-
- [x] Bilinear upsampling as a transposed convolution
- [x] BatchNorm Fusion
- [x] Compare the inference results (CNTK vs PyTorch)
- [ ] Tiling strategy for large samples
- [ ] Test VNet and UNet
-
I notice that in the config files for all the experiments, channel_mults is set to [1,2,4,8], while attn_res is at 16. This means that you dont use attention within the upsampling and downsampling blo…
-
Hello,I' ve trained GAN for Upsampling(PixelShuffle, ConvTranspose2d + stride).But It will get bad checkerboard.
-
您好，请问您提到的“Comparisons of PSNR performance and the inference latency of different models. The inference latency is tested on Dimensity 8100 SoC, NNAPI driver, INT8 precision and upsampling from 360 × 6…
-
### 🚀 The feature, motivation and pitch
Motivated by the same reasons ConvTranspose modules have an `output_size` argument.
The problem is that multiple tensor sizes will downsample to the same si…
-
The model upsampling the coordinate information. Will RGB information be upsampled?
-
Hi,
Thanks for the amazing dataset and for sharing your code.
I am unable to reproduce the results for validation set seen.
I downloaded the checkpoints as provided by you and I am using the best_s…
sgdgp updated
3 years ago
-
你好，参考你的例子来做yolov3的剪枝，现在遇到上采样upsampling卡住了，不知大佬有什么建议吗
-
Thank you very much for your well organized code. May I ask how the KITTI experiment was conducted? Do you divide KITTI into multiple blocks, then perform upsampling separately?
-
Hey professor. I remember that the 2 stride conv is more stable than up-pooling (according to DCGAN). However, in your model, the downsampling part is 2 stride conv, while up-pooling in upsampling par…