issues
search
PINTO0309
/
onnx2tf
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). I don't need a Star, but give me a pull request.
MIT License
712
stars
73
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
pre_explicit_broadcast should not expend scalar tensor
#573
peiciwu
closed
4 months ago
20
Facing onnx2tf converstion issue with resnet model mentioned in README
#572
akilesh2999
closed
10 months ago
1
0 trainable parameters
#571
julietaumpierrez
closed
10 months ago
1
improve flatc warning message
#570
spacycoder
closed
10 months ago
1
ValueError: Exception encountered when calling layer "tf.math.multiply_46" (type TFOpLambda).
#569
MuffinTopSJY
closed
7 months ago
1
Update README.md about converting ONNX to TF
#568
shyhyawJou
closed
10 months ago
3
Full int8 quantized model doesn't work when "flatc" is installed on the system
#567
spacycoder
closed
10 months ago
8
Add STFT op onnx2tf support
#566
guanerdan
closed
10 months ago
1
Error when onnx2tf: Floating point exception (core dumped)
#565
MuffinTopSJY
closed
7 months ago
11
Implement workaround for cases where the input tensor contains multiple undefined dimensions `Resize`
#564
PINTO0309
closed
10 months ago
0
Failed to convert Real-ESRGAN x4-general (NCHW)
#563
md-rifatkhan
closed
10 months ago
2
Added ability to optimize patterns with consecutive `ReLU` and `ReLU6`
#562
PINTO0309
closed
11 months ago
0
Support for onnx==1.15.0
#561
PINTO0309
closed
11 months ago
0
`-nodafsc`, `-eatfp16`
#560
PINTO0309
closed
11 months ago
0
Support for `Gelu`
#559
PINTO0309
closed
11 months ago
0
Fixed a bug that caused `-nodafsc` processing to be unconditionally skipped.
#558
PINTO0309
closed
11 months ago
0
Conversion of YoloV5, conversion of StridedSlice from 5d to 4d
#557
alpapstm32
closed
11 months ago
7
module 'tensorflow' has no attribute 'random' for tensorflow 2.15, but 2.14.0 does
#556
mprynce
closed
11 months ago
2
Conversion of ScatterND operator results in error
#555
AndreasBeering
closed
11 months ago
2
tf v2.15.0
#554
PINTO0309
closed
11 months ago
0
Add option for tflite float16 model
#553
ysohma
closed
11 months ago
2
SavedModel saved prior to TF 2.5 detected when loading Keras model.
#552
julietaumpierrez
closed
12 months ago
2
[ssdlite320_mobilenet_v3_large] Wrong shapes during inference
#551
zeyadkay
closed
7 months ago
2
yolov8-seg output transpose (0,3,1,2)
#550
ChenLiangChong
closed
1 year ago
5
I convert onnx to tensorflow use -osd option, saved_model wierd, almost every layer have many output
#549
allenliuvip
closed
11 months ago
2
Improve macOS compatibility via docker
#548
ysohma
closed
12 months ago
1
Add GitHub asset
#547
glenn-jocher
closed
1 year ago
0
Downgrade of ~10% on multiple weights of YoloX
#546
eladmeir
closed
11 months ago
7
onnx2tf `download_test_image_data()` S3 file connection error
#545
glenn-jocher
closed
1 year ago
3
Improved grid_sample
#544
AlexanderLutsenko
opened
1 year ago
1
Failed to convert model from segmentation_models_pytorch with dynamic shape
#543
hgaiser
closed
7 months ago
3
(1)Not correctly recognize depthwise_conv (2)-oiqt could not skip SavedModel
#542
AngLi666
closed
1 year ago
2
Created a custom wrapper class for Keras as a preliminary step to support TF v2.15.0.
#541
PINTO0309
closed
1 year ago
0
Onnx in tflite on Windows11
#540
Dmiriy
closed
1 year ago
2
Bug fixes in `Trilu`
#539
PINTO0309
closed
1 year ago
0
Trilu dtype error when using k greater than tensor dimension.
#538
kirant1994
closed
1 year ago
1
Bug fix for `--number_of_dimensions_after_flextranspose_compression` option.
#537
PINTO0309
closed
1 year ago
0
Yolov8 conversion to edgetpu for image sizes greater than 192x192
#536
Alan01252
closed
1 year ago
4
Improved stability of accuracy check process for unsearchable OPs in subgraphs
#535
PINTO0309
closed
1 year ago
0
If all axes are of different sizes and the axis sizes specified in axis are the same in onnx and TensorFlow, skip the accuracy check.
#534
PINTO0309
closed
1 year ago
0
Support for special max and min values for `Clip`
#533
PINTO0309
closed
1 year ago
0
Fixed an error when the input tensor was 1-dimensional during `Concat` accuracy correction.
#532
PINTO0309
closed
1 year ago
0
Fixed to skip accuracy check if one of the multiple input tensors contains `np.ndarray (constant)`
#531
PINTO0309
closed
1 year ago
0
Much stricter accuracy correction conditions for `Reshape`
#530
PINTO0309
closed
1 year ago
0
Fixed a critical bug in `Reshape`, `LayerNormalization` accuracy correction process
#529
PINTO0309
closed
1 year ago
0
Improved the high likelihood of accuracy degradation in `Concat` input tensors where all axes except the batch size are the same size.
#528
PINTO0309
closed
1 year ago
0
Improved processing speed of `MatMul` accuracy correction process
#527
PINTO0309
closed
1 year ago
0
Improved `BatchMatMul` transformation stability in the presence of undefined dimensions in the input tensor.
#526
PINTO0309
closed
1 year ago
0
Reduces the frequency of output shape mismatch
#525
PINTO0309
closed
1 year ago
0
Pilot implementation of `Col2Im`
#524
PINTO0309
closed
1 year ago
0
Previous
Next