-
So I tried running your code on my dataset with a pre-trained ResNet50 model. I got these results
Full precision model i got accuracy of : MobileNetV2 (58.19)
Quantized model (W8A8) i got accuracy…
-
### 🐛 Describe the bug
```FlopCounterMode``` reports 0 FLOPS when the forward propagation has the inference mode enabled by ```torch.inference_mode()```. The counter works fine if I use ```torch_no_g…
-
Thank you for the repo! I can reproduce the SAN-10 pairwise / patchwise results. However, for the CNN baselines mentioned in this paper (i.e. ResNet-26, ResNet-38, ResNet-50), I wonder how they are tr…
-
Python version: 3.9.6
Operating System: Mac
## Description
I'm fine-tuning a model pre-trained with Vggface2 with the data I collected, but the accuracy doesn't improve.
If you have any optio…
-
xbw@xbw-P65xRP:~/FastMaskRCNN-master/train$ python train.py
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcublas.so.8.0 locally
I tensorflow/stream_executor/dso…
-
Hello, author. I am running test_Badnets.py for ResNet-18_CIFAR-10_BadNets with the following settings: a poisoning rate of 0.1 and training for 200 epochs. However, regardless of the number of epochs…
-
I tried using wide_resnet_imagenet64_1000, but found that it is giving zero accuracy. So, wanted to double check if this usage is correct. Here I am evaluating its natural accuracy on: Imagenet64_val…
-
When I try to save a ResNet18 model to ONNX with the `export_for_inference` function while providing the `apply_blurpool` surgery algorithm as well as the dynamic axes I get the following error:
``…
dneup updated
3 months ago
-
Right on the 60k iteration, I got this error, please suggest what might have been wrong. Can you also share your models for MPII human pose dataset? I basically followed all the instructions for train…
-
### Is there an existing issue for this?
- [x] I have searched the existing issues and checked the recent builds/commits
### What happened?
I've had this problem for a while. I've tried updating, d…