leovinus2001

PyTorch to CoreML BatchNorm model SCRIPT conversion v4 fails with "temporary: the only valid use of a module is looking up an attribute but found = prim::SetAttr[name="num_batches_tracked"](%13, %80)"

4

Relevance:----------------------------------------------------------- Firstly, while the JIT conversion of the attached test modeland code works fine, the torch.jit.script() fails on the BatchNorm conversion. The conversion of both BatchNorm1D and BatchNorm2D fails which...

PyTorch to CoreML model conversion does not handle the torch tensor narrow() operation.

7

Title: PyTorch to CoreML model conversion does not handle the torch tensor narrow() operation. Relevance: See the question I filed for coremltools titled "Cannot properly convert PyTorch model to .mlmodel...

Objective: Advise the coremltools converter that the sequence length of the input is variable size. Useful in the context of LSTM, Transformers and other setups. Reproducible: Yes, all issues are...

PyTorch to CoreML model conversion via scripting (torch.jit.script) gives 3 different errors (missing op 'dim', IndexError: out of Range, and INTERNAL ERROR)

4

Title: PyTorch to CoreML model conversion via scripting (torch.jit.script) gives error messages. Relevance: For certain models, torch scripting is preferred over the JIT trace as explained here https://coremltools.readme.io/docs/model-scripting When we...

PyTorch to CoreML model conversion does not handle torch.randn_like(), missing op (ERROR: PyTorch convert function for op randn_like not implemented)

3

Relevance: This function is used in some Variational Autoencoders (VAE) models, e.g., the example from PyTorch docs at https://github.com/pytorch/examples/blob/master/vae/main.py Reproducible: Yes Testcase: Attached Setup: Torch version : 1.5.0 CoreML tools...

While there are many documentation links (thanks), I haven't had to handle punchcards and drums for decades. Therefore, could you be a bit more explicit for a simple example program...