|
Comparison between saving the whole model, saving only state_dict and torchscript
|
|
3
|
534
|
January 25, 2024
|
|
RuntimeError: torch.linalg.lu_factor: (Batch element 1): U[4,4] is zero and using it on lu_solve would result in a division by zero. If you still want to perform the factorization, consider calling linalg.lu(A, pivot) or linalg.lu_factor_ex(A, pivot)
|
|
0
|
176
|
January 23, 2024
|
|
Having troubles to vmap a custom function with permute
|
|
0
|
223
|
January 20, 2024
|
|
Nondeterminstic behaviour of sigmoid and tanh in JIT script
|
|
1
|
199
|
January 19, 2024
|
|
How to calculate FLOPS of a JIT model?
|
|
1
|
388
|
January 18, 2024
|
|
Converting GPT-2 to TorchScript
|
|
5
|
1031
|
December 30, 2023
|
|
About initialization of RecursiveScriptModule instance?
|
|
0
|
208
|
December 29, 2023
|
|
Access to model parameters
|
|
5
|
423
|
December 26, 2023
|
|
Jit tracing failing (torch mangling diverging operator)
|
|
0
|
290
|
December 24, 2023
|
|
Fully convolutional jit module variable input libtorch
|
|
4
|
361
|
December 20, 2023
|
|
Cannot save model
|
|
2
|
339
|
December 11, 2023
|
|
Traced/Scripted models do not produce same output as eager models when weights are loaded
|
|
5
|
1033
|
December 10, 2023
|
|
NaN in gradients when using jit.script
|
|
0
|
230
|
December 6, 2023
|
|
JIT function changed the default encoding of the built-in `open`
|
|
1
|
276
|
November 16, 2023
|
|
Spliting model into three wihle JIT tracing
|
|
0
|
236
|
November 16, 2023
|
|
Pytorch model and exported ONNX differs in inference
|
|
0
|
266
|
November 14, 2023
|
|
Convert fasterrcnn_resnet50_fpn to torchscript
|
|
5
|
1890
|
November 2, 2023
|
|
Torchscript jit scripting & Faster rCNN issue
|
|
0
|
244
|
October 31, 2023
|
|
Converting Deeplabv3 for inference
|
|
9
|
379
|
October 28, 2023
|
|
Saving a Pytorch neural net (torch.autograd.grad included) as a Torch Script code
|
|
0
|
295
|
October 26, 2023
|
|
Get error "tuple index with non-constant index" when trying to export a model to onnx format
|
|
1
|
481
|
October 26, 2023
|
|
[jit][script] torch.jit.script(), UnsupportedNodeError returns NoneType error
|
|
1
|
818
|
October 25, 2023
|
|
Using TorschScript to save a model with multiple heads
|
|
1
|
1081
|
October 9, 2023
|
|
Error converting .pth to .pt, Could not export Python function call 'Scatter'?
|
|
0
|
334
|
September 27, 2023
|
|
Detect CUDA graph capture in a TorchScript model
|
|
0
|
307
|
September 18, 2023
|
|
Better stack trace for jit error messages
|
|
1
|
690
|
September 15, 2023
|
|
Modify Loaded TorchScript Model
|
|
0
|
321
|
September 15, 2023
|
|
The result generated by trace immediately is different with the result generated by trace loaded
|
|
0
|
268
|
September 12, 2023
|
|
Unable to compile RAFT model in torch_tensorrt
|
|
2
|
757
|
September 12, 2023
|
|
Should adding @torch.jit.export annotation on a single method make it export all module properties?
|
|
2
|
405
|
September 6, 2023
|