Merge pull request #1034 from cuicheng01/develop

support load pretrain from url

ppcls/arch/gears/cosmargin.py

@@ -38,7 +38,7 @@ class CosMargin(paddle.nn.Layer):
 
         input_norm = paddle.sqrt(
             paddle.sum(paddle.square(input), axis=1, keepdim=True))
-        input = paddle.divide(input, x_norm)
+        input = paddle.divide(input, input_norm)
 
         weight = self.fc.weight
         weight_norm = paddle.sqrt(

ppcls/configs/ImageNet/DPN/DPN107.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/DPN/DPN131.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/DPN/DPN68.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/DPN/DPN92.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/DPN/DPN98.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/DarkNet/DarkNet53.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/DataAugment/ResNet50_Cutmix.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
   Eval:
     - CELoss:

ppcls/configs/ImageNet/DataAugment/ResNet50_Mixup.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
   Eval:
     - CELoss:

ppcls/configs/ImageNet/Inception/InceptionV3.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/Inception/InceptionV4.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/Res2Net/Res2Net101_vd_26w_4s.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/Res2Net/Res2Net200_vd_26w_4s.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/Res2Net/Res2Net50_14w_8s.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/Res2Net/Res2Net50_26w_4s.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/Res2Net/Res2Net50_vd_26w_4s.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/ResNeSt/ResNeSt101.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/ResNeSt/ResNeSt50.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/ResNeSt/ResNeSt50_fast_1s1x64d.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/ResNeXt/ResNeXt101_vd_32x4d.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/ResNeXt/ResNeXt101_vd_64x4d.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/ResNeXt/ResNeXt152_vd_32x4d.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/ResNeXt/ResNeXt152_vd_64x4d.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/ResNeXt/ResNeXt50_vd_32x4d.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/ResNeXt/ResNeXt50_vd_64x4d.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/ResNet/ResNet101_vd.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/ResNet/ResNet152_vd.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/ResNet/ResNet18_vd.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/ResNet/ResNet200_vd.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/ResNet/ResNet34_vd.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/ResNet/ResNet50_vd.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/SENet/SENet154_vd.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/SENet/SE_ResNeXt101_32x4d.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/SENet/SE_ResNeXt50_32x4d.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/SENet/SE_ResNeXt50_vd_32x4d.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/SENet/SE_ResNet18_vd.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/SENet/SE_ResNet34_vd.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/SENet/SE_ResNet50_vd.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/Xception/Xception65.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/ImageNet/Xception/Xception71.yaml

@@ -22,7 +22,7 @@ Arch:
 # loss function config for traing/eval process
 Loss:
   Train:
-    - CELoss:
+    - MixCELoss:
         weight: 1.0
         epsilon: 0.1
   Eval:

ppcls/configs/Products/ResNet50_vd_Inshop.yaml

 # global configs
 Global:
   checkpoints: null
-# please download pretrained model via this link:
-# https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/pretrain/product_ResNet50_vd_Aliproduct_v1.0_pretrained.pdparams
-  pretrained_model: product_ResNet50_vd_Aliproduct_v1.0_pretrained
+  pretrained_model: "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/pretrain/product_ResNet50_vd_Aliproduct_v1.0_pretrained.pdparams"
   output_dir: ./output/
   device: gpu
   save_interval: 10

ppcls/configs/Products/ResNet50_vd_SOP.yaml

 # global configs
 Global:
   checkpoints: null
-# please download pretrained model via this link:
-# https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/pretrain/product_ResNet50_vd_Aliproduct_v1.0_pretrained.pdparams
-  pretrained_model: product_ResNet50_vd_Aliproduct_v1.0_pretrained
+  pretrained_model: "https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/rec/models/pretrain/product_ResNet50_vd_Aliproduct_v1.0_pretrained.pdparams"
   output_dir: ./output/
   device: gpu
   save_interval: 10

ppcls/engine/trainer.py

@@ -40,7 +40,7 @@ from ppcls.arch import apply_to_static
 from ppcls.loss import build_loss
 from ppcls.metric import build_metrics
 from ppcls.optimizer import build_optimizer
-from ppcls.utils.save_load import load_dygraph_pretrain
+from ppcls.utils.save_load import load_dygraph_pretrain, load_dygraph_pretrain_from_url
 from ppcls.utils.save_load import init_model
 from ppcls.utils import save_load
 
@@ -78,8 +78,12 @@ class Trainer(object):
         apply_to_static(self.config, self.model)
 
         if self.config["Global"]["pretrained_model"] is not None:
-            load_dygraph_pretrain(self.model,
-                                  self.config["Global"]["pretrained_model"])
+            if self.config["Global"]["pretrained_model"].startswith("http"):
+                load_dygraph_pretrain_from_url(
+                    self.model, self.config["Global"]["pretrained_model"])
+            else:
+                load_dygraph_pretrain(
+                    self.model, self.config["Global"]["pretrained_model"])
 
         if self.config["Global"]["distributed"]:
             self.model = paddle.DataParallel(self.model)
@@ -174,9 +178,12 @@ class Trainer(object):
                     out = self.model(batch[0])
                 else:
                     out = self.model(batch[0], batch[1])
-
                 # calc loss
-                loss_dict = self.train_loss_func(out, batch[1])
+                if self.config["DataLoader"]["Train"]["dataset"].get(
+                        "batch_transform_ops", None):
+                    loss_dict = self.train_loss_func(out, batch[1:])
+                else:
+                    loss_dict = self.train_loss_func(out, batch[1])
 
                 for key in loss_dict:
                     if not key in output_info:

ppcls/loss/__init__.py

@@ -4,7 +4,7 @@ import paddle
 import paddle.nn as nn
 from ppcls.utils import logger
 
-from .celoss import CELoss
+from .celoss import CELoss, MixCELoss
 from .googlenetloss import GoogLeNetLoss
 from .centerloss import CenterLoss
 from .emlloss import EmlLoss
@@ -30,7 +30,6 @@ class CombinedLoss(nn.Layer):
         assert isinstance(config_list, list), (
             'operator config should be a list')
         for config in config_list:
-            print(config)
             assert isinstance(config,
                               dict) and len(config) == 1, "yaml format error"
             name = list(config)[0]

ppcls/loss/celoss.py

@@ -18,6 +18,10 @@ import paddle.nn.functional as F
 
 
 class CELoss(nn.Layer):
+    """
+    Cross entropy loss
+    """
+
     def __init__(self, epsilon=None):
         super().__init__()
         if epsilon is not None and (epsilon <= 0 or epsilon >= 1):
@@ -50,3 +54,21 @@ class CELoss(nn.Layer):
             loss = F.cross_entropy(x, label=label, soft_label=soft_label)
         loss = loss.mean()
         return {"CELoss": loss}
+
+
+class MixCELoss(CELoss):
+    """
+    Cross entropy loss with mix(mixup, cutmix, fixmix)
+    """
+
+    def __init__(self, epsilon=None):
+        super().__init__()
+        self.epsilon = epsilon
+
+    def __call__(self, input, batch):
+        target0, target1, lam = batch
+        loss0 = super().forward(input, target0)["CELoss"]
+        loss1 = super().forward(input, target1)["CELoss"]
+        loss = lam * loss0 + (1.0 - lam) * loss1
+        loss = paddle.mean(loss)
+        return {"MixCELoss": loss}

ppcls/utils/save_load.py

@@ -54,7 +54,7 @@ def load_dygraph_pretrain(model, path=None):
     return
 
 
-def load_dygraph_pretrain_from_url(model, pretrained_url, use_ssld):
+def load_dygraph_pretrain_from_url(model, pretrained_url, use_ssld=False):
     if use_ssld:
         pretrained_url = pretrained_url.replace("_pretrained",
                                                 "_ssld_pretrained")