Differences

This shows you the differences between two versions of the page.

--- downloads:cryolo_1 [2019/07/23 10:31]
twagner [Known issues]
+++ downloads:cryolo_1 [2019/07/29 09:41]
twagner [Installation]
@@ Line 157: / Line 157: @@
 Install fast numpy from conda:
 <code>
-conda install numpy==1.15.4
+conda install numpy==1.14.5
 </code>
 In case you run **crYOLO on a GPU** run:
 <code>
-pip install 'cryolo-X.Y.Z.tar.gz[gpu]'
+pip install 'cryolo[gpu]'
 </code>
 But if you want to run **crYOLO on a CPU** run:
 <code>
-pip install 'cryolo-X.Y.Z.tar.gz[cpu]'
+pip install 'cryolo[cpu]'
 </code>
-Finally you install the cryolo boxmanager:
+<note>
-<code>
+During the installtion of crYOLO you will see the following error message:
-pip install cryoloBM-X.Y.Z.tar.gz
+''ERROR: imagecodecs-lite 2019.2.22 has requirement numpy>=1.15.4, but you'll have numpy 1.14.5 which is incompatible.''
-</code>
+However, you can ignore it. It is actually also working with numpy==1.14.5
+</note>
 **That's it!**
@@ Line 196: / Line 197: @@
 ====crYOLO====
+**crYOLO 1.4.1:**
+  * Downgrade the dependencies to tensorflow 1.10.1 and numpy 1.14.5 as some users reported long initialization times. (Thanks to Shaun Rawson)
+  * The initialization weights are not longer shipped with the package and downloaded on-the-fly (because they are big and pypi does not allow such big packages)
+  * crYOLO is installed through pypi
+  * crYOLO box manager is installed through pypi and automatically shipped with the crYOLO package
+  * Fix fine-tune mode (Thanks to Antoine Koehl)
+  * Fixed normalization function for YOLO backend (Thanks to Wolfgang Lugmayr)
+<hidden **Old crYOLO change logs**>
 **crYOLO 1.4.0:**
@@ Line 203: / Line 214: @@
   * Update numpy from 1.14.5 to 1.15.4 to make crYOLO compatible with JANNI
-<hidden **Old crYOLO change logs**>
 **crYOLO 1.3.6:**
   * Changed filament search radius factor from 0.8 to 1.41 (this fixed issue 21)

User Tools

Site Tools

Differences

Page Tools