Tramac
Tramac
Hi, thanks for the great work! When i set `results = saliency.get_image_saliency_results(model, img, input_tensor, prediction_tensor), methods=['gradcam', 'smooth_grad']` in [`cnn_pred_explain.ipynb `](https://github.com/microsoft/tensorwatch/issues/new), Error happend: ``` Traceback (most recent call last): File "debug.py",...
When will [`if num_picks == 0:`](https://github.com/KaiyangZhou/pytorch-vsumm-reinforce/blob/fdd03be93f090278424af789c120531e49aefa40/rewards.py#L20) in `reward.py` be executed? It seems impossible to equal 0 because of these code [`num_picks = len(pick_idxs) if pick_idxs.ndimension() > 0 else 1`](https://github.com/KaiyangZhou/pytorch-vsumm-reinforce/blob/fdd03be93f090278424af789c120531e49aefa40/rewards.py#L18).
The model does not converge on other datasets, do you have any advice? where `epochs=60, backbone=resnet50, lr=0.00001`.
Hi, thank you for the wonderful work! I want to know is it possible to complete functions `scaled_l2` and `aggerage` in `Encoding` ?
img_group shape=`(4, 3, 10, 224, 224)` # NCTHW After operator: [img_group.reshape((-1,) + img_group.shape[2:])](https://github.com/decisionforce/TPN/blob/117a4d187517f51ea914b17be8ac59ef1a36b594/mmaction/models/recognizers/TSN3D.py#L94), the shape of x is: `(12, 10, 224, 224)`, and leads to the error above in [here](https://github.com/decisionforce/TPN/blob/117a4d187517f51ea914b17be8ac59ef1a36b594/mmaction/models/tenons/backbones/resnet_slow.py#L397)....
start server: `python3 main.py --listen` ``` Total VRAM 32510 MB, total RAM 51200 MB Set vram state to: NORMAL_VRAM Device: cuda:0 Tesla V100-PCIE-32GB : cudaMallocAsync VAE dtype: torch.float32 Using pytorch...
`cross_relationship_score` values in eval mode:  it's so confused.
### Describe the bug When I create a dataset, it gets stuck while generating cached data. The image format is PNG, and it will not get stuck when the image...
Hello, the size of image in the VOC is different. there seems to be no function to crop the image in [`transform`](https://github.com/L1aoXingyu/fcn.pytorch/blob/master/data/transforms/transforms.py). How is this part handled?
Thanks for your error report and we appreciate it a lot. **Checklist** * I have searched the tutorial on modelscope [doc-site](https://modelscope.cn/docs) * I have searched related issues but cannot get...