Facing onnx2tf converstion issue with resnet model mentioned in README
akilesh2999 opened this issue · comments
Issue Type
Others
OS
Linux
onnx2tf version number
1.19.7
onnx version number
1.15.0
onnxruntime version number
1.16.3
onnxsim (onnx_simplifier) version number
0.4.30
tensorflow version number
2.15.0
Download URL for ONNX
https://github.com/PINTO0309/onnx2tf/releases/download/0.0.2/resnet18-v1-7.onnx
Parameter Replacement JSON
i think it is not needed
Description
- Personal development
2 . Error log -
error_log.txt
$ pip show tensorflow
Name: tensorflow
Version: 2.15.0.post1
onnx2tf -i resnet18-v1-7.onnx
INFO: input.5.beta: val: 1.0
INFO: output.1.output: name: tf.__operators__.add/AddV2:0 shape: (1, 1000) dtype: <dtype: 'float32'>
saved_model output started ==========================================================
saved_model output complete!
Summary on the non-converted ops:
---------------------------------
* Accepted dialects: tfl, builtin, func
* Non-Converted Ops: 48, Total Ops 89, % non-converted = 53.93 %
* 48 ARITH ops
- arith.constant: 48 occurrences (f32: 43, i32: 5)
(f32: 8)
(f32: 20)
(f32: 1)
(f32: 1)
(f32: 1)
(f32: 4)
(f32: 1)
(f32: 1)
(f32: 1)
Float32 tflite output complete!
Summary on the non-converted ops:
---------------------------------
* Accepted dialects: tfl, builtin, func
* Non-Converted Ops: 48, Total Ops 132, % non-converted = 36.36 %
* 48 ARITH ops
- arith.constant: 48 occurrences (f16: 43, i32: 5)
(f32: 8)
(f32: 20)
(f32: 43)
(f32: 1)
(f32: 1)
(f32: 1)
(f32: 4)
(f32: 1)
(f32: 1)
(f32: 1)
Float16 tflite output complete!