add multilabel feature

docs/en/advanced_tutorials/multilabel/multilabel_en.md

@@ -25,58 +25,68 @@ tar -xf NUS-SCENE-dataset.tar
 cd ../../
 ```
 
-## Environment
+## Training
 
-### Download pretrained model
+```shell
+export CUDA_VISIBLE_DEVICES=0,1,2,3
+python3 -m paddle.distributed.launch \
+    --gpus="0,1,2,3" \
+    tools/train.py \
+        -c ./ppcls/configs/quick_start/professional/MobileNetV1_multilabel.yaml
+```
 
-You can use the following commands to download the pretrained model of ResNet50_vd.
+After training for 10 epochs, the best accuracy over the validation set should be around 0.95.
+
+## Evaluation
 
 ```bash
-mkdir pretrained
-cd pretrained
-wget https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet50_vd_pretrained.pdparams
-cd ../
+python tools/eval.py \
+    -c ./ppcls/configs/quick_start/professional/MobileNetV1_multilabel.yaml \
+    -o Arch.pretrained="./output/MobileNetV1/best_model"
 ```
 
-## Training
+## Prediction
 
-```shell
-export CUDA_VISIBLE_DEVICES=0
-python -m paddle.distributed.launch \
-    --gpus="0" \
-    tools/train.py \
-        -c ./configs/quick_start/ResNet50_vd_multilabel.yaml
+```bash
+python3 tools/infer.py
+    -c ./ppcls/configs/quick_start/professional/MobileNetV1_multilabel.yaml \
+    -o Arch.pretrained="./output/MobileNetV1/best_model"
 ```
 
-After training for 10 epochs, the best accuracy over the validation set should be around 0.72.
+You will get multiple output such as the following:
+```
+[{'class_ids': [6, 13, 17, 23, 26, 30], 'scores': [0.95683, 0.5567, 0.55211, 0.99088, 0.5943, 0.78767], 'file_name': './deploy/images/0517_2715693311.jpg', 'label_names': []}]  
+```
 
-## Evaluation
+## Prediction based on prediction engine
+
+### Export model
 
 ```bash
-python tools/eval.py \
-    -c ./configs/quick_start/ResNet50_vd_multilabel.yaml \
-    -o pretrained_model="./output/ResNet50_vd/best_model/ppcls" \
-    -o load_static_weights=False
+python3 tools/export_model.py \
+    -c ./ppcls/configs/quick_start/professional/MobileNetV1_multilabel.yaml \
+    -o Arch.pretrained="./output/MobileNetV1/best_model"
 ```
 
-The metric of evaluation is based on mAP, which is commonly used in multilabel task to show model perfermance. The mAP over validation set should be around 0.57.
+The default path of the inference model is under the current path `./inference`
 
-## Prediction
+### Prediction based on prediction engine
+
+Enter the deploy directory:
 
 ```bash
-python tools/infer/infer.py \
-    -i "./dataset/NUS-WIDE-SCENE/NUS-SCENE-dataset/images/0199_434752251.jpg" \
-    --model ResNet50_vd \
-    --pretrained_model "./output/ResNet50_vd/best_model/ppcls" \
-    --use_gpu True \
-    --load_static_weights False \
-    --multilabel True \
-    --class_num 33
+cd ./deploy
+```
+
+Prediction based on prediction engine:
+
+```
+python3 python/predict_cls.py \
+     -c configs/inference_multilabel_cls.yaml
 ```
 
 You will get multiple output such as the following:
+
 ```
-    class id: 3, probability: 0.6025
-    class id: 23, probability: 0.5491
-    class id: 32, probability: 0.7006
+0517_2715693311.jpg:    class id(s): [6, 13, 17, 23, 26, 30], score(s): [0.96, 0.56, 0.55, 0.99, 0.59, 0.79], label_name(s): []
 ```

ppcls/configs/quick_start/MobileNetV1_multilabel.yaml

-# global configs
-Global:
-  checkpoints: null
-  pretrained_model: null
-  output_dir: ./output/
-  device: gpu
-  save_interval: 1
-  eval_during_train: True
-  eval_interval: 1
-  epochs: 10
-  print_batch_step: 10
-  use_visualdl: False
-  # used for static mode and model export
-  image_shape: [3, 224, 224]
-  save_inference_dir: ./inference
-  use_multilabel: True
-# model architecture
-Arch:
-  name: MobileNetV1
-  class_num: 33
-  pretrained: True
-
-# loss function config for traing/eval process
-Loss:
-  Train:
-    - MultiLabelLoss:
-        weight: 1.0
-  Eval:
-    - MultiLabelLoss:
-        weight: 1.0
-
-
-Optimizer:
-  name: Momentum
-  momentum: 0.9
-  lr:
-    name: Cosine
-    learning_rate: 0.1
-  regularizer:
-    name: 'L2'
-    coeff: 0.00004
-
-
-# data loader for train and eval
-DataLoader:
-  Train:
-    dataset:
-      name: MultiLabelDataset
-      image_root: ./dataset/NUS-SCENE-dataset/images/
-      cls_label_path: ./dataset/NUS-SCENE-dataset/multilabel_train_list.txt
-      transform_ops:
-        - DecodeImage:
-            to_rgb: True
-            channel_first: False
-        - RandCropImage:
-            size: 224
-        - RandFlipImage:
-            flip_code: 1
-        - NormalizeImage:
-            scale: 1.0/255.0
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-
-    sampler:
-      name: DistributedBatchSampler
-      batch_size: 64
-      drop_last: False
-      shuffle: True
-    loader:
-      num_workers: 4
-      use_shared_memory: True
-
-  Eval:
-    dataset: 
-      name: MultiLabelDataset
-      image_root: ./dataset/NUS-SCENE-dataset/images/
-      cls_label_path: ./dataset/NUS-SCENE-dataset/multilabel_test_list.txt
-      transform_ops:
-        - DecodeImage:
-            to_rgb: True
-            channel_first: False
-        - ResizeImage:
-            resize_short: 256
-        - CropImage:
-            size: 224
-        - NormalizeImage:
-            scale: 1.0/255.0
-            mean: [0.485, 0.456, 0.406]
-            std: [0.229, 0.224, 0.225]
-            order: ''
-    sampler:
-      name: DistributedBatchSampler
-      batch_size: 256
-      drop_last: False
-      shuffle: False
-    loader:
-      num_workers: 4
-      use_shared_memory: True
-
-Infer:
-  infer_imgs: dataset/NUS-SCENE-dataset/images/0001_109549716.jpg
-  batch_size: 10
-  transforms:
-    - DecodeImage:
-        to_rgb: True
-        channel_first: False
-    - ResizeImage:
-        resize_short: 256
-    - CropImage:
-        size: 224
-    - NormalizeImage:
-        scale: 1.0/255.0
-        mean: [0.485, 0.456, 0.406]
-        std: [0.229, 0.224, 0.225]
-        order: ''
-    - ToCHWImage:
-  PostProcess:
-    name: MutiLabelTopk
-    topk: 5
-    class_id_map_file: None
-
-Metric:
-  Train:
-    - HammingDistance:
-    - AccuracyScore:
-  Eval:
-    - HammingDistance:
-    - AccuracyScore:

train.sh

-#!/usr/bin/env bash
-
-# for single card train
-# python3.7 tools/train.py -c ./ppcls/configs/ImageNet/ResNet/ResNet50.yaml
-
-# for multi-cards train
-python3.7 -m paddle.distributed.launch --gpus="0" tools/train.py -c ./MobileNetV2.yaml