* Installation: Please refer to [Paddle Installation Tutorial](../installation/install_paddle_en.md) and [PaddleClas Installation Tutorial](../installation/install_paddleclas_en.md) to configure the running environment.
* Installation: Please refer to [Installation Tutorial](../installation.md) to configure the running environment.
@@ -17,7 +17,7 @@ PaddlePaddle supports exporting inference model for deployment. Compared with tr
## 1. Environmental preparation
First, refer to the [Installing PaddlePaddle](../installation/install_paddle_en.md) and the [Installing PaddleClas](../installation/install_paddleclas_en.md) to prepare environment.
First, refer to the [Installing PaddleClas](../installation.md) to prepare environment.
@@ -6,7 +6,7 @@ The model saved during the training process is the checkpoints model, which save
Compared with the checkpoints model, the inference model will additionally save the structural information of the model. Therefore, it is easier to deploy because the model structure and model parameters are already solidified in the inference model file, and is suitable for integration with actual systems.
Please refer to the document [install paddle](../installation/install_paddle_en.md) and [install paddleclas](../installation/install_paddleclas_en.md) to prepare the environment.
Please refer to the document [install paddleclas](../installation.md) to prepare the environment.
@@ -86,7 +86,7 @@ After a model is trained, the evaluation results of the model on the validation
## 3. Application Methods
Please refer to [Installation](../installation/install_paddleclas_en.md) to setup environment at first, and prepare flower102 dataset by following the instruction mentioned in the [Quick Start](../quick_start/quick_start_classification_new_user_en.md).
Please refer to [Installation](../installation.md) to setup environment at first, and prepare flower102 dataset by following the instruction mentioned in the [Quick Start](../quick_start/quick_start_classification_new_user_en.md).
So far, PaddleClas supports the following training/evaluation environments:
@@ -16,7 +16,7 @@ The feature gallery is built in advance using the labeled image datasets. The co
To experience the whole image recognition system, or learn how to build a feature gallery, please refer to [Quick Start of Image Recognition](../quick_start/quick_start_recognition_en.md), which explains the overall application process. The following parts expound on the training part of the above three steps.
Please first refer to the [Installation Guide](../installation/install_paddleclas_en.md) to configure the runtime environment.
Please first refer to the [Installation Guide](../installation.md) to configure the runtime environment.
@@ -48,7 +48,7 @@ Image classification is a pattern classification problem, which is the most basi
<aname="2"></a>
## 2. Environmental installation and configuration
For specific installation steps, please refer to [Paddle Installation Document](../installation/install_paddle_en.md), [PaddleClas Installation Document](../installation/install_paddleclas_en.md).
For specific installation steps, please refer to [Installation Document](../installation.md).
<aname="3"></a>
## 3. Data preparation and processing
...
...
@@ -191,4 +191,4 @@ The `-i` parameter can also be the directory of the image file to be tested (`da
Here is a quick start tutorial for professional users to use PaddleClas on the Linux operating system. The main content is based on the CIFAR-100 data set. You can quickly experience the training of different models, experience loading different pre-trained models, experience the SSLD knowledge distillation solution, and experience data augmentation. Please refer to [Installation Guide](../installation/install_paddleclas_en.md) to configure the operating environment and clone PaddleClas code.
Here is a quick start tutorial for professional users to use PaddleClas on the Linux operating system. The main content is based on the CIFAR-100 data set. You can quickly experience the training of different models, experience loading different pre-trained models, experience the SSLD knowledge distillation solution, and experience data augmentation. Please refer to [Installation Guide](../installation.md) to configure the operating environment and clone PaddleClas code.
------
...
...
@@ -37,7 +37,7 @@ Here is a quick start tutorial for professional users to use PaddleClas on the L
cd path_to_PaddleClas
```
<aname="1.1.1"></a>
<aname="1.1.1"></a>
#### 1.1.1 Prepare CIFAR100
...
...
@@ -54,11 +54,11 @@ cd ../
## 2. Model training
<aname="2.1"></a>
<aname="2.1"></a>
### 2.1 Single label training
<aname="2.1.1"></a>
<aname="2.1.1"></a>
#### 2.1.1 Training without loading the pre-trained model
* Since the initial learning rate and batch-size need to maintain a linear relationship, when training is switched from 4 GPUs to 1 GPU, the total batch-size is reduced to 1/4 of the original, and the learning rate also needs to be reduced to 1/4 of the original, so changed the default learning rate from 0.04 to 0.01.
<aname="2.1.2"></a>
<aname="2.1.2"></a>
#### 2.1.2 Transfer learning
...
...
@@ -148,7 +148,7 @@ The highest accuracy of the validation set is about 0.601, which is nearly 12% l
PaddleClas contains many data augmentation methods, such as Mixup, Cutout, RandomErasing, etc. For specific methods, please refer to [Data augmentation chapter](../algorithm_introduction/DataAugmentation_en.md)。
<aname="3.1"></a>
<aname="3.1"></a>
### 3.1 Data augmentation-Mixup
...
...
@@ -245,11 +245,11 @@ In the end, the accuracy on the CIFAR100 validation set was 64.4%. Using the tea
## 5. Model evaluation and inference
<aname="5.1"></a>
<aname="5.1"></a>
### 5.1 Single-label classification model evaluation and inference
<aname="5.1.1"></a>
<aname="5.1.1"></a>
#### 5.1.1 Single-label classification model evaluation
Experience the training, evaluation, and prediction of multi-label classification based on the [NUS-WIDE-SCENE](https://lms.comp.nus.edu.sg/wp-content/uploads/2019/research/nuswide/NUS-WIDE.html) dataset, which is a subset of the NUS-WIDE dataset. Please first install PaddlePaddle and PaddleClas, see [Paddle Installation](../installation/install_paddle_en.md) and [PaddleClas installation](../installation/install_paddleclas_en.md) for more details.
Experience the training, evaluation, and prediction of multi-label classification based on the [NUS-WIDE-SCENE](https://lms.comp.nus.edu.sg/wp-content/uploads/2019/research/nuswide/NUS-WIDE.html) dataset, which is a subset of the NUS-WIDE dataset. Please first install PaddlePaddle and PaddleClas, see [Installation Doc](../installation.md) for more details.
@@ -99,7 +99,7 @@ One can preview it according to the instructions in [Function Experience - Previ
### 2.1 Environment configuration
* Installation: Please refer to the document [Environment Preparation](../installation/install_paddleclas_en.md) to configure the PaddleClas operating environment.
* Installation: Please refer to the document [Environment Preparation](../installation.md) to configure the PaddleClas operating environment.
* Go to the `deploy` run directory. All the content and scripts in this section need to be run in the `deploy` directory, you can enter the `deploy` directory with the following scripts.
