From f689ce5d39c6f1475dfc71503288ea2905c8f685 Mon Sep 17 00:00:00 2001 From: zachcp Date: Fri, 15 Nov 2024 02:30:15 -0500 Subject: Documentation Pass for Models (#2617) * links in chinese_clip * links for clip model * add mod docs for flux and llava * module doc for MMDIT and MIMI * add docs for a few more modesl * mod docs for bert naser and beit * add module docs for convmixer colpali codegeex and chatglm * add another series of moddocs * add fastvit-llama2_c * module docs mamba -> mobileone * module docs from moondream-phi3 * mod docs for quantized and qwen * update to yi * fix long names * Update llama2_c.rs * Update llama2_c_weights.rs * Fix the link for mimi + tweaks --------- Co-authored-by: Laurent Mazare --- candle-transformers/src/models/vgg.rs | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'candle-transformers/src/models/vgg.rs') diff --git a/candle-transformers/src/models/vgg.rs b/candle-transformers/src/models/vgg.rs index 010643c8..57f9ae67 100644 --- a/candle-transformers/src/models/vgg.rs +++ b/candle-transformers/src/models/vgg.rs @@ -1,7 +1,18 @@ //! VGG-16 model implementation. //! -//! See Very Deep Convolutional Networks for Large-Scale Image Recognition -//! +//! VGG-16 is a convolutional neural network architecture. It consists of 13 +//! convolutional layers followed by 3 fully connected layers. +//! +//! Key characteristics: +//! - Conv layers with 3x3 filters +//! - Max pooling after every 2-3 conv layers +//! - Three fully connected layers of 4096, 4096, 1000 units +//! - ReLU activation and dropout +//! +//! References: +//! - [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://arxiv.org/abs/1409.1556) +//! + use candle::{ModuleT, Result, Tensor}; use candle_nn::{FuncT, VarBuilder}; -- cgit v1.2.3