microsoft/onnxconverter-common

Issues

• Resize in FP16

  #306 opened 3 months ago by wejoncy
  0

• Vulnerability due to pinned protobuf package

  #303 opened 3 months ago by famenzel
  1

• Release a version to pypi with protobuf version unpinned

  #300 opened 4 months ago by griffindore
  1

• Float mismatch error after float16 quantization ：Data in initializer 'onnx::Add_2877' has element type tensor(float16) but usage of initializer in graph expects tensor(float)

  #304 opened 3 months ago by majisama
  1

• Integrate with ONNX 1.17.0 release branch

  #302 opened 4 months ago by roborags
  0

• Meaning of warning: The maximum opset needed by this model is only

  #301 opened 4 months ago by ogencoglu
  0

• fp16精度在/norm/ReduceMean_output_0节点返回nan

  #299 opened 5 months ago by 13484835805
  1

• Max supported opset is very old

  #296 opened 6 months ago by addisonklinke
  5

• 👋Version update ？

  #298 opened 6 months ago by juntaosun
  0

• ValueError: Validation Failed

  #297 opened 6 months ago by RhinoInani
  0

• max_finite_val default value

  #295 opened 6 months ago by haowang5128
  0

• New release

  #292 opened 7 months ago by gdippolito
  1

• convert to FP16 generate orphan and self-recurring nodes

  #276 opened 10 months ago by ttyio
  2

• [Error] Load fp16

  #287 opened 8 months ago by phamkhactu
  2

• Performance degrade after sess_options.enable_profiling = True

  #267 opened a year ago by Jay19751103
  1

• convert float32 model to float16, but memory usage has not decreased

  #289 opened 8 months ago by kukugpt
  5

• protobuf version

  #265 opened 8 months ago by OKUA1
  4

• onnxconverter_common.auto_mixed_precision.auto_convert_mixed_precision never ends

  #251 opened 2 years ago by FrancescoSaverioZuppichini
  1

• convert_float_to_float16() produces a model that causes ValidationError with onnx.checker.check_model()

  #256 opened 2 years ago by SergeySandler
  6

• Converting model fp32 to fp16 with auto_mixed_precision_model_path from gets NaN

  #249 opened 2 years ago by taoisu
  1

• `auto_convert_mixed_precision` Error: two nodes with same node name error occurred during

  #259 opened a year ago by KunMengcode
  5

• FP16 conversion yields an unusable model

  #266 opened a year ago by eddieevt-DXC
  2

• Is there any upgrades on onnxconverter-common?

  #270 opened a year ago by hanzigs
  1

• resize op convert to FP16 fail

  #272 opened a year ago by nistarlwc
  4

• #Onnx Quantisation

  #273 opened 10 months ago by vanditha18
  2

• Integrate with ONNX 1.16.0 release branch

  #277 opened 8 months ago by cjvolzka
  1

• Redundant dependencies in requirements.txt

  #250 opened 8 months ago by jonathanunderwood
  1

• Documentation

  #264 opened 8 months ago by laclouis5
  1

• Extra Cast nodes causes overflow in onnxruntime 1.17

  #271 opened 8 months ago by tianleiwu
  1

• How to convert a model to mixed precision?

  #252 opened 9 months ago by FrancescoSaverioZuppichini
  21

• FP16 model can not get acceleration on GPU with ONNXRuntime-GPU

  #255 opened 9 months ago by yeliang2258
  2

• Add `convert_float_to_bfloat16` function to avoid overflow

  #268 opened a year ago by vraintanakarei
  0

• Failing tests

  #242 opened 2 years ago by FRidh
  3

• onnx.onnx_cpp2py_export.checker.ValidationError: Nodes in a graph must be topologically sorted, however input 'Resize__139_input_cast_1' of node: name: Resize__139 OpType: Resize is not output of any previous nodes.

  #261 opened a year ago by 1615070057
  2

• Issues when converting model to float16

  #208 opened 2 years ago by toothache
  3

• Inference issue after convert_float_to_float16

  #200 opened 2 years ago by leqiao-1
  2

• 1.12.2 version released？

  #245 opened 2 years ago by philipwan
  1

• Fp32-->fp16: original fp32 model works well with input data, but converted fp16 model failed with the same input data

  #196 opened 2 years ago by yetingqiaqia
  0

• Source tarball for v1.9.0 republished?

  #204 opened 2 years ago by iarspider
  0

• Add bounds warning to FP16 conversion script

  #211 opened 2 years ago by kevinch-nv
  1

• Error: onnx.onnx_cpp2py_export.checker.ValidationError: Nodes in a graph must be topologically sorted, however input 'TopK_111_input_cast_0' of node:

  #240 opened 2 years ago by seungtaek94
  1

• `Unsupported shape calculation for operator mlProgram` while using `onnxmltools.convert_coreml`

  #241 opened 2 years ago by KOLANICH
  1

• F16 file does not convert correctly

  #207 opened 2 years ago by hardik124
  3

• Problem of converting model from 32-bit to 16-bit

  #238 opened 2 years ago by MuxiRabbit
  1

• StrictVersion is deprecated

  #220 opened 2 years ago by xiaowuhu
  1

• Security Development Lifecycle review for 2022-06

  #213 opened 2 years ago by garymm
  2

• "No space left on device" issue on auto_convert_mixed_precision_model_path()

  #229 opened 2 years ago by yetingqiaqia
  1

• add NOTICE file to onnxconverter-common

  #227 opened 2 years ago by xiaowuhu
  1

• verify onnx 1.12.0 rc

  #218 opened 3 years ago by xiaowuhu
  3

• auto_convert_mixed_precision() doesn't support >2GB model

  #215 opened 3 years ago by yetingqiaqia
  2