Skip to content

Issues: apple/coremltools

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

293 Open 1,052 Closed
293 Open 1,052 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Support for MLLMs such as LLaVA? question Response providing clarification needed. Will not be assigned to a release. (type)
#2224 opened May 20, 2024 by echo840
NaN results for PyTorch models on versions > 6.3.0 bug Unexpected behaviour that should be corrected (type)
#2223 opened May 17, 2024 by hjrnunes
x param of type int32 are cast to int16 for gather ops which should overflow, but doesn't bug Unexpected behaviour that should be corrected (type)
#2222 opened May 16, 2024 by 0seba
Convert Yolov8 to CoreML give different results bug Unexpected behaviour that should be corrected (type)
#2221 opened May 16, 2024 by X901
Failed to load _MLModelProxy: No module named 'coremltools.libcoremlpython question Response providing clarification needed. Will not be assigned to a release. (type)
#2220 opened May 16, 2024 by Asadashino-o
ARM64.whl not support on M3 ? question Response providing clarification needed. Will not be assigned to a release. (type)
#2219 opened May 13, 2024 by Xiaoyuan-Huang
1
ct.convert call appears to corrupt torchscript model bug Unexpected behaviour that should be corrected (type) PyTorch (traced) triaged Reviewed and examined, release as been assigned if applicable (status)
#2215 opened May 7, 2024 by carsonswope
1
About Image Input and Output. question Response providing clarification needed. Will not be assigned to a release. (type)
#2213 opened May 6, 2024 by jhl13
1
ValueError: Op "complex_stft_0_promoted" (op_type: cast) Input x="complex_stft_0" expects tensor or scalar of dtype from type domain ['fp16', 'fp32', 'int32', 'bool'] but got tensor[1,1025,250,complex64] bug Unexpected behaviour that should be corrected (type) PyTorch (traced)
#2212 opened May 3, 2024 by miku1958
1
Flexible input for MelSpectrogram: 'complex_shape' object has no attribute 'data' bug Unexpected behaviour that should be corrected (type) Flexible Shape PyTorch (traced) triaged Reviewed and examined, release as been assigned if applicable (status)
#2211 opened Apr 30, 2024 by twoertwein
Is there support to run ANE accelerated loops/while_loop? question Response providing clarification needed. Will not be assigned to a release. (type)
#2208 opened Apr 29, 2024 by 0seba
tf.random.uniform is optimized out when it shouldn't be bug Unexpected behaviour that should be corrected (type) tf2.x / tf.keras Issue could be related to tf2.x where coremltools isn't supported (component) triaged Reviewed and examined, release as been assigned if applicable (status)
#2204 opened Apr 24, 2024 by drubinstein
2
[ExecuTorch] Placeholder Assertion Error bug Unexpected behaviour that should be corrected (type) ExecuTorch triaged Reviewed and examined, release as been assigned if applicable (status)
#2199 opened Apr 16, 2024 by YifanShenSZ
1
support for torch.cdist missing layer type Unable to convert a layer type from the relevant framework PyTorch (traced) triaged Reviewed and examined, release as been assigned if applicable (status)
#2198 opened Apr 16, 2024 by SpiraMira
3
Support an aarch64 wheel feature request Functionality does not currently exist, would need to be created as a new feature (type)
#2195 opened Apr 15, 2024 by 4np
4
pytorch model is transformed into coreml model expect a tensor of type integer, but actually receive a tensor of type floating point. bug Unexpected behaviour that should be corrected (type) PyTorch (traced)
#2193 opened Apr 9, 2024 by yuqilol
1
[ExecuTorch] Cannot Use Dynamic Index to Select bug Unexpected behaviour that should be corrected (type)
#2189 opened Apr 5, 2024 by YifanShenSZ
1
[torch.jit.trace] Inplace Index Put Silent Error bug Unexpected behaviour that should be corrected (type) PyTorch (traced)
#2188 opened Apr 4, 2024 by YifanShenSZ
@YifanShenSZ
[ExecuTorch] IndexPut Fails on NeuralNetwork Backend bug Unexpected behaviour that should be corrected (type) ExecuTorch NN backend only Affects only the NN backend (not MIL backend)
#2185 opened Apr 4, 2024 by YifanShenSZ
@YifanShenSZ
[ExecuTorch] Cannot Convert Empty Model ExecuTorch feature request Functionality does not currently exist, would need to be created as a new feature (type) triaged Reviewed and examined, release as been assigned if applicable (status)
#2184 opened Apr 4, 2024 by YifanShenSZ
@YifanShenSZ
[ExecuTorch] Cannot Use Bool Index bug Unexpected behaviour that should be corrected (type) ExecuTorch triaged Reviewed and examined, release as been assigned if applicable (status)
#2183 opened Apr 4, 2024 by YifanShenSZ
@YifanShenSZ
1
AssertionError: Item selection is supported only on python list/tuple objects bug Unexpected behaviour that should be corrected (type) PyTorch (not traced)
#2176 opened Mar 26, 2024 by yash-codiste
6
Cuda Out of memory with DKMPalettizer ct.optimize Question/issue related to the coremltool's optimization package question Response providing clarification needed. Will not be assigned to a release. (type)
#2172 opened Mar 18, 2024 by coleridge72
1
Result of Flexible-input-shape Model is NAN bug Unexpected behaviour that should be corrected (type) Flexible Shape PyTorch (traced)
#2166 opened Mar 12, 2024 by jmcc113
4
official CoreML Unity plugin for Unity Polyspatial visionOS? feature request Functionality does not currently exist, would need to be created as a new feature (type)
#2165 opened Mar 11, 2024 by yosun
1
ProTip! Exclude everything labeled bug with -label:bug.