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
706
stars
73
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Bloated Full Integer Quant TFLite file
#724
Y-T-G
opened
3 days ago
0
Unet Int8 quatiesation
#723
ElectroMonk
closed
1 week ago
1
When my model is conv3d, avgpool3d seems to have some issues
#722
jungyin
closed
3 days ago
8
issue converting clip onnx float model to tflite
#721
tensorbuffer
closed
2 weeks ago
5
Unable to convert Phi-3.5-mini-instruct-onnx to tflite format
#720
beefho67
closed
3 weeks ago
1
Fix/style fixes
#719
kwikwag
opened
1 month ago
1
renamed replace_GRU.json to allow cloning to Windows
#718
kwikwag
closed
1 month ago
0
add output_saved_model flag
#717
kwikwag
opened
1 month ago
3
[LaMa] Matmul
#716
slowlyideal
closed
1 month ago
2
Multi batch quant
#715
PINTO0309
closed
1 month ago
0
Problem of quantization with batch_size 2
#714
WildTaras
closed
1 month ago
5
Problem of yolov8 convertion using dynamic batch_size or static batch_size=2
#713
WildTaras
closed
1 month ago
5
Added `Float32` option
#712
PINTO0309
closed
1 month ago
0
Fixed mistake of #710
#711
marcoschepis
closed
1 month ago
1
Float32 in quantization
#710
marcoschepis
closed
1 month ago
0
Is it possible to control scale and zero point of full integer quantized (INT8) tflite model during conversion?
#709
deltacosos
closed
1 month ago
5
Update `replace_slice.json` reference
#708
emmanuel-ferdman
closed
1 month ago
1
Add `--builtins_only` Flag to CLI for generating TFLITE_BUILTINS-Only TensorFlow Lite Models
#707
JihwanEom
opened
1 month ago
3
Comment fix. `input_quant_dtype`, `output_quant_dtype`
#706
PINTO0309
closed
1 month ago
0
Improved conversion stability of `Mul`
#705
PINTO0309
closed
1 month ago
0
Supports parameter substitution for post-processing of `Conv`
#704
PINTO0309
closed
1 month ago
8
Updated README.md
#703
marcoschepis
closed
1 month ago
1
README corrections due to API changes (I'll get serious from tomorrow)
#702
PINTO0309
closed
1 month ago
2
Input and output quantization chosen separately
#701
marcoschepis
closed
1 month ago
2
Add transposition to the tflite model
#700
pipipyau
closed
1 month ago
5
Fixed to force switch between `X` and `Y` when X: `np.ndarray`, Y: `Tensor`
#699
PINTO0309
closed
1 month ago
0
Error by broadcasting in tf.math.Multiply Operation
#698
JihwanEom
closed
1 month ago
6
Dealing with quantized onnx - ie int8; mixed int8/fp32; etc
#697
Alexey234432
closed
1 month ago
2
Dealing with garbage-like broken structures in ONNX (ArgMin) #695
#696
PINTO0309
closed
1 month ago
0
Dealing with garbage-like broken structures in ONNX
#695
PINTO0309
closed
1 month ago
0
[YOLOv7] None in graph_node_input.shape
#694
MichaelMonashev
closed
1 month ago
9
Confusion about "Quantization error simulation of SiLU(Swish) Activation"
#693
Reciphon
closed
2 months ago
4
Improved handling when `axis` attribute is not defined and the batch size of the first dimension is undefined.
#692
PINTO0309
closed
2 months ago
0
Update to improve mAP ?
#691
PetiteFleurPF
closed
2 months ago
2
Improved the conversion stability of `BatchNormalization`.
#690
PINTO0309
closed
2 months ago
0
Addressed the issue of missing conversions when multi-dimensional flattening is performed and the batch size of the first dimension is an undefined dimension.
#689
PINTO0309
closed
2 months ago
0
[EfficientNetV2_m] Output size is constant not variable
#688
Eddudos
closed
2 months ago
3
Wrong shape converted for GIST-all-MiniLM-L6-v2
#687
superjackie
closed
2 months ago
3
Fixed a bug in the optimization process for arithmetic operations
#686
PINTO0309
closed
2 months ago
0
Model gives inaccurate results post conversion to tflite
#685
AD-lite24
closed
2 months ago
9
RuntimeError: Quantized dimension for tensor property and quantization parameters do not match. Got 3 and 0 respectively.
#684
ambitious-octopus
closed
2 months ago
2
int8 version of mobilenetv3 has bad accuracy
#683
ogvalt
closed
2 months ago
1
Fixed problem of being stuck in an infinite loop
#682
PINTO0309
closed
2 months ago
0
An input to an ADD node keeps getting casted to float32 despite being float16 in the onnx file causing issues with the ADD op
#681
AD-lite24
closed
2 months ago
17
[Question] Quantized ONNX to Quantized TFLite
#680
Illia-tsar
closed
3 months ago
5
Improvement of huge model transformation (implementation of Out of Memory workaround)
#679
PINTO0309
opened
3 months ago
0
Can it support mixed precision quantization: one part with full int8 quantized and the rest with int16_act quantized
#678
hayyaw
closed
3 months ago
1
yolov8n onnx to tflite without transpose ops
#677
codewarrior26
closed
3 months ago
2
[YOLOvN] failed tf to tflite convertion
#676
R4Ajeti
closed
3 months ago
4
Automatic accuracy compensation `Expand`, `BatchNormalization`, `Gather`
#675
PINTO0309
closed
4 months ago
0
Next