Skip to content

Commit

Permalink
add link to 512 model (apache#5675)
Browse files Browse the repository at this point in the history
  • Loading branch information
zhreshold authored and piiswrong committed Apr 3, 2017
1 parent b57237f commit 8f2fe4c
Show file tree
Hide file tree
Showing 2 changed files with 6 additions and 6 deletions.
4 changes: 2 additions & 2 deletions example/ssd/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ Due to the permission issue, this example is maintained in this [repository](htt
* Monitor validation mAP during training.
* More network symbols under development and test.
* Extra operators are now in `mxnet/src/operator/contrib`.
* Old models are incompatible, use https://github.com/dmlc/mxnet/commits/17b6aac0d7656b44764b75b12c22074ed81038b3 for backward support. Or, you can modify the json file to update the symbols if you are familiar with it.
* Old models are incompatible, use [e06c55d](https://github.com/dmlc/mxnet/commits/e06c55d6466a0c98c7def8f118a48060fb868901) or [e4f73f1](https://github.com/dmlc/mxnet/commits/e4f73f1f4e76397992c4b0a33c139d52b4b7af0e) for backward compatibility. Or, you can modify the json file to update the symbols if you are familiar with it, because only names have changed while weights and bias should still be good.

### Demo results
![demo1](https://cloud.githubusercontent.com/assets/3307514/19171057/8e1a0cc4-8be0-11e6-9d8f-088c25353b40.png)
Expand All @@ -33,7 +33,7 @@ Due to the permission issue, this example is maintained in this [repository](htt
| Model | Training data | Test data | mAP |
|:-----------------:|:----------------:|:---------:|:----:|
| [VGG16_reduced 300x300](https://github.com/zhreshold/mxnet-ssd/releases/download/v0.5-beta/vgg16_ssd_300_voc0712_trainval.zip) | VOC07+12 trainval| VOC07 test| 77.8|
| VGG16_reduced 512x512 | VOC07+12 trainval | VOC07 test| 79.9|
| [VGG16_reduced 512x512](https://github.com/zhreshold/mxnet-ssd/releases/download/v0.5-beta/vgg16_ssd_512_voc0712_trainval.zip) | VOC07+12 trainval | VOC07 test| 79.9|
*More to be added*

### Speed
Expand Down
8 changes: 4 additions & 4 deletions example/ssd/symbol/symbol_vgg16_ssd_512.py
Original file line number Diff line number Diff line change
Expand Up @@ -106,12 +106,12 @@ def get_symbol_train(num_classes=20, nms_thresh=0.5, force_suppress=False, nms_t
stride=(2,2), act_type="relu", use_batchnorm=False)
conv10_1, relu10_1 = conv_act_layer(relu9_2, "10_1", 128, kernel=(1,1), pad=(0,0), \
stride=(1,1), act_type="relu", use_batchnorm=False)
conv10_2, relu10_2 = conv_act_layer(relu10_1, "10_2", 256, kernel=(3,3), pad=(0,0), \
stride=(1,1), act_type="relu", use_batchnorm=False)
conv10_2, relu10_2 = conv_act_layer(relu10_1, "10_2", 256, kernel=(3,3), pad=(1,1), \
stride=(2,2), act_type="relu", use_batchnorm=False)
conv11_1, relu11_1 = conv_act_layer(relu10_2, "11_1", 128, kernel=(1,1), pad=(0,0), \
stride=(1,1), act_type="relu", use_batchnorm=False)
conv11_2, relu11_2 = conv_act_layer(relu11_1, "11_2", 256, kernel=(3,3), pad=(0,0), \
stride=(1,1), act_type="relu", use_batchnorm=False)
conv11_2, relu11_2 = conv_act_layer(relu11_1, "11_2", 256, kernel=(3,3), pad=(1,1), \
stride=(2,2), act_type="relu", use_batchnorm=False)
conv12_1, relu12_1 = conv_act_layer(relu11_2, "12_1", 128, kernel=(1,1), pad=(0,0), \
stride=(1,1), act_type="relu", use_batchnorm=False)
conv12_2, relu12_2 = conv_act_layer(relu12_1, "12_2", 256, kernel=(4,4), pad=(1,1), \
Expand Down

0 comments on commit 8f2fe4c

Please sign in to comment.