-
Nils is it possible to create an integer only models so this could run on accelerators or frameworks such as ArmNN?
https://www.tensorflow.org/lite/performance/post_training_quantization#full_integer…
-
Layer: https://codgis.itos.uga.edu/arcgis/rest/services/COD_External/QAT_pcode/
Proposed fix: https://data.fieldmaps.io/cod/originals/qat.shp.zip
Issue: Layer used to exist and has now disappear…
-
hi，in the paper you said “we use 4096 samples from RedPajama with a context length of 2048”， is it enough
for QAT?
-
Hi, I want to do QAT for a fine-tuned model. I don't know what to choose as the calib dataset. Do you have any suggestions? And does it achieve the same results as the pre-trained model mentioned in t…
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and fou…
-
When using a network that splits the tensor at some point in the network into two pieces, I run into a problem. The `torch.split` operator is not supported, so I rewrote it using two slices:
```
b =…
-
hi, openscanhub code security scanner reports a number of resource leaks in the qatengine code:
Defect type: RESOURCE_LEAK
QAT_Engine-1.6.0/qat_hw_ecx.c:557:13: leaked_storage: Freeing "key" witho…
-
hi
when I want to generate c files I get this error "the checkpoint file contains 1-dimensional weights for `conv1.bn.weight` with dimensions (24,). Ensure the BatchNorm layers have been folded."
…
-
### Have I written custom code (as opposed to using a stock example script provided in MediaPipe)
None
### OS Platform and Distribution
Kaggle
### Python Version
3.10.13
### MediaPipe Model Mak…
-
Hello, for my application I have been able to generate the C code using the synthesizer tool. But while testing the code on the hardware, the KAT fails with the `Data mismatch` error.
The sample in…