-
I'm trying to train the model on PASCAL 2012, however, the model doesn't seem to converge with my settings (Batch size: 2, Rezolution: 416). This is the highest batch size I could go without my GPU me…
-
I try to reproduce the results with the following cmd, modified from the readme:
```bash
CUDA_VISIBLE_DEVICES=7,6,5,4 python train_net_dshmp.py --config-file configs/dshmp_swin_tiny.yaml --nu…
-
### System Info
requirements file:
```
transformers[torch]==4.44.2
onnxruntime
-
Can you include the weights for a trained model?
-
Currently, when someone identifies a blind spot for KataGo, they post about it here on GitHub. While helpful, this approach feels somewhat inefficient.
I propose the creation of a dedicated platfor…
-
I have been using the cordova face-api project together,
when I'm loading the MODELS, I come across the following errors:
CODE - 1:
net.load(await faceapi.fetchNetWeights('file:///android_asset/…
-
**Describe the bug**
I have a major issue that I have seen in lot of the cases on other trial. The MLX training gives rarely a good performance while for torch and keras it is more stable and better.…
-
I'm trying to train my network on my own images, but after ~16h (after training was complete) I realized that not a single model was saved to the weights directory.
This is the code I'm running (b…
-
Hi,
I have an RT-DETR (l) model trained using ultralytics. Naturally, I used the ultralytics-rtdetr script to get an ONNX file. As I wanted a dynamic batch size, I use
```console
python3 rtdetr_…
-
I ran into the following problem when converting `densenet121_baseline_att_256x256_B_epoch_160.pth` and also `resnet18_baseline_att_224x224_A_epoch_249.pth` into a trt model, which appears to be due…