NFS setup, bootloader flashing, U-Boot, Linux boot, login) -- exact steps depend on your board/network setup.
63
  kind: note
int8/benchmarks/x5h_mwmx_npu_apm80_6core.yaml CHANGED
@@ -57,7 +57,7 @@ reproduce:
57
  command: hf download Renesas/RetinaNet-R101-ONNX --repo-type model --include "fp32/*" "compile_config/*" --local-dir ./RetinaNet-R101-ONNX-fp32
58
  - title: Compile with the NNAC toolchain (INT8 auto-cast from the FP32 graph)
59
  command: |
60
- python3 nnac_frontend/legalize.py -d binary/nnx ./RetinaNet-R101-ONNX-fp32/fp32/retinanet-9.onnx --num-core 6 --network-config ./RetinaNet-R101-ONNX-fp32/compile_config/network_config.yaml
61
  - title: Set up the R-Car X5H board
62
  command: Configure the board per the AI Compiler (NNAC) "Getting Started" guide, section 3.4 (host TFTP/NFS setup, bootloader flashing, U-Boot, Linux boot, login) -- exact steps depend on your board/network setup.
63
  kind: note
 
57
  command: hf download Renesas/RetinaNet-R101-ONNX --repo-type model --include "fp32/*" "compile_config/*" --local-dir ./RetinaNet-R101-ONNX-fp32
58
  - title: Compile with the NNAC toolchain (INT8 auto-cast from the FP32 graph)
59
  command: |
60
+ python3 nnac_frontend/legalize.py -d binary/nnx ./RetinaNet-R101-ONNX-fp32/fp32/retinanet-9.onnx --num-core 6 --network-config ./RetinaNet-R101-ONNX-fp32/compile_config/network_config.yaml --enable-opt
61
  - title: Set up the R-Car X5H board
62
  command: Configure the board per the AI Compiler (NNAC) "Getting Started" guide, section 3.4 (host TFTP/NFS setup, bootloader flashing, U-Boot, Linux boot, login) -- exact steps depend on your board/network setup.
63
  kind: note