annotated_deep_learning_paper_implementations
annotated_deep_learning_paper_implementations copied to clipboard
labmlai
🧑🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gan...
Since we just add RoPE to `x_rope`, so more precisely, we should use the `cos_cached[:x_rope.shape[0]]` and `sin_cached[:x_rope.shape[0]]` instead.
` def forward(self, *, x: torch.Tensor, mem: Optional[torch.Tensor], mask: torch.Tensor): """ * `x` is a tensor of the token level feature vectors of shape `[seq_len, batch_size, d_model]` * `mem` is...
Changes made in branch: **MayureshMore:master** [Documentation] Added missing docstrings to 7 function(s) in translate_cache.
Hello, I have been studying the U-Net implementation in this repository and noticed that the skip connections between the encoder and decoder are implemented using Center Crop to match feature...
In my experiments, I found that when I directly load an image, both in_paint.py and image_to_image.py encounter an error: File "/root/autodl-tmp/SD/model/unet.py", line 178, in forward x = torch.cat([x, x_input_block.pop()], dim=1)...
