upgrade models to opset 8 (onnx#106)

* Update README.md * Update README.md * Update README.md
dendisuhubdy · Nov 1, 2018 · a9a4882 · a9a4882
1 parent ef6bdca
commit a9a4882
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 6 deletions.
diff --git a/emotion_ferplus/README.md b/emotion_ferplus/README.md
@@ -7,8 +7,9 @@ This model is a deep convolutional neural network for emotion recognition in fac
 
 | Model          | Checksum  | Download (with sample test data) | ONNX version | Opset version | 
 |----------------|:----------|:-----------|:--------|:-------------|
-|Emotion FERPlus |[MD5](https://www.cntk.ai/OnnxModels/emotion_ferplus/opset_2/emotion_ferplus-md5.txt)|[32.4 MB](https://www.cntk.ai/OnnxModels/emotion_ferplus/opset_2/emotion_ferplus.tar.gz)|1.0|2|
-|                |[MD5](https://www.cntk.ai/OnnxModels/emotion_ferplus/opset_7/emotion_ferplus-md5.txt)|[32.4 MB](https://www.cntk.ai/OnnxModels/emotion_ferplus/opset_7/emotion_ferplus.tar.gz)|1.2|7|
+|Emotion FERPlus |[MD5](https://onnxzoo.blob.core.windows.net/models/opset_2/emotion_ferplus/emotion_ferplus-md5.txt)|[31 MB](https://onnxzoo.blob.core.windows.net/models/opset_2/emotion_ferplus/emotion_ferplus.tar.gz)|1.0|2|
+|                |[MD5](https://onnxzoo.blob.core.windows.net/models/opset_7/emotion_ferplus/emotion_ferplus-md5.txt)|[31 MB](https://onnxzoo.blob.core.windows.net/models/opset_7/emotion_ferplus/emotion_ferplus.tar.gz)|1.2|7|
+|                |[MD5](https://onnxzoo.blob.core.windows.net/models/opset_8/emotion_ferplus/emotion_ferplus-md5.txt)|[31 MB](https://onnxzoo.blob.core.windows.net/models/opset_8/emotion_ferplus/emotion_ferplus.tar.gz)|1.3|8|
 
 ### Paper
 "Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution" [arXiv:1608.01041](https://arxiv.org/abs/1608.01041)

diff --git a/mnist/README.md b/mnist/README.md
@@ -6,8 +6,9 @@ This model predicts handwritten digits using a convolutional neural network (CNN
 ## Model
 |Model|Checksum|Download (with sample test data)| ONNX version |Opset version|
 |-----|:-------|:-------------------------------|:-------------|:------------|
-|MNIST|[MD5](https://www.cntk.ai/OnnxModels/mnist/opset_1/mnist-md5.txt)|[26.2 kB](https://www.cntk.ai/OnnxModels/mnist/opset_1/mnist.tar.gz) |1.0  |1 |
-|     |[MD5](https://www.cntk.ai/OnnxModels/mnist/opset_7/mnist-md5.txt)|[25.9 kB](https://www.cntk.ai/OnnxModels/mnist/opset_7/mnist.tar.gz) |1.2  |7 |
+|MNIST|[MD5](https://onnxzoo.blob.core.windows.net/models/opset_1/mnist/mnist-md5.txt)|[26 kB](https://onnxzoo.blob.core.windows.net/models/opset_1/mnist/mnist.tar.gz) |1.0  |1 |
+|     |[MD5](https://onnxzoo.blob.core.windows.net/models/opset_7/mnist/mnist-md5.txt)|[26 kB](https://onnxzoo.blob.core.windows.net/models/opset_7/mnist/mnist.tar.gz) |1.2  |7 |
+|     |[MD5](https://onnxzoo.blob.core.windows.net/models/opset_8/mnist/mnist-md5.txt)|[26 kB](https://onnxzoo.blob.core.windows.net/models/opset_8/mnist/mnist.tar.gz) |1.3  |8 |
 
 ### Dataset
 The model has been trained on the popular [MNIST dataset](http://yann.lecun.com/exdb/mnist/).

diff --git a/tiny_yolov2/README.md b/tiny_yolov2/README.md
@@ -6,8 +6,9 @@ This model is a real-time neural network for object detection that detects 20 di
 ## Model
 |Model|Checksum|Download (with sample test data)| ONNX version |Opset version|
 |-----|:-------|:-------------------------------|:-------------|:------------|
-|Tiny YOLOv2|[MD5](https://www.cntk.ai/OnnxModels/tiny_yolov2/opset_1/tiny_yolov2-md5.txt)|[60.8 MB](https://www.cntk.ai/OnnxModels/tiny_yolov2/opset_1/tiny_yolov2.tar.gz) |1.0  |1 |
-|     |[MD5](https://www.cntk.ai/OnnxModels/tiny_yolov2/opset_7/tiny_yolov2-md5.txt)|[60.8 MB](https://www.cntk.ai/OnnxModels/tiny_yolov2/opset_7/tiny_yolov2.tar.gz) |1.2  |7 |
+|Tiny YOLOv2|[MD5](https://onnxzoo.blob.core.windows.net/models/opset_1/tiny_yolov2/tiny_yolov2-md5.txt)|[58 MB](https://onnxzoo.blob.core.windows.net/models/opset_1/tiny_yolov2/tiny_yolov2.tar.gz) |1.0  |1 |
+|     |[MD5](https://onnxzoo.blob.core.windows.net/models/opset_7/tiny_yolov2/tiny_yolov2-md5.txt)|[58 MB](https://onnxzoo.blob.core.windows.net/models/opset_7/tiny_yolov2/tiny_yolov2.tar.gz) |1.2  |7 |
+|     |[MD5](https://onnxzoo.blob.core.windows.net/models/opset_8/tiny_yolov2/tiny_yolov2-md5.txt)|[58 MB](https://onnxzoo.blob.core.windows.net/models/opset_8/tiny_yolov2/tiny_yolov2.tar.gz) |1.3  |8 |
 
 ### Paper
 "YOLO9000: Better, Faster, Stronger" [arXiv:1612.08242](https://arxiv.org/pdf/1612.08242.pdf)