From a0dc4d717ab2d95e5e90f5b7b6344e8074b81606 Mon Sep 17 00:00:00 2001
From: Alexey <AlexeyAB@users.noreply.github.com>
Date: Fri, 30 Mar 2018 15:34:28 +0000
Subject: [PATCH] Update Readme.md
---
README.md | 8 ++++++--
1 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/README.md b/README.md
index d576a1e..343db79 100644
--- a/README.md
+++ b/README.md
@@ -188,7 +188,7 @@
## How to train (Pascal VOC Data):
-1. Download pre-trained weights for the convolutional layers (76 MB): http://pjreddie.com/media/files/darknet53.conv.74 and put to the directory `build\darknet\x64`
+1. Download pre-trained weights for the convolutional layers (154 MB): http://pjreddie.com/media/files/darknet53.conv.74 and put to the directory `build\darknet\x64`
2. Download The Pascal VOC Data and unpack it to directory `build\darknet\x64\data\voc` will be created dir `build\darknet\x64\data\voc\VOCdevkit\`:
* http://pjreddie.com/media/files/VOCtrainval_11-May-2012.tar
@@ -219,7 +219,7 @@
1. Train it first on 1 GPU for like 1000 iterations: `darknet.exe detector train data/voc.data cfg/yolov3-voc.cfg darknet53.conv.74`
-2. Then stop and by using partially-trained model `/backup/yolo-voc_1000.weights` run training with multigpu (up to 4 GPUs): `darknet.exe detector train data/voc.data cfg/yolov3-voc.cfg /backup/yolo-voc_1000.weights -gpus 0,1,2,3`
+2. Then stop and by using partially-trained model `/backup/yolov3-voc_1000.weights` run training with multigpu (up to 4 GPUs): `darknet.exe detector train data/voc.data cfg/yolov3-voc.cfg /backup/yolov3-voc_1000.weights -gpus 0,1,2,3`
https://groups.google.com/d/msg/darknet/NbJqonJBTSY/Te5PfIpuCAAJ
@@ -239,7 +239,9 @@
* https://github.com/AlexeyAB/darknet/blob/0039fd26786ab5f71d5af725fc18b3f521e7acfd/cfg/yolov3.cfg#L776
So if `classes=1` then should be `filters=18`. If `classes=2` then write `filters=31`.
+
**(Do not write in the cfg-file: filters=(classes + 5)x3)**
+
(Generally `filters` depends on the `classes`, `coords` and number of `mask`s, i.e. filters=`(classes + coords + 1)*<number of mask>`, where `mask` is indices of anchors. If `mask` is absence, then filters=`(classes + coords + 1)*num`)
So for example, for 2 objects, your file `yolo-obj.cfg` should differ from `yolov3.cfg` in such lines in each of **3** [yolo]-layers:
@@ -303,6 +305,8 @@
* Also you can get result earlier than all 45000 iterations.
+ **Note:** If during training you see `nan` values in some lines then training goes well, but if `nan` are in all lines then training goes wrong.
+
### How to train tiny-yolo (to detect your custom objects):
Do all the same steps as for the full yolo model as described above. With the exception of:
--
Gitblit v1.10.0