-
I got the clear-cut idea of the encoder side of the segmentation_models. I am using Resnet 152 as the UNet backbone. But I am unclear about the decoder architecture. What configuration of kernel size,…
-
There are so many fc layers in both CNN encoder and RNN decoder, only one is enough. When I implement the CRNN training, I got over 70% test acc with only one fc layer in both CNN and LSTM (However, t…
-
Hello! I have carefully read your code and paper (FULL TRANSFORMER NETWORK FOR IMAGE CAPTIONING), and I have found some inconsistencies that confuse me. I would appreciate it if you could give me some…
-
https://doi.org/10.1101/242818 https://www.biorxiv.org/content/early/2018/01/04/242818
> Breast cancer remains the most common type of cancer and the leading cause of cancer-induced mortality among…
-
### 🐛 Describe the bug
**🐛 Bug**
- cuDNN error on Torch 1.6.0 with CUDA 10.1 when running on a 1080Ti with 512.15 Nvidia drivers.
- cuDNN error on Torch 1.11.0 with CUDA 11.3 when running on a 1080…
-
Dear Mr. Gao
Thank you so much for the great work. However, I met some problems when I implemented this code.
As described in you article, "For the visual frames, we use an ImageNet pre-tra…
-
Hi,
I am fine-tuning an “imagenet-resnet-152-dag.mat”. I have compiled MatConvNet-24 using 2×1060 gpus, 64g ram in windows 10. However, after any epoch is finished, I get this error:
_Error usin…
-
Hi AlphaPose Team, thank you for sharing the great work! I am looking for a setting with the most accurate 2D keypoint detection you can get with Alphapose (no matter how slowly inference runs).
…
-
Caffe's `time` command includes two timers: a per layer timer and an overall timer. However, the overall timer currently also includes the overhead of the per-layer timers. For instance, for forward p…
-
Hi, thank you for these clear and efficient codes! May I ask, if you have trained this model on Optical Flow images?