microsoft
/
CNTK
зеркало из
1
0
Форкнуть 0
Код Задачи Пакеты Проекты Релизы Вики Активность

Consistent naming for pretrained models

This commit is contained in:
Philipp Kranen 2017-08-23 10:30:50 +02:00
Родитель 5e15c6a177
Коммит e6f54374b5
3 изменённых файлов: 12 добавлений и 4 удалений
Показать статистику Скачать Patch файл Скачать Diff файл Показать все файлы Свернуть все файлы

4
PretrainedModels/Image.md
Просмотреть файл

@ -62,13 +62,13 @@ This page contains pre-trained image models either converted from other toolkits
|Single crop top 1 / top 5 error | 23.862% / 7.180%
#### ResNet20 for CIFAR-10
|CNTK model download path | https://www.cntk.ai/Models/CNTK_Pretrained/ResNet20_CIFAR10_Python.model
|CNTK model download path | https://www.cntk.ai/Models/CNTK_Pretrained/ResNet20_CIFAR10_CNTK.model
|:-------|:---
|Training script | [TrainResNet_CIFAR10.py --network resnet20](../Examples/Image/Classification/ResNet/Python/TrainResNet_CIFAR10.py)
|Single crop top 1 error | 8.17%
#### ResNet110 for CIFAR-10
|CNTK model download path | https://www.cntk.ai/Models/CNTK_Pretrained/ResNet110_CIFAR10_Python.model
|CNTK model download path | https://www.cntk.ai/Models/CNTK_Pretrained/ResNet110_CIFAR10_CNTK.model
|:-------|:---
|Training script | [TrainResNet_CIFAR10.py --network resnet110](../Examples/Image/Classification/ResNet/Python/TrainResNet_CIFAR10.py)
|Single crop top 1 error | 6.08%

8
PretrainedModels/README.md
Просмотреть файл

@ -2,4 +2,12 @@
This folder contains pre-trained models that can be used as DNN featurizers or as the basis for transfer learning. Some of the models are trained from scratch by CNTK, and some others are converted from other toolkits such as Caffe. The models are categorized by their application domains.
To download a model run
`python download_model.py <model_name>`
To see the list of available models run
`python download_model.py list`
## [Image models](./Image.md)

4
PretrainedModels/download_model.py
Просмотреть файл

@ -20,8 +20,8 @@ models = (('Image Classification', 'AlexNet_ImageNet_CNTK', 'https://www.cntk.ai
('Image Classification', 'ResNet18_ImageNet_CNTK', 'https://www.cntk.ai/Models/CNTK_Pretrained/ResNet18_ImageNet_CNTK.model'),
('Image Classification', 'ResNet34_ImageNet_CNTK', 'https://www.cntk.ai/Models/CNTK_Pretrained/ResNet34_ImageNet_CNTK.model'),
('Image Classification', 'ResNet50_ImageNet_CNTK', 'https://www.cntk.ai/Models/CNTK_Pretrained/ResNet50_ImageNet_CNTK.model'),
('Image Classification', 'ResNet20_CIFAR10_Python', 'https://www.cntk.ai/Models/CNTK_Pretrained/ResNet20_CIFAR10_Python.model'),
('Image Classification', 'ResNet110_CIFAR10_Python', 'https://www.cntk.ai/Models/CNTK_Pretrained/ResNet110_CIFAR10_Python.model'),
('Image Classification', 'ResNet20_CIFAR10_CNTK', 'https://www.cntk.ai/Models/CNTK_Pretrained/ResNet20_CIFAR10_CNTK.model'),
('Image Classification', 'ResNet110_CIFAR10_CNTK', 'https://www.cntk.ai/Models/CNTK_Pretrained/ResNet110_CIFAR10_CNTK.model'),
('Image Classification', 'ResNet50_ImageNet_Caffe', 'https://www.cntk.ai/Models/Caffe_Converted/ResNet50_ImageNet_Caffe.model'),
('Image Classification', 'ResNet101_ImageNet_Caffe', 'https://www.cntk.ai/Models/Caffe_Converted/ResNet101_ImageNet_Caffe.model'),
('Image Classification', 'ResNet152_ImageNet_Caffe', 'https://www.cntk.ai/Models/Caffe_Converted/ResNet152_ImageNet_Caffe.model'),