Sheng Wang issues

Repositories
Issues
Comments

Results 4 issues of


                                            Sheng Wang

Trained on small dataset with pre-trained weight, don't have good result.

``` pretrained_v = timm.create_model('vit_base_patch16_224', pretrained=True) pretrained_v.head = nn.Linear(768,2) ``` I tried Kaggle Cats vs Dogs Dataset for binary classification. Didn't work, output is all cat or all dog. Any idea...

test can't run

I run: ```python test_expVAE.py``` And get error as follows: ``` cuda available Traceback (most recent call last): File "test_expVAE.py", line 99, in main() File "test_expVAE.py", line 77, in main gcam.backward(mu,...

Is there any classification code?

LoRA做infer的时候用int4之后，模型性能会大幅度下降

重参数化是自己写的，想知道有人LoRA+int4成功的吗？