Import from internal hub.

MegEngine · Jul 9, 2020 · 73b3450 · 73b3450
1 parent 8e966d9
commit 73b3450
Show file tree

Hide file tree

Showing 5 changed files with 35 additions and 24 deletions.
diff --git a/models/megengine_nlp_bert.md b/models/megengine_nlp_bert.md
@@ -11,16 +11,16 @@ github-link: https://github.com/megengine/models
 
 ```python
 import megengine.hub as hub
-model = hub.load("megengine/models", "wwm_cased_L-24_H-1024_A-16", pretrained=True)
+model = megengine.hub.load("megengine/models", "wwm_cased_L-24_H-1024_A-16", pretrained=True)
 # or any of these variants
-# model = hub.load("megengine/models", "wwm_cased_L-24_H-1024_A-16", pretrained=True)
-# model = hub.load("megengine/models", "wwm_uncased_L-24_H-1024_A-16", pretrained=True)
-# model = hub.load("megengine/models", "cased_L-12_H-768_A-12", pretrained=True)
-# model = hub.load("megengine/models", "cased_L-24_H-1024_A-16", pretrained=True)
-# model = hub.load("megengine/models", "uncased_L-12_H-768_A-12", pretrained=True)
-# model = hub.load("megengine/models", "uncased_L-24_H-1024_A-16", pretrained=True)
-# model = hub.load("megengine/models", "chinese_L-12_H-768_A-12", pretrained=True)
-# model = hub.load("megengine/models", "multi_cased_L-12_H-768_A-12", pretrained=True)
+# model = megengine.hub.load("megengine/models", "wwm_cased_L-24_H-1024_A-16", pretrained=True)
+# model = megengine.hub.load("megengine/models", "wwm_uncased_L-24_H-1024_A-16", pretrained=True)
+# model = megengine.hub.load("megengine/models", "cased_L-12_H-768_A-12", pretrained=True)
+# model = megengine.hub.load("megengine/models", "cased_L-24_H-1024_A-16", pretrained=True)
+# model = megengine.hub.load("megengine/models", "uncased_L-12_H-768_A-12", pretrained=True)
+# model = megengine.hub.load("megengine/models", "uncased_L-24_H-1024_A-16", pretrained=True)
+# model = megengine.hub.load("megengine/models", "chinese_L-12_H-768_A-12", pretrained=True)
+# model = megengine.hub.load("megengine/models", "multi_cased_L-12_H-768_A-12", pretrained=True)
 ```
 
 <!-- section: zh_CN --> 
@@ -147,7 +147,7 @@ We provide the following pre-trained models for users to finetune in different t
 * `chinese_L-12_H-768_A-12`
 * `multi_cased_L-12_H-768_A-12`
 
-The weight of the model comes from Google's pre-trained models, and its meaning is also consistent with it. Users can use `megengine.hub` to easily use the pre-trained bert model, and download the corresponding` vocab.txt` and `bert_config.json`. We also provide a convenient script in [models] (https://github.com/megengine/models/official/nlp/bert), which can directly obtain the corresponding dictionary, configuration, and pre-trained model by task name. .
+The weight of the model comes from Google's pre-trained models, and its meaning is also consistent with it. Users can use `megengine.hub` to easily use the pre-trained bert model, and download the corresponding` vocab.txt` and `bert_config.json`. We also provide a convenient script in [models](https://github.com/megengine/models/official/nlp/bert), which can directly obtain the corresponding dictionary, configuration, and pre-trained model by task name. .
 
 ```python
 import megengine.hub as hub
@@ -229,11 +229,11 @@ bert, config, vocab_file = create_hub_bert('uncased_L-12_H-768_A-12', pretrained
 model = BertForSequenceClassification(config, num_labels=2, bert=bert)
 ```
 
-All pre-trained models expect the data to be pre-processed correctly. The requirements are consistent with the Google's bert. For details, please refer to original [bert] (https://github.com/google-research/bert), or refer to our example [models] ( https://github.com/megengine/models/official/nlp/bert).
+All pre-trained models expect the data to be pre-processed correctly. The requirements are consistent with the Google's bert. For details, please refer to original [bert](https://github.com/google-research/bert), or refer to our example [models](https://github.com/megengine/models/official/nlp/bert).
 
 
 ### Model Description
-We provide example code in [models] (https://github.com/megengine/models/official/nlp/bert).
+We provide example code in [models](https://github.com/megengine/models/official/nlp/bert).
 This example code fine-tunes the pre-trained `uncased_L-12_H-768_A-12` model on the Microsoft Research Paraphrase (MRPC) dataset. 
 
 Our test ran on the original implementation hyper-parameters gave evaluation results between 84% and 88%.

diff --git a/models/megengine_vision_deeplabv3plus.md b/models/megengine_vision_deeplabv3plus.md
@@ -1,9 +1,9 @@
 ---
 template: hub1
-title: deeplabv3plus
+title: DeepLabV3plus
 summary:
- en_US: Deeplabv3plus pre-trained on VOC
- zh_CN: Deeplabv3plus (VOC预训练权重）
+ en_US: DeepLabV3plus pre-trained on VOC
+ zh_CN: DeepLabV3plus (VOC预训练权重）
 author: MegEngine Team
 tags: [vision]
 github-link: https://github.com/megengine/models
@@ -61,7 +61,7 @@ pred = cv2.resize(pred.astype("uint8"), (oriw, orih), interpolation=cv2.INTER_LI
 
 ### 模型描述
 
-目前我们提供了deeplabv3plus的预训练模型, 在voc验证集的表现如下：
+目前我们提供了 deeplabv3plus 的预训练模型, 在voc验证集的表现如下：
 
  Methods | Backbone | TrainSet | EvalSet | mIoU_single | mIoU_multi |
  :--: |:--: |:--: |:--: |:--: |:--: |

diff --git a/models/megengine_vision_resnet.md b/models/megengine_vision_resnet.md
@@ -16,6 +16,7 @@ model = megengine.hub.load('megengine/models', 'resnet18', pretrained=True)
 # model = megengine.hub.load('megengine/models', 'resnet34', pretrained=True)
 # model = megengine.hub.load('megengine/models', 'resnet50', pretrained=True)
 # model = megengine.hub.load('megengine/models', 'resnet101', pretrained=True)
+# model = megengine.hub.load('megengine/models', 'resnet152', pretrained=True)
 # model = megengine.hub.load('megengine/models', 'resnext50_32x4d', pretrained=True)
 model.eval()
 ```
@@ -54,14 +55,15 @@ print(probs)
 
 ### 模型描述
 
-目前我们提供了以下几个预训练模型，分别是`resnet18`, `resnet34`, `resnet50`, `resnet101`，`resnext50_32x4d`，它们在ImageNet验证集上的单crop性能如下表：
+目前我们提供了以下几个预训练模型，分别是`resnet18`, `resnet34`, `resnet50`, `resnet101`，`resnet152`, `resnext50_32x4d`，它们在ImageNet验证集上的单crop性能如下表：
 
 | 模型 | Top1 acc | Top5 acc |
 | --- | --- | --- |
 | ResNet18 | 70.312 | 89.430 | 
 | ResNet34 | 73.960 | 91.630 | 
 | ResNet50 | 76.254 | 93.056 | 
 | ResNet101| 77.944 | 93.844 | 
+| ResNet152| 78.582 | 94.130 |
 | ResNeXt50 32x4d | 77.592 | 93.644 |
 
 ### 参考文献
@@ -105,14 +107,15 @@ print(probs)
 
 ### Model Description
 
-Currently we provide these pretrained models: `resnet18`, `resnet34`, `resnet50`, `resnet101`, `resnext50_32x4d`. Their 1-crop accuracy on ImageNet validation dataset can be found in following table.
+Currently we provide these pretrained models: `resnet18`, `resnet34`, `resnet50`, `resnet101`, `resnet152`, `resnext50_32x4d`. Their 1-crop accuracy on ImageNet validation dataset can be found in following table.
 
 | model | Top1 acc | Top5 acc |
 | --- | --- | --- |
 | ResNet18 | 70.312 | 89.430 | 
 | ResNet34 | 73.960 | 91.630 | 
 | ResNet50 | 76.254 | 93.056 | 
 | ResNet101| 77.944 | 93.844 | 
+| ResNet152| 78.582 | 94.130 |
 | ResNeXt50 32x4d | 77.592 | 93.644 |
 
 ### References

diff --git a/models/megengine_vision_retinanet.md b/models/megengine_vision_retinanet.md
@@ -1,6 +1,6 @@
 ---
 template: hub1
-title: retinanet
+title: RetinaNet
 summary:
  en_US: RetinaNet pre-trained on COCO
  zh_CN: RetinaNet (COCO预训练权重）
@@ -13,9 +13,8 @@ github-link: https://github.com/megengine/models
 from megengine import hub
 model = hub.load(
  "megengine/models",
- "retinanet_res50_coco_1x_800size",
+ "retinanet_res50_1x_800size",
  pretrained=True,
- use_cache=False,
 )
 model.eval()
 

diff --git a/models/megengine_vision_shufflenet_v2.md b/models/megengine_vision_shufflenet_v2.md
@@ -1,6 +1,6 @@
 ---
 template: hub1
-title: ResNet
+title: ShuffleNet V2
 summary:
  en_US: "ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design"
  zh_CN: ShuffleNet V2（ImageNet 预训练权重）
@@ -12,6 +12,9 @@ github-link: https://github.com/megengine/models
 ```python
 import megengine.hub
 model = megengine.hub.load('megengine/models', 'shufflenet_v2_x1_0', pretrained=True)
+# model = megengine.hub.load('megengine/models', 'shufflenet_v2_x0_5', pretrained=True)
+# model = megengine.hub.load('megengine/models', 'shufflenet_v2_x1_5', pretrained=True)
+# model = megengine.hub.load('megengine/models', 'shufflenet_v2_x2_0', pretrained=True)
 model.eval()
 ```
 <!-- section: zh_CN --> 
@@ -53,7 +56,10 @@ print(probs)
 
 | 模型 | top1 acc | top5 acc |
 | --- | --- | --- |
-| shufflenet_v2_x1_0 | 69.369 | 88.793 |
+| ShuffleNetV2 x0.5 | 60.696 | 82.190 | 
+| ShuffleNetV2 x1.0 | 69.372 | 88.764 | 
+| ShuffleNetV2 x1.5 | 72.806 | 90.792 | 
+| ShuffleNetV2 x2.0 | 75.074 | 92.278 | 
 
 ### 参考文献
 
@@ -99,7 +105,10 @@ Currently we provide several pretrained models(see the table below), Their 1-cro
 
 | model | top1 acc | top5 acc |
 | --- | --- | --- |
-| shufflenet_v2_x1_0 | 69.369 | 88.793 |
+| ShuffleNetV2 x0.5 | 60.696 | 82.190 | 
+| ShuffleNetV2 x1.0 | 69.372 | 88.764 | 
+| ShuffleNetV2 x1.5 | 72.806 | 90.792 | 
+| ShuffleNetV2 x2.0 | 75.074 | 92.278 | 
 
 ### References