-
## Feature
Currently, MKLDNNFuser always starts a fusion group with a `aten::conv2d` operation. It replaces `aten::conv2d` with `prim::mkldnn_convolution` and inserts a conversion op (`aten::to_mkl…
-
## 🐛 Bug
The snippet below looks hacky, but it's how I'm approaching support for having the user control the `thunder.jit` call outside of Fabric: https://github.com/Lightning-AI/litgpt/pull/1204
…
-
Great work team!
Currently, I am pruning on the llama2-7b-chat-hf model from hugging face.
python main.py
> --model NousResearch/Llama-2-7b-chat-hf
> --prune_method wanda
> …
-
当我运行“python attack.py --attack TGR --batch_size 1 --model_name vit_base_patch16_224”命令时，报错为
C:\Users\xj\AppData\Local\Programs\Python\Python310\lib\site-packages\torch\nn\modules\module.py:1359: User…
-
Hi everyone,
I am trying to process a group of TerraSARX images with stackStripMap.py, I managed to generate the SLCs with unpackFrame_TSX.py.
I am trying to apply stackStripMap.py with the foll…
-
I get started Alphapose from training my model following examples in README.md:
`./scripts/train.sh ./configs/coco/resnet/256x192_res50_lr1e-3_1x.yaml exp_fastpose`
Everything seems perfect unti…
-
Hi, first of all let me congratulate you for this fantastic work.
After following the installation instructions I tried to run the usage example in cpu_mode
`python test.py --imgfile=example/sampl…
-
Taking the same code for Image Classification should work for `TensorTS` too:
```
@typedispatch
def plot_top_losses(x:TensorTS, y:TensorCategory, samples, outs, raws, losses, nrows=None, ncols=No…
-
When I run train.trainer() .here are much mistake.Can you meet this problem?
Building model
Building f_log_probs... Done
Building f_cost... Done
Building sentence encoder
Building image encoder…
-
While reading CIE (NFC reading) I got an error with the SAMSUNG SM-A300FU and authentication process fail.
I tested two different CIE cards on these apps:
1. IO App -> fails
1. INPS Mobile -> fai…