From afa18c92f00c6ed771b61cb08b285d2f93446ea4 Mon Sep 17 00:00:00 2001 From: HuguesTHOMAS Date: Mon, 27 Apr 2020 18:55:39 -0400 Subject: [PATCH] Corrections --- doc/object_classification_guide.md | 13 ++++++++++--- doc/object_segmentation_guide.md | 2 +- doc/scene_segmentation_guide.md | 2 +- 3 files changed, 12 insertions(+), 5 deletions(-) diff --git a/doc/object_classification_guide.md b/doc/object_classification_guide.md index 415d2e5..ff600a3 100644 --- a/doc/object_classification_guide.md +++ b/doc/object_classification_guide.md @@ -3,9 +3,16 @@ ### Data -Regularly sampled clouds from ModelNet40 dataset can be downloaded here (1.6 GB). Uncompress the folder and move it to `Data/ModelNet40/modelnet40_normal_resampled`. +We consider our experiment folder is located at `XXXX/Experiments/KPConv-PyTorch`. And we use a common Data folder +loacated at `XXXX/Data`. Therefore the relative path to the Data folder is `../../Data`. + +Regularly sampled clouds from ModelNet40 dataset can be downloaded +here (1.6 GB). +Uncompress the data and move it inside the folder `../../Data/ModelNet40`. + +N.B. If you want to place your data anywhere else, you just have to change the variable +`self.path` of `ModelNet40Dataset` class ([here](https://github.com/HuguesTHOMAS/KPConv-PyTorch/blob/e9d328135c0a3818ee0cf1bb5bb63434ce15c22e/datasets/ModelNet40.py#L113)). -N.B. If you want to place your data anywhere else, you just have to change the variable `self.path` of `ModelNet40Dataset` class (in the file `datasets/ModelNet40.py`). ### Training a model @@ -17,7 +24,7 @@ This file contains a configuration subclass `ModelNet40Config`, inherited from t ### Plot a logged training -When you start a new training, it is saved in a `results` folder. A dated log folder will be created, containing many information including loss values, validation metrics, model snapshots, etc. +When you start a new training, it is saved in a `results` folder. A dated log folder will be created, containing many information including loss values, validation metrics, model checkpoints, etc. In `plot_convergence.py`, you will find detailed comments explaining how to choose which training log you want to plot. Follow them and then run the script : diff --git a/doc/object_segmentation_guide.md b/doc/object_segmentation_guide.md index bb44868..60d9dbd 100644 --- a/doc/object_segmentation_guide.md +++ b/doc/object_segmentation_guide.md @@ -15,7 +15,7 @@ Similarly to ModelNet40 training, the parameters can be modified in a configurat ### Plot a logged training -When you start a new training, it is saved in a `results` folder. A dated log folder will be created, containing many information including loss values, validation metrics, model snapshots, etc. +When you start a new training, it is saved in a `results` folder. A dated log folder will be created, containing many information including loss values, validation metrics, model checkpoints, etc. In `plot_convergence.py`, you will find detailed comments explaining how to choose which training log you want to plot. Follow them and then run the script : diff --git a/doc/scene_segmentation_guide.md b/doc/scene_segmentation_guide.md index ce81e35..ff5f2a1 100644 --- a/doc/scene_segmentation_guide.md +++ b/doc/scene_segmentation_guide.md @@ -44,7 +44,7 @@ Incoming ### Plot a logged training -When you start a new training, it is saved in a `results` folder. A dated log folder will be created, containing many information including loss values, validation metrics, model snapshots, etc. +When you start a new training, it is saved in a `results` folder. A dated log folder will be created, containing many information including loss values, validation metrics, model checkpoints, etc. In `plot_convergence.py`, you will find detailed comments explaining how to choose which training log you want to plot. Follow them and then run the script :