-
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."
…
-
📚 This guide explains how to **freeze** YOLOv5 🚀 layers when **transfer learning**. Transfer learning is a useful way to quickly retrain a model on new data without having to retrain the entire networ…
-
### 🚀 The feature, motivation and pitch
All T5 models and their derivatives (t5, mt5, t0, etc.) use `RMSNorm`, instead of `LayerNorm`. The former is a subset of the latter, it only scales and doesn…
-
### 🐛 Describe the bug
I'm trying to build PyTorch 1.8.2 wheel but failed to link CXX shared library lib/libtorch_cuda.so due to `tmpxft_00008487_00000000-6_THCStorage.compute_86.cudafe1.cpp:(.text…
-
Is it possible to support conv-bn fold with [QDQ](https://onnxruntime.ai/docs/performance/model-optimizations/quantization.html#onnx-quantization-representation-format) node inserted and bn-conv fold…
-
Hi, I think it's really amazing the work you've done, congrats!! For my thesis project, I would like to use your network to analyze point cloud data, so right now what I have is only a series of .pcd …
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar bug report.
### YOLOv8 Component
Detection
### Bug
```
…
-
Hi,
I changed gap_sdk version into 4.22.0. (why I must use gap_sdkv4.22.0,pls see here[gap_sdk/issues/370](https://github.com/GreenWaves-Technologies/gap_sdk/issues/370))
But when I tried to run`mak…
-
## 🐛 Bug
## To Reproduce
Steps to reproduce the behavior:
I ran the following code:
1. conda create detectron2 python=3.7
2. conda activate detectron2
3. conda install numpy ninja py…
-
**Describe the bug**
Context parallel does not work in some cases, such as pretrain llama-34b with 64 A800 GPUs and seqlen>=32768. **But using megatron-lm directly has no problem with the same conf…
XLzed updated
4 months ago