diff --git a/docs/en/tutorials/getting_started_retrieval_en.md b/docs/en/tutorials/getting_started_retrieval_en.md index eea6c1667036ab6eb8c554b6959d8d1cc669e86a..f548572d9f17a58695404ccb53839926cdfcf3eb 100644 --- a/docs/en/tutorials/getting_started_retrieval_en.md +++ b/docs/en/tutorials/getting_started_retrieval_en.md @@ -120,7 +120,7 @@ python3 tools/train.py \ `-c` is used to specify the path to the configuration file, and `-o` is used to specify the parameters that need to be modified or added, where `-o Arch.Backbone.pretrained=True` indicates that the Backbone part uses the pre-trained model, in addition, `Arch.Backbone.pretrained` can also specify backbone.`pretrained` can also specify the address of a specific model weight file, which needs to be replaced with the path to your own pre-trained model weight file when using it. `-o Global.device=gpu` indicates that the GPU is used for training. If you want to use a CPU for training, you need to set `Global.device` to `cpu`. -For more detailed training configuration, you can also modify the corresponding configuration file of the model directly. Refer to the [configuration document](config_en.md) for specific configuration parameters. +For more detailed training configuration, you can also modify the corresponding configuration file of the model directly. Refer to the [configuration document](config_description_en.md) for specific configuration parameters. Run the above commands to check the output log, an example is as follows: diff --git a/docs/images/wx_group.png b/docs/images/wx_group.png index d73a7e9254f3bedfba5c6274028cf0e848f94c9c..fe34a9a1e3b92f4170e15cec2a626ace8ddfd4dd 100644 Binary files a/docs/images/wx_group.png and b/docs/images/wx_group.png differ diff --git a/docs/zh_CN/tutorials/getting_started_retrieval.md b/docs/zh_CN/tutorials/getting_started_retrieval.md index 06dcc11c77af238aec346c4432cec570e2ac0c4f..a0695d88c1cd2f9a1ef1bc93cabb17276eddf5a9 100644 --- a/docs/zh_CN/tutorials/getting_started_retrieval.md +++ b/docs/zh_CN/tutorials/getting_started_retrieval.md @@ -117,7 +117,7 @@ python3 tools/train.py \ 其中，`-c`用于指定配置文件的路径，`-o`用于指定需要修改或者添加的参数，其中`-o Arch.Backbone.pretrained=True`表示Backbone部分使用预训练模型，此外，`Arch.Backbone.pretrained`也可以指定具体的模型权重文件的地址，使用时需要换成自己的预训练模型权重文件的路径。`-o Global.device=gpu`表示使用GPU进行训练。如果希望使用CPU进行训练，则需要将`Global.device`设置为`cpu`。 -更详细的训练配置，也可以直接修改模型对应的配置文件。具体配置参数参考[配置文档](config.md)。 +更详细的训练配置，也可以直接修改模型对应的配置文件。具体配置参数参考[配置文档](config_description.md)。 运行上述命令，可以看到输出日志，示例如下： @@ -245,4 +245,4 @@ python3 tools/export_model.py \ - 平均检索精度(mAP) - AP: AP指的是不同召回率上的正确率的平均值 - - mAP: 测试集中所有图片对应的AP的的平均值 \ No newline at end of file + - mAP: 测试集中所有图片对应的AP的的平均值 diff --git a/ppcls/arch/backbone/model_zoo/googlenet.py b/ppcls/arch/backbone/model_zoo/googlenet.py index 00b7feeb9207aace64d84f71f77bf2cbe2be6af8..22528427ea3b9afa38856d632fbc08901f3c1009 100644 --- a/ppcls/arch/backbone/model_zoo/googlenet.py +++ b/ppcls/arch/backbone/model_zoo/googlenet.py @@ -131,7 +131,7 @@ class GoogLeNetDY(nn.Layer): self._ince5b = Inception( 832, 832, 384, 192, 384, 48, 128, 128, name="ince5b") - self._pool_5 = AvgPool2D(kernel_size=7, stride=7) + self._pool_5 = AdaptiveAvgPool2D(1) self._drop = Dropout(p=0.4, mode="downscale_in_infer") self._fc_out = Linear( diff --git a/ppcls/configs/ImageNet/AlexNet/AlexNet.yaml b/ppcls/configs/ImageNet/AlexNet/AlexNet.yaml index 7fa94c7513aed34095edac999972419b00c5c968..1df2cbd1ec59d102cb56f9250bf71680b89d475d 100644 --- a/ppcls/configs/ImageNet/AlexNet/AlexNet.yaml +++ b/ppcls/configs/ImageNet/AlexNet/AlexNet.yaml @@ -34,9 +34,8 @@ Optimizer: momentum: 0.9 lr: name: Piecewise - learning_rate: 0.01 decay_epochs: [30, 60, 90] - values: [0.1, 0.01, 0.001, 0.0001] + values: [0.01, 0.001, 0.0001, 0.00001] regularizer: name: 'L2' coeff: 0.0001