Merge pull request #796 from Intsigstephon/develop_reg

add icaroonface dataset and config file

ppcls/configs/Cartoonface/ResNet50_icartoon.yaml

+# global configs
+Global:
+  checkpoints: null
+  pretrained_model: null
+  output_dir: "./output/"
+  device: "gpu"
+  class_num: 5013
+  save_interval: 1
+  eval_mode: "retrieval"
+  eval_during_train: True
+  eval_interval: 1
+  epochs: 120
+  print_batch_step: 10
+  use_visualdl: False
+  image_shape: [3, 224, 224]
+  infer_imgs:
+  save_inference_dir: "./output"
+  feature_normalize: True
+
+Arch:  
+  name: "RecModel"
+  Backbone:
+    name: "ResNet50"
+    pretrained: True
+  BackboneStopLayer: 
+    name: "flatten_0"
+    output_dim: 2048
+  Head:
+    name: "FC"
+    class_num: 5013
+    embedding_size: 2048
+    # margin: 0.5
+    # scale:  80
+  infer_output_key:  "features"
+  infer_add_softmax: "false"
+
+Loss:
+  Train:
+    - CELoss:
+        weight: 1.0
+    # - TripletLoss:  
+    #     margin: 0.1
+    #     weight: 0.1
+  Eval:
+    - CELoss:
+        weight: 1.0
+
+Optimizer:
+  name: Momentum
+  momentum: 0.9
+  lr:
+    name: Piecewise
+    learning_rate: 0.1
+    decay_epochs: [30, 60, 90]
+    values: [0.1, 0.01, 0.001, 0.0001]
+  regularizer:
+    name: 'L2'
+    coeff: 0.0001
+
+DataLoader:
+  Train:
+    dataset:
+        name: ICartoonDataset
+        image_root:  "./dataset/iCartoonFace"
+        cls_label_path:  "./dataset/iCartoonFace/train_list.txt"
+        transform_ops:
+          - RandCropImage:
+              size: 224
+          - RandFlipImage:
+              flip_code: 1
+          - NormalizeImage:
+              scale: 0.00392157
+              mean: [0.485, 0.456, 0.406]
+              std: [0.229, 0.224, 0.225]
+              order: ''
+    sampler:
+        name: DistributedBatchSampler
+        #num_instances: 2
+        batch_size: 256
+        drop_last: False
+        shuffle: True
+    loader:
+        num_workers: 6
+        use_shared_memory: False
+  
+  Eval:
+    Query:
+      dataset: 
+          name: ICartoonDataset
+          image_root: "./dataset/iCartoonFace"
+          cls_label_path: "./dataset/iCartoonFace/query.txt"
+          transform_ops:
+            - ResizeImage:
+                resize_short: 256
+            - CropImage:
+                size: 224
+            - NormalizeImage:
+                scale: 0.00392157
+                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: False
+      loader:
+          num_workers: 6
+          use_shared_memory: False
+
+    Gallery:
+      dataset: 
+          name: ICartoonDataset
+          image_root: "./dataset/iCartoonFace"
+          cls_label_path: "./dataset/iCartoonFace/gallery.txt"
+          transform_ops:
+            - ResizeImage:
+                resize_short: 256
+            - CropImage:
+                size: 224
+            - NormalizeImage:
+                scale: 0.00392157
+                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: False
+      loader:
+          num_workers: 6
+          use_shared_memory: False
+
+Metric:
+    Train:
+    - TopkAcc:
+        topk: [1, 5]
+    Eval:
+    - Recallk:
+        topk: 1

ppcls/data/__init__.py

@@ -25,6 +25,7 @@ from ppcls.data.dataloader.imagenet_dataset import ImageNetDataset
 from ppcls.data.dataloader.multilabel_dataset import MultiLabelDataset
 from ppcls.data.dataloader.common_dataset import create_operators
 from ppcls.data.dataloader.vehicle_dataset import CompCars, VeriWild
+from ppcls.data.dataloader.icartoon_dataset import ICartoonDataset
 
 # sampler
 from ppcls.data.dataloader.DistributedRandomIdentitySampler import DistributedRandomIdentitySampler

ppcls/data/dataloader/icartoon_dataset.py

+#   Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import print_function
+
+import numpy as np
+import os
+
+from .common_dataset import CommonDataset
+
+
+class ICartoonDataset(CommonDataset):
+    def _load_anno(self, seed=None):
+        assert os.path.exists(self._cls_path)
+        assert os.path.exists(self._img_root)
+        self.images = []
+        self.labels = []
+
+        with open(self._cls_path) as fd:
+            lines = fd.readlines()
+            if seed is not None:
+                np.random.RandomState(seed).shuffle(lines)
+            else:
+                np.random.shuffle(lines)
+            for l in lines:
+                l = l.strip().split("\t")
+                self.images.append(os.path.join(self._img_root, l[0][2:]))
+                self.labels.append(int(l[1]))
+                assert os.path.exists(self.images[-1])