fix pylint

model_zoo/deeplabv3/README.md

@@ -1,10 +1,7 @@
 # Deeplab-V3 Example
 
 ## Description
-- This is an example of training DeepLabv3 with PASCAL VOC 2012 dataset in MindSpore.
-- Paper Rethinking Atrous Convolution for Semantic Image Segmentation
-Liang-Chieh Chen, George Papandreou, Florian Schroff, Hartwig Adam
-
+This is an example of training DeepLabv3 with PASCAL VOC 2012 dataset in MindSpore. 
 
 ## Requirements
 - Install [MindSpore](https://www.mindspore.cn/install/en).

model_zoo/deeplabv3/src/losses.py

@@ -50,7 +50,7 @@ class OhemLoss(nn.Cell):
         losses = self.cross_entropy(logits, one_hot_labels)[0]
         weights = self.cast(self.not_equal(labels, self.ignore_label), mstype.float32) * self.loss_weight
         weighted_losses = self.mul(losses, weights)
-        loss = self.reduce_sum(weighted_losses,(0,))
+        loss = self.reduce_sum(weighted_losses, (0,))
         zeros = self.fill(mstype.float32, self.shape(weights), 0.0)
         ones = self.fill(mstype.float32, self.shape(weights), 1.0)
         present = self.select(self.equal(weights, zeros), zeros, ones)

model_zoo/deeplabv3/train.py

@@ -80,9 +80,9 @@ if __name__ == "__main__":
         ckpoint_cb = ModelCheckpoint(prefix='checkpoint_deeplabv3', config=config_ck)
         callback.append(ckpoint_cb)
     net = deeplabv3_resnet50(config.seg_num_classes, [args_opt.batch_size, 3, args_opt.crop_size, args_opt.crop_size],
-                              infer_scale_sizes=config.eval_scales, atrous_rates=config.atrous_rates,
-                              decoder_output_stride=config.decoder_output_stride, output_stride=config.output_stride,
-                              fine_tune_batch_norm=config.fine_tune_batch_norm, image_pyramid=config.image_pyramid)
+                             infer_scale_sizes=config.eval_scales, atrous_rates=config.atrous_rates,
+                             decoder_output_stride=config.decoder_output_stride, output_stride=config.output_stride,
+                             fine_tune_batch_norm=config.fine_tune_batch_norm, image_pyramid=config.image_pyramid)
     net.set_train()
     model_fine_tune(args_opt, net, 'layer')
     loss = OhemLoss(config.seg_num_classes, config.ignore_label)