Onnx2tf

- `Reshape`, `Transpose`
- Special support for ShuffleNet patterns
- `5D Reshape -> 5D Transpose -> 4D Reshape`
- e.g. `1,2,72,16,16 -> 1,72,2,16,16 -> 1,144,16,16`
- At this time, only the channel shuffling pattern of image processing is supported.
- [[nanodet-plus] Conv layer shape wrong 15](https://github.com/PINTO0309/onnx2tf/issues/15)

|ONNX|TFLite|
|:-:|:-:|
|||

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.28...1.1.29

- Bug fixes. [Question about channel_transpose in common_functions.py 18](https://github.com/PINTO0309/onnx2tf/issues/18)
- Bug fixes. [bug fix in explicit_broadcast 20](https://github.com/PINTO0309/onnx2tf/pull/20)
- Replaced `:` in OP names that cause errors when outputting saved_model with `_`.

- Validated model (without replacement.json) - **Models for which no license file is explicitly posted should follow the license of the cited paper implementation.**
- https://github.com/onnx/models
- https://github.com/opencv/opencv_zoo
|No.|Model|Pass|
|:-:|:-|:-:|
|1|age_googlenet.onnx|:heavy_check_mark:|
|2|alike_t_opset11_192x320.onnx|:heavy_check_mark:|
|3|arcfaceresnet100-8.onnx|:heavy_check_mark:|
|4|baseline_simplified.onnx|:heavy_check_mark:|
|5|big_slice_11.onnx|:heavy_check_mark:|
|6|bvlcalexnet-12.onnx|:heavy_check_mark:|
|7|caffenet-12.onnx|:heavy_check_mark:|
|8|convtranspose_3_1_5_2.onnx|:heavy_check_mark:|
|9|convtranspose_4_5_2_2.onnx|:heavy_check_mark:|
|10|convtranspose_5_5_6_1.onnx|:heavy_check_mark:|
|11|convtranspose_6_5_5_8.onnx|:heavy_check_mark:|
|12|convtranspose_7_1_3_4.onnx|:heavy_check_mark:|
|13|damoyolo_tinynasL20_T_192x192_post.onnx|:heavy_check_mark:|
|14|deeplabv3_mobilenet_v3_large.onnx|:heavy_check_mark:|
|15|densenet-12.onnx|:heavy_check_mark:|
|16|depth_to_spase_17.onnx|:heavy_check_mark:|
|17|double_gru.onnx|:heavy_check_mark:|
|18|digits.onnx|:heavy_check_mark:|
|19|detr_demo.onnx|:heavy_check_mark:|
|20|efficientformer_l1.onnx|:heavy_check_mark:|
|21|efficientdet_lite2_detection_1.onnx|:heavy_check_mark:|
|22|efficientnet-lite4-11_nchw.onnx|:heavy_check_mark:|
|23|effnet_opset11_dynamic_axis.onnx|:heavy_check_mark:|
|24|emotion-ferplus-8_rename.onnx|:heavy_check_mark:|
|25|face_detection_yunet_2022mar.onnx|:heavy_check_mark:|
|26|face_recognition_sface_2021dec-act_int8-wt_int8-quantized.onnx|:heavy_check_mark:|
|27|face_recognition_sface_2021dec.onnx|:heavy_check_mark:|
|28|faster_rcnn-10.onnx|:heavy_check_mark:|
|29|fastestdet.onnx|:heavy_check_mark:|
|30|fused_conv_clip.onnx|:heavy_check_mark:|
|31|fused_conv_hardsigmoid.onnx|:heavy_check_mark:|
|32|fused_conv_leakyrelu.onnx|:heavy_check_mark:|
|33|fused_conv_relu.onnx|:heavy_check_mark:|
|34|fused_conv_sigmoid.onnx|:heavy_check_mark:|
|35|fused_conv_tanh.onnx|:heavy_check_mark:|
|36|gender_googlenet.onnx|:heavy_check_mark:|
|37|gmflow-scale1-mixdata-train320x576-4c3a6e9a_1x3x480x640_bidir_flow_sim.onnx|:heavy_check_mark:|
|38|handpose_estimation_mediapipe_2022may.onnx|:heavy_check_mark:|
|39|htnet_1x17x2_without_norm.onnx|:heavy_check_mark:|
|40|iat_llie_180x320.onnx|:heavy_check_mark:|
|41|if_p1_11.onnx|:heavy_check_mark:|
|42|if_p2_11.onnx|:heavy_check_mark:|
|43|if_p3_11.onnx|:heavy_check_mark:|
|44|imageclassifier.onnx|:heavy_check_mark:|
|45|inception-v2-9.onnx|:heavy_check_mark:|
|46|inverse11.onnx|:heavy_check_mark:|
|47|mhformer_NxFxKxXY_1x27x17x2.onnx|:heavy_check_mark:|
|48|mnist.onnx|:heavy_check_mark:|
|49|mnist-12.onnx|:heavy_check_mark:|
|50|mobilenetv2-12.onnx|:heavy_check_mark:|
|51|mosaic_11.onnx|:heavy_check_mark:|
|52|mosaic-9.onnx|:heavy_check_mark:|
|53|movenet_multipose_lightning_192x256_p6.onnx|:heavy_check_mark:|
|54|nanodet-plus-m_416.onnx|:heavy_check_mark:|
|55|object_tracking_dasiamrpn_kernel_cls1_2021nov.onnx|:heavy_check_mark:|
|56|object_tracking_dasiamrpn_kernel_r1_2021nov.onnx|:heavy_check_mark:|
|57|object_tracking_dasiamrpn_model_2021nov.onnx|:heavy_check_mark:|
|58|pidnet_S_cityscapes_192x320.onnx|:heavy_check_mark:|
|59|ppmattingv2_stdc1_human_480x640.onnx|:heavy_check_mark:|
|60|qlinear_conv_tensor_test.onnx|:heavy_check_mark:|
|61|rcnn-ilsvrc13-9.onnx|:heavy_check_mark:|
|62|regnet_x_400mf.onnx|:heavy_check_mark:|
|63|ResNet101-DUC-12.onnx|:heavy_check_mark:|
|64|resnet18-v1-7.onnx|:heavy_check_mark:|
|65|resnet50-v1-12.onnx|:heavy_check_mark:|
|66|resnet50-v2-7.onnx|:heavy_check_mark:|
|67|retinanet-9.onnx|:heavy_check_mark:|
|68|sinet_320_op.onnx|:heavy_check_mark:|
|69|squeezenet1.0-12.onnx|:heavy_check_mark:|
|70|super-resolution-10.onnx|:heavy_check_mark:|
|71|swinir-m_64x64_12.onnx|:heavy_check_mark:|
|72|text_recognition_CRNN_EN_2021sep.onnx|:heavy_check_mark:|
|73|tinyyolov2-8.onnx|:heavy_check_mark:|
|74|version-RFB-640.onnx|:heavy_check_mark:|
|75|vit-b-32_textual.onnx|:heavy_check_mark:|
|76|vit-b-32_visual.onnx|:heavy_check_mark:|
|77|yolact_edge_mobilenetv2_550x550.onnx|:heavy_check_mark:|
|78|yolact_regnetx_600mf_d2s_31classes_512x512.onnx|:heavy_check_mark:|
|79|yolact_regnetx_800mf_20classes_512x512.onnx|:heavy_check_mark:|
|80|yolo_free_nano_crowdhuman_192x320_post.onnx|:heavy_check_mark:|
|81|yolov7_tiny_head_0.768_post_480x640.onnx|:heavy_check_mark:|
|82|yolox_nano_192x192.onnx|:heavy_check_mark:|
|83|yolox_nano_416x416.onnx|:heavy_check_mark:|
|84|yolox_s.onnx|:heavy_check_mark:|
|85|yolox_x_crowdhuman_mot17_bytetrack.onnx|:heavy_check_mark:|
|86|zero_dce_640_dele.onnx|:heavy_check_mark:|
|87|zfnet512-12.onnx|:heavy_check_mark:|

What's Changed
* bug fix in explicit_broadcast by Hyunseok-Kim0 in https://github.com/PINTO0309/onnx2tf/pull/20

New Contributors
* Hyunseok-Kim0 made their first contribution in https://github.com/PINTO0309/onnx2tf/pull/20

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.27...1.1.28

- `explicit_broadcast`
- Supports some undefined dimensions (UNK, None)
- [Question about channel_transpose in common_functions.py 18](https://github.com/PINTO0309/onnx2tf/issues/18)
- Simply implementing the method suggested by Hyunseok-Kim0 could not handle UNK (undefined dimension), so I improved the process
- [human_segmentation_pphumanseg_2021oct.onnx](https://github.com/PINTO0309/onnx2tf/releases/download/1.1.27/human_segmentation_pphumanseg_2021oct.onnx)
- [replace.json](https://github.com/PINTO0309/onnx2tf/releases/download/1.1.27/replace.json)

- Support for `keep_shape_absolutely_input_names option`

-kat KEEP_SHAPE_ABSOLUTELY_INPUT_NAMES [KEEP_SHAPE_ABSOLUTELY_INPUT_NAMES ...], \
--keep_shape_absolutely_input_names KEEP_SHAPE_ABSOLUTELY_INPUT_NAMES \
[KEEP_SHAPE_ABSOLUTELY_INPUT_NAMES ...]
Name of the INPUT that unconditionally maintains its shape.
If a nonexistent INPUT OP name is specified, it is ignored.
e.g. --keep_shape_absolutely_input_names "input0" "input1" "input2"

- Non-brute-force checking part of `explicit_broadcast`
- [18 Non-brute-force checking part of explicit_broadcast](https://github.com/PINTO0309/onnx2tf/issues/18)
- Improved visibility of debug logs

---


What's Changed
* Non-brute-force checking part of explicit_broadcast by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/19


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.25...1.1.26

- Support for `Hardmax`

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.24...1.1.25

- `ConvTranspose`
- Bug fixes
- `BatchNormalization`
- Bug fixes
- [Batchnorm after convtranspose converted to wrong bias 16](https://github.com/PINTO0309/onnx2tf/issues/16)

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.23...1.1.24