Upgrade API to PaddlePaddle 1.7 version (#214)

* release change log

* update readme

* update readme

* upload fast-scnn image

* update readme

* update readme

* replace fluid.layers.data

* update api fluid.data and fluid.io.DataLoader
Co-authored-by: NLielinJiang <jianglielin@baidu.com>
Co-authored-by: NLielinJiang <50691816+LielinJiang@users.noreply.github.com>

README.md

@@ -6,7 +6,7 @@
 
 ## 简介
 
-PaddleSeg是基于[PaddlePaddle](https://www.paddlepaddle.org.cn)开发的语义分割库，覆盖了DeepLabv3+, U-Net, ICNet, PSPNet, HRNet等主流分割模型。通过统一的配置，帮助用户更便捷地完成从训练到部署的全流程图像分割应用。
+PaddleSeg是基于[PaddlePaddle](https://www.paddlepaddle.org.cn)开发的语义分割库，覆盖了DeepLabv3+, U-Net, ICNet, PSPNet, HRNet, Fast-SCNN等主流分割模型。通过统一的配置，帮助用户更便捷地完成从训练到部署的全流程图像分割应用。
 
 </br>
 
@@ -33,7 +33,7 @@ PaddleSeg是基于[PaddlePaddle](https://www.paddlepaddle.org.cn)开发的语义
 
 - **模块化设计**
 
-支持U-Net, DeepLabv3+, ICNet, PSPNet, HRNet五种主流分割网络，结合预训练模型和可调节的骨干网络，满足不同性能和精度的要求；选择不同的损失函数如Dice Loss, BCE Loss等方式可以强化小目标和不均衡样本场景下的分割精度。
+支持U-Net, DeepLabv3+, ICNet, PSPNet, HRNet, Fast-SCNN六种主流分割网络，结合预训练模型和可调节的骨干网络，满足不同性能和精度的要求；选择不同的损失函数如Dice Loss, BCE Loss等方式可以强化小目标和不均衡样本场景下的分割精度。
 
 - **高性能**
 
@@ -163,6 +163,14 @@ A: 请将PaddlePaddle升级至1.5.2版本或以上。
 <p align="center">  &#8194;&#8194;&#8194;微信公众号&#8194;&#8194;&#8194;&#8194;&#8194;&#8194;&#8194;&#8194;&#8194;&#8194;&#8194;&#8194;&#8194;&#8194;&#8194;&#8194;官方技术交流QQ群</p>
 
 ## 更新日志
+* 2020.02.25
+
+  **`v0.4.0`**
+  * 新增适用于实时场景且不需要预训练模型的分割网络Fast-SCNN，提供基于Cityscapes的[预训练模型](./docs/model_zoo.md)1个。
+  * 新增LaneNet车道线检测网络，提供[预训练模型](https://github.com/PaddlePaddle/PaddleSeg/tree/release/v0.4.0/contrib/LaneNet#%E4%B8%83-%E5%8F%AF%E8%A7%86%E5%8C%96)一个。
+  * 新增基于PaddleSlim的分割库压缩策略([量化](./slim/quantization/README.md), [蒸馏](./slim/distillation/README.md), [剪枝](./slim/prune/README.md), [搜索](./slim/nas/README.md))
+  
+  
 * 2019.12.15
 
   **`v0.3.0`**

contrib/LaneNet/README.md

@@ -108,7 +108,7 @@ SOLVER:
 使用下述命令启动训练
 
 ```shell
-CUDA_VISIBLE_DEVICES=0 python -u train.py --cfg configs/lanenet.yaml --use_gpu --use_mpio --do_eval
+CUDA_VISIBLE_DEVICES=0 python -u train.py --cfg configs/lanenet.yaml --use_gpu --do_eval
 ```
 
 ## 六. 进行评估

contrib/LaneNet/eval.py

@@ -101,10 +101,10 @@ def evaluate(cfg, ckpt_dir=None, use_gpu=False, use_mpio=False, **kwargs):
         for b in data_gen:
             yield b
 
-    py_reader, pred, grts, masks, accuracy, fp, fn = build_model(
+    data_loader, pred, grts, masks, accuracy, fp, fn = build_model(
         test_prog, startup_prog, phase=ModelPhase.EVAL)
 
-    py_reader.decorate_sample_generator(
+    data_loader.set_sample_generator(
         data_generator, drop_last=False, batch_size=cfg.BATCH_SIZE)
 
     # Get device environment
@@ -127,7 +127,9 @@ def evaluate(cfg, ckpt_dir=None, use_gpu=False, use_mpio=False, **kwargs):
     # Use streaming confusion matrix to calculate mean_iou
     np.set_printoptions(
         precision=4, suppress=True, linewidth=160, floatmode="fixed")
-    fetch_list = [pred.name, grts.name, masks.name, accuracy.name, fp.name, fn.name]
+    fetch_list = [
+        pred.name, grts.name, masks.name, accuracy.name, fp.name, fn.name
+    ]
     num_images = 0
     step = 0
     avg_acc = 0.0
@@ -137,7 +139,7 @@ def evaluate(cfg, ckpt_dir=None, use_gpu=False, use_mpio=False, **kwargs):
     all_step = cfg.DATASET.TEST_TOTAL_IMAGES // cfg.BATCH_SIZE + 1
     timer = Timer()
     timer.start()
-    py_reader.start()
+    data_loader.start()
     while True:
         try:
             step += 1
@@ -153,7 +155,8 @@ def evaluate(cfg, ckpt_dir=None, use_gpu=False, use_mpio=False, **kwargs):
 
             print(
                 "[EVAL]step={} accuracy={:.4f} fp={:.4f} fn={:.4f} step/sec={:.2f} | ETA {}"
-                .format(step, avg_acc / num_images, avg_fp / num_images, avg_fn / num_images, speed,
+                .format(step, avg_acc / num_images, avg_fp / num_images,
+                        avg_fn / num_images, speed,
                         calculate_eta(all_step - step, speed)))
 
             timer.restart()
@@ -162,7 +165,8 @@ def evaluate(cfg, ckpt_dir=None, use_gpu=False, use_mpio=False, **kwargs):
             break
 
     print("[EVAL]#image={} accuracy={:.4f} fp={:.4f} fn={:.4f}".format(
-        num_images, avg_acc / num_images, avg_fp / num_images, avg_fn / num_images))
+        num_images, avg_acc / num_images, avg_fp / num_images,
+        avg_fn / num_images))
 
     return avg_acc / num_images, avg_fp / num_images, avg_fn / num_images
 

contrib/LaneNet/models/model_builder.py

@@ -25,6 +25,7 @@ from pdseg.loss import multi_softmax_with_loss
 from loss import discriminative_loss
 from models.modeling import lanenet
 
+
 class ModelPhase(object):
     """
     Standard name for model phase in PaddleSeg
@@ -107,35 +108,31 @@ def build_model(main_prog, start_prog, phase=ModelPhase.TRAIN):
         width = cfg.EVAL_CROP_SIZE[0]
         height = cfg.EVAL_CROP_SIZE[1]
 
-    image_shape = [cfg.DATASET.DATA_DIM, height, width]
-    grt_shape = [1, height, width]
+    image_shape = [-1, cfg.DATASET.DATA_DIM, height, width]
+    grt_shape = [-1, 1, height, width]
     class_num = cfg.DATASET.NUM_CLASSES
 
     with fluid.program_guard(main_prog, start_prog):
         with fluid.unique_name.guard():
-            image = fluid.layers.data(
-                name='image', shape=image_shape, dtype='float32')
-            label = fluid.layers.data(
-                name='label', shape=grt_shape, dtype='int32')
+            image = fluid.data(name='image', shape=image_shape, dtype='float32')
+            label = fluid.data(name='label', shape=grt_shape, dtype='int32')
             if cfg.MODEL.MODEL_NAME == 'lanenet':
-                label_instance = fluid.layers.data(
+                label_instance = fluid.data(
                     name='label_instance', shape=grt_shape, dtype='int32')
-            mask = fluid.layers.data(
-                name='mask', shape=grt_shape, dtype='int32')
+            mask = fluid.data(name='mask', shape=grt_shape, dtype='int32')
 
-            # use PyReader when doing traning and evaluation
+            # use DataLoader.from_generator when doing traning and evaluation
             if ModelPhase.is_train(phase) or ModelPhase.is_eval(phase):
-                py_reader = fluid.io.PyReader(
+                data_loader = fluid.io.DataLoader.from_generator(
                     feed_list=[image, label, label_instance, mask],
                     capacity=cfg.DATALOADER.BUF_SIZE,
                     iterable=False,
                     use_double_buffer=True)
 
-
             loss_type = cfg.SOLVER.LOSS
             if not isinstance(loss_type, list):
                 loss_type = list(loss_type)
-            
+
             logits = seg_model(image, class_num)
 
             if ModelPhase.is_train(phase):
@@ -144,25 +141,30 @@ def build_model(main_prog, start_prog, phase=ModelPhase.TRAIN):
                 if cfg.MODEL.MODEL_NAME == 'lanenet':
                     embeding_logit = logits[1]
                     logits = logits[0]
-                    disc_loss, _, _, l_reg = discriminative_loss(embeding_logit, label_instance, 4,
-                                                             image_shape[1:], 0.5, 3.0, 1.0, 1.0, 0.001)
+                    disc_loss, _, _, l_reg = discriminative_loss(
+                        embeding_logit, label_instance, 4, image_shape[2:], 0.5,
+                        3.0, 1.0, 1.0, 0.001)
 
                 if "softmax_loss" in loss_type:
                     weight = None
                     if cfg.MODEL.MODEL_NAME == 'lanenet':
                         weight = get_dynamic_weight(label)
-                    seg_loss = multi_softmax_with_loss(logits, label, mask, class_num, weight)
+                    seg_loss = multi_softmax_with_loss(logits, label, mask,
+                                                       class_num, weight)
                     loss_valid = True
                     valid_loss.append("softmax_loss")
 
                 if not loss_valid:
-                    raise Exception("SOLVER.LOSS: {} is set wrong. it should "
-                            "include one of (softmax_loss, bce_loss, dice_loss) at least"
-                            " example: ['softmax_loss']".format(cfg.SOLVER.LOSS))
+                    raise Exception(
+                        "SOLVER.LOSS: {} is set wrong. it should "
+                        "include one of (softmax_loss, bce_loss, dice_loss) at least"
+                        " example: ['softmax_loss']".format(cfg.SOLVER.LOSS))
 
                 invalid_loss = [x for x in loss_type if x not in valid_loss]
                 if len(invalid_loss) > 0:
-                    print("Warning: the loss {} you set is invalid. it will not be included in loss computed.".format(invalid_loss))
+                    print(
+                        "Warning: the loss {} you set is invalid. it will not be included in loss computed."
+                        .format(invalid_loss))
 
                 avg_loss = disc_loss + 0.00001 * l_reg + seg_loss
 
@@ -202,12 +204,12 @@ def build_model(main_prog, start_prog, phase=ModelPhase.TRAIN):
 
             accuracy, fp, fn = compute_metric(pred, label)
             if ModelPhase.is_eval(phase):
-                return py_reader, pred, label, mask, accuracy, fp, fn
+                return data_loader, pred, label, mask, accuracy, fp, fn
 
             if ModelPhase.is_train(phase):
                 optimizer = solver.Solver(main_prog, start_prog)
                 decayed_lr = optimizer.optimise(avg_loss)
-                return py_reader, avg_loss, decayed_lr, pred, label, mask, disc_loss, seg_loss, accuracy, fp, fn
+                return data_loader, avg_loss, decayed_lr, pred, label, mask, disc_loss, seg_loss, accuracy, fp, fn
 
 
 def compute_metric(pred, label):
@@ -216,19 +218,27 @@ def compute_metric(pred, label):
     idx = fluid.layers.where(pred == 1)
     pix_cls_ret = fluid.layers.gather_nd(label, idx)
 
-    correct_num = fluid.layers.reduce_sum(fluid.layers.cast(pix_cls_ret, 'float32'))
+    correct_num = fluid.layers.reduce_sum(
+        fluid.layers.cast(pix_cls_ret, 'float32'))
 
-    gt_num = fluid.layers.cast(fluid.layers.shape(fluid.layers.gather_nd(label,
-                                                                         fluid.layers.where(label == 1)))[0], 'int64')
-    pred_num = fluid.layers.cast(fluid.layers.shape(fluid.layers.gather_nd(pred, idx))[0], 'int64')
+    gt_num = fluid.layers.cast(
+        fluid.layers.shape(
+            fluid.layers.gather_nd(label, fluid.layers.where(label == 1)))[0],
+        'int64')
+    pred_num = fluid.layers.cast(
+        fluid.layers.shape(fluid.layers.gather_nd(pred, idx))[0], 'int64')
     accuracy = correct_num / gt_num
 
     false_pred = pred_num - correct_num
-    fp = fluid.layers.cast(false_pred, 'float32') / fluid.layers.cast(fluid.layers.shape(pix_cls_ret)[0], 'int64')
-
-    label_cls_ret = fluid.layers.gather_nd(label, fluid.layers.where(label == 1))
-    mis_pred = fluid.layers.cast(fluid.layers.shape(label_cls_ret)[0], 'int64') - correct_num
-    fn = fluid.layers.cast(mis_pred, 'float32') / fluid.layers.cast(fluid.layers.shape(label_cls_ret)[0], 'int64')
+    fp = fluid.layers.cast(false_pred, 'float32') / fluid.layers.cast(
+        fluid.layers.shape(pix_cls_ret)[0], 'int64')
+
+    label_cls_ret = fluid.layers.gather_nd(label,
+                                           fluid.layers.where(label == 1))
+    mis_pred = fluid.layers.cast(fluid.layers.shape(label_cls_ret)[0],
+                                 'int64') - correct_num
+    fn = fluid.layers.cast(mis_pred, 'float32') / fluid.layers.cast(
+        fluid.layers.shape(label_cls_ret)[0], 'int64')
     accuracy.stop_gradient = True
     fp.stop_gradient = True
     fn.stop_gradient = True
@@ -239,7 +249,8 @@ def get_dynamic_weight(label):
     label = fluid.layers.reshape(label, [-1])
     unique_labels, unique_id, counts = fluid.layers.unique_with_counts(label)
     counts = fluid.layers.cast(counts, 'float32')
-    weight = 1.0 / fluid.layers.log((counts / fluid.layers.reduce_sum(counts) + 1.02))
+    weight = 1.0 / fluid.layers.log(
+        (counts / fluid.layers.reduce_sum(counts) + 1.02))
     return weight
 
 

contrib/LaneNet/train.py

@@ -232,9 +232,9 @@ def train(cfg):
     cfg.BATCH_SIZE_PER_DEV = batch_size_per_dev
     print_info("batch_size_per_dev: {}".format(batch_size_per_dev))
 
-    py_reader, avg_loss, lr, pred, grts, masks, emb_loss, seg_loss, accuracy, fp, fn = build_model(
+    data_loader, avg_loss, lr, pred, grts, masks, emb_loss, seg_loss, accuracy, fp, fn = build_model(
         train_prog, startup_prog, phase=ModelPhase.TRAIN)
-    py_reader.decorate_sample_generator(
+    data_loader.set_sample_generator(
         data_generator, batch_size=batch_size_per_dev, drop_last=drop_last)
 
     exe = fluid.Executor(place)
@@ -315,7 +315,10 @@ def train(cfg):
             format(cfg.TRAIN.PRETRAINED_MODEL_DIR))
 
     # fetch_list = [avg_loss.name, lr.name, accuracy.name, precision.name, recall.name]
-    fetch_list = [avg_loss.name, lr.name, seg_loss.name, emb_loss.name, accuracy.name, fp.name, fn.name]
+    fetch_list = [
+        avg_loss.name, lr.name, seg_loss.name, emb_loss.name, accuracy.name,
+        fp.name, fn.name
+    ]
     if args.debug:
         # Fetch more variable info and use streaming confusion matrix to
         # calculate IoU results if in debug mode
@@ -359,7 +362,7 @@ def train(cfg):
         print_info("Use multi-thread reader")
 
     for epoch in range(begin_epoch, cfg.SOLVER.NUM_EPOCHS + 1):
-        py_reader.start()
+        data_loader.start()
         while True:
             try:
                 # If not in debug mode, avoid unnessary log and calculate
@@ -385,16 +388,15 @@ def train(cfg):
                     avg_fn /= args.log_steps
                     speed = args.log_steps / timer.elapsed_time()
                     print((
-                              "epoch={} step={} lr={:.5f} loss={:.4f} seg_loss={:.4f} emb_loss={:.4f} accuracy={:.4} fp={:.4} fn={:.4} step/sec={:.3f} | ETA {}"
-                          ).format(epoch, global_step, lr[0], avg_loss, avg_seg_loss, avg_emb_loss, avg_acc, avg_fp, avg_fn, speed,
-                                   calculate_eta(all_step - global_step, speed)))
+                        "epoch={} step={} lr={:.5f} loss={:.4f} seg_loss={:.4f} emb_loss={:.4f} accuracy={:.4} fp={:.4} fn={:.4} step/sec={:.3f} | ETA {}"
+                    ).format(epoch, global_step, lr[0], avg_loss, avg_seg_loss,
+                             avg_emb_loss, avg_acc, avg_fp, avg_fn, speed,
+                             calculate_eta(all_step - global_step, speed)))
                     if args.use_tb:
                         log_writer.add_scalar('Train/loss', avg_loss,
                                               global_step)
-                        log_writer.add_scalar('Train/lr', lr[0],
-                                              global_step)
-                        log_writer.add_scalar('Train/speed', speed,
-                                              global_step)
+                        log_writer.add_scalar('Train/lr', lr[0], global_step)
+                        log_writer.add_scalar('Train/speed', speed, global_step)
                     sys.stdout.flush()
                     avg_loss = 0.0
                     avg_seg_loss = 0.0
@@ -405,7 +407,7 @@ def train(cfg):
                     timer.restart()
 
             except fluid.core.EOFException:
-                py_reader.reset()
+                data_loader.reset()
                 break
             except Exception as e:
                 print(e)
@@ -423,10 +425,8 @@ def train(cfg):
                 if args.use_tb:
                     log_writer.add_scalar('Evaluate/accuracy', accuracy,
                                           global_step)
-                    log_writer.add_scalar('Evaluate/fp', fp,
-                                          global_step)
-                    log_writer.add_scalar('Evaluate/fn', fn,
-                                          global_step)
+                    log_writer.add_scalar('Evaluate/fp', fp, global_step)
+                    log_writer.add_scalar('Evaluate/fn', fn, global_step)
 
             # Use Tensorboard to visualize results
             if args.use_tb and cfg.DATASET.VIS_FILE_LIST is not None:

docs/models.md

@@ -5,6 +5,7 @@
 - [PSPNet](#PSPNet)
 - [ICNet](#ICNet)
 - [HRNet](#HRNet)
+- [Fast-SCNN](#Fast-SCNN)
 
 ## U-Net
 U-Net [1] 起源于医疗图像分割，整个网络是标准的encoder-decoder网络，特点是参数少，计算快，应用性强，对于一般场景适应度很高。U-Net最早于2015年提出，并在ISBI 2015 Cell Tracking Challenge取得了第一。经过发展，目前有多个变形和应用。
@@ -58,6 +59,14 @@ HRNet在人体姿态估计、语义分割和目标检测领域都取得了显著
 
 ![](./imgs/hrnet.png)
 
+### Fast-SCNN
+
+Fast-SCNN [7] 是一个面向实时的语义分割网络。在双分支的结构基础上，大量使用了深度可分离卷积和逆残差（inverted-residual）模块，并且使用特征融合构造金字塔池化模块 (Pyramid Pooling Module)来融合上下文信息。这使得Fast-SCNN在保持高效的情况下能学习到丰富的细节信息。
+
+整个网络结构如下：
+
+![](./imgs/fast-scnn.png)
+
 ## 参考文献
 
 [1] [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://arxiv.org/abs/1505.04597)
@@ -72,3 +81,6 @@ HRNet在人体姿态估计、语义分割和目标检测领域都取得了显著
 
 [6] [Deep High-Resolution Representation Learning for Visual Recognition](https://arxiv.org/abs/1908.07919)
 
+[7] [Fast-SCNN: Fast Semantic Segmentation Network](https://arxiv.org/abs/1902.04502)
+
+

pdseg/eval.py

@@ -92,10 +92,10 @@ def evaluate(cfg, ckpt_dir=None, use_gpu=False, use_mpio=False, **kwargs):
         for b in data_gen:
             yield b[0], b[1], b[2]
 
-    py_reader, avg_loss, pred, grts, masks = build_model(
+    data_loader, avg_loss, pred, grts, masks = build_model(
         test_prog, startup_prog, phase=ModelPhase.EVAL)
 
-    py_reader.decorate_sample_generator(
+    data_loader.set_sample_generator(
         data_generator, drop_last=False, batch_size=cfg.BATCH_SIZE)
 
     # Get device environment
@@ -128,7 +128,7 @@ def evaluate(cfg, ckpt_dir=None, use_gpu=False, use_mpio=False, **kwargs):
     all_step = cfg.DATASET.TEST_TOTAL_IMAGES // cfg.BATCH_SIZE + 1
     timer = Timer()
     timer.start()
-    py_reader.start()
+    data_loader.start()
     while True:
         try:
             step += 1

pdseg/models/backbone/mobilenet_v2.py

@@ -308,8 +308,8 @@ def MobileNetV2_scale():
 
 
 if __name__ == '__main__':
-    image_shape = [3, 224, 224]
-    image = fluid.layers.data(name='image', shape=image_shape, dtype='float32')
+    image_shape = [-1, 3, 224, 224]
+    image = fluid.data(name='image', shape=image_shape, dtype='float32')
     model = MobileNetV2_x1_0()
     logit, decode_ends = model.net(image)
     #print("logit:", logit.shape)

pdseg/models/backbone/xception.py

@@ -311,7 +311,7 @@ def xception_71():
 
 
 if __name__ == '__main__':
-    image_shape = [3, 224, 224]
-    image = fluid.layers.data(name='image', shape=image_shape, dtype='float32')
+    image_shape = [-1, 3, 224, 224]
+    image = fluid.data(name='image', shape=image_shape, dtype='float32')
     model = xception_65()
     logit = model.net(image)

pdseg/models/model_builder.py

@@ -166,8 +166,8 @@ def build_model(main_prog, start_prog, phase=ModelPhase.TRAIN):
         width = cfg.EVAL_CROP_SIZE[0]
         height = cfg.EVAL_CROP_SIZE[1]
 
-    image_shape = [cfg.DATASET.DATA_DIM, height, width]
-    grt_shape = [1, height, width]
+    image_shape = [-1, cfg.DATASET.DATA_DIM, height, width]
+    grt_shape = [-1, 1, height, width]
     class_num = cfg.DATASET.NUM_CLASSES
 
     with fluid.program_guard(main_prog, start_prog):
@@ -175,25 +175,22 @@ def build_model(main_prog, start_prog, phase=ModelPhase.TRAIN):
             # 在导出模型的时候，增加图像标准化预处理,减小预测部署时图像的处理流程
             # 预测部署时只须对输入图像增加batch_size维度即可
             if ModelPhase.is_predict(phase):
-                origin_image = fluid.layers.data(
+                origin_image = fluid.data(
                     name='image',
                     shape=[-1, -1, -1, cfg.DATASET.DATA_DIM],
-                    dtype='float32',
-                    append_batch_size=False)
+                    dtype='float32')
                 image, valid_shape, origin_shape = export_preprocess(
                     origin_image)
 
             else:
-                image = fluid.layers.data(
+                image = fluid.data(
                     name='image', shape=image_shape, dtype='float32')
-            label = fluid.layers.data(
-                name='label', shape=grt_shape, dtype='int32')
-            mask = fluid.layers.data(
-                name='mask', shape=grt_shape, dtype='int32')
+            label = fluid.data(name='label', shape=grt_shape, dtype='int32')
+            mask = fluid.data(name='mask', shape=grt_shape, dtype='int32')
 
-            # use PyReader when doing traning and evaluation
+            # use DataLoader when doing traning and evaluation
             if ModelPhase.is_train(phase) or ModelPhase.is_eval(phase):
-                py_reader = fluid.io.PyReader(
+                data_loader = fluid.io.DataLoader.from_generator(
                     feed_list=[image, label, mask],
                     capacity=cfg.DATALOADER.BUF_SIZE,
                     iterable=False,
@@ -227,7 +224,8 @@ def build_model(main_prog, start_prog, phase=ModelPhase.TRAIN):
                 if "softmax_loss" in loss_type:
                     weight = cfg.SOLVER.CROSS_ENTROPY_WEIGHT
                     avg_loss_list.append(
-                        multi_softmax_with_loss(logits, label, mask, class_num, weight))
+                        multi_softmax_with_loss(logits, label, mask, class_num,
+                                                weight))
                     loss_valid = True
                     valid_loss.append("softmax_loss")
                 if "dice_loss" in loss_type:
@@ -300,12 +298,12 @@ def build_model(main_prog, start_prog, phase=ModelPhase.TRAIN):
                 return pred, logit
 
             if ModelPhase.is_eval(phase):
-                return py_reader, avg_loss, pred, label, mask
+                return data_loader, avg_loss, pred, label, mask
 
             if ModelPhase.is_train(phase):
                 optimizer = solver.Solver(main_prog, start_prog)
                 decayed_lr = optimizer.optimise(avg_loss)
-                return py_reader, avg_loss, decayed_lr, pred, label, mask
+                return data_loader, avg_loss, decayed_lr, pred, label, mask
 
 
 def to_int(string, dest="I"):

pdseg/models/modeling/hrnet.py

@@ -202,7 +202,7 @@ def hrnet(input, num_classes):
     return logit
 
 if __name__ == '__main__':
-    image_shape = [3, 769, 769]
-    image = fluid.layers.data(name='image', shape=image_shape, dtype='float32')
+    image_shape = [-1, 3, 769, 769]
+    image = fluid.data(name='image', shape=image_shape, dtype='float32')
     logit = hrnet(image, 4)
     print("logit:", logit.shape)

pdseg/models/modeling/icnet.py

@@ -191,7 +191,7 @@ def icnet(input, num_classes):
 
 
 if __name__ == '__main__':
-    image_shape = [3, 320, 320]
-    image = fluid.layers.data(name='image', shape=image_shape, dtype='float32')
+    image_shape = [-1, 3, 320, 320]
+    image = fluid.data(name='image', shape=image_shape, dtype='float32')
     logit = icnet(image, 4)
     print("logit:", logit.shape)

pdseg/models/modeling/unet.py

@@ -129,7 +129,7 @@ def unet(input, num_classes):
 
 
 if __name__ == '__main__':
-    image_shape = [3, 320, 320]
-    image = fluid.layers.data(name='image', shape=image_shape, dtype='float32')
+    image_shape = [-1, 3, 320, 320]
+    image = fluid.data(name='image', shape=image_shape, dtype='float32')
     logit = unet(image, 4)
     print("logit:", logit.shape)

pdseg/train.py

@@ -103,7 +103,7 @@ def parse_args():
         help='If set True, enable continuous evaluation job.'
         'This flag is only used for internal test.',
         action='store_true')
-    
+
     # NOTE: This for benchmark
     parser.add_argument(
         '--is_profiler',
@@ -114,7 +114,7 @@ def parse_args():
         '--profiler_path',
         help='the profiler output file path.(used for benchmark)',
         default='./seg.profiler',
-        type=str) 
+        type=str)
     return parser.parse_args()
 
 
@@ -265,9 +265,9 @@ def train(cfg):
     batch_size_per_dev = cfg.BATCH_SIZE // dev_count
     print_info("batch_size_per_dev: {}".format(batch_size_per_dev))
 
-    py_reader, avg_loss, lr, pred, grts, masks = build_model(
+    data_loader, avg_loss, lr, pred, grts, masks = build_model(
         train_prog, startup_prog, phase=ModelPhase.TRAIN)
-    py_reader.decorate_sample_generator(
+    data_loader.set_sample_generator(
         data_generator, batch_size=batch_size_per_dev, drop_last=drop_last)
 
     exe = fluid.Executor(place)
@@ -386,7 +386,7 @@ def train(cfg):
         print_info("Use multi-thread reader")
 
     for epoch in range(begin_epoch, cfg.SOLVER.NUM_EPOCHS + 1):
-        py_reader.start()
+        data_loader.start()
         while True:
             try:
                 if args.debug:
@@ -454,16 +454,16 @@ def train(cfg):
                         sys.stdout.flush()
                         avg_loss = 0.0
                         timer.restart()
-                     
+
                     # NOTE : used for benchmark, profiler tools
-                    if args.is_profiler and epoch == 1 and global_step == args.log_steps: 
+                    if args.is_profiler and epoch == 1 and global_step == args.log_steps:
                         profiler.start_profiler("All")
                     elif args.is_profiler and epoch == 1 and global_step == args.log_steps + 5:
                         profiler.stop_profiler("total", args.profiler_path)
                         return
 
             except fluid.core.EOFException:
-                py_reader.reset()
+                data_loader.reset()
                 break
             except Exception as e:
                 print(e)

slim/distillation/README.md

@@ -89,7 +89,6 @@ python -m paddle.distributed.launch ./slim/distillation/train_distill.py \
 --log_steps 10 --cfg ./slim/distillation/cityscape.yaml \
 --teacher_cfg ./slim/distillation/cityscape_teacher.yaml \
 --use_gpu \
---use_mpio \
 --do_eval 
 ```
 

slim/distillation/model_builder.py

@@ -156,7 +156,10 @@ def export_preprocess(image):
     return image, valid_shape, origin_shape
 
 
-def build_model(main_prog=None, start_prog=None, phase=ModelPhase.TRAIN, **kwargs):
+def build_model(main_prog=None,
+                start_prog=None,
+                phase=ModelPhase.TRAIN,
+                **kwargs):
 
     if not ModelPhase.is_valid_phase(phase):
         raise ValueError("ModelPhase {} is not valid!".format(phase))
@@ -167,8 +170,8 @@ def build_model(main_prog=None, start_prog=None, phase=ModelPhase.TRAIN, **kwarg
         width = cfg.EVAL_CROP_SIZE[0]
         height = cfg.EVAL_CROP_SIZE[1]
 
-    image_shape = [cfg.DATASET.DATA_DIM, height, width]
-    grt_shape = [1, height, width]
+    image_shape = [-1, cfg.DATASET.DATA_DIM, height, width]
+    grt_shape = [-1, 1, height, width]
     class_num = cfg.DATASET.NUM_CLASSES
 
     #with fluid.program_guard(main_prog, start_prog):
@@ -176,36 +179,30 @@ def build_model(main_prog=None, start_prog=None, phase=ModelPhase.TRAIN, **kwarg
     # 在导出模型的时候，增加图像标准化预处理,减小预测部署时图像的处理流程
     # 预测部署时只须对输入图像增加batch_size维度即可
     if cfg.SLIM.KNOWLEDGE_DISTILL_IS_TEACHER:
-        image = main_prog.global_block()._clone_variable(kwargs['image'],
-                                                         force_persistable=False)
-        label = main_prog.global_block()._clone_variable(kwargs['label'],
-                                                         force_persistable=False)
-        mask = main_prog.global_block()._clone_variable(kwargs['mask'],
-                                                        force_persistable=False)
+        image = main_prog.global_block()._clone_variable(
+            kwargs['image'], force_persistable=False)
+        label = main_prog.global_block()._clone_variable(
+            kwargs['label'], force_persistable=False)
+        mask = main_prog.global_block()._clone_variable(
+            kwargs['mask'], force_persistable=False)
     else:
         if ModelPhase.is_predict(phase):
-            origin_image = fluid.layers.data(
+            origin_image = fluid.data(
                 name='image',
                 shape=[-1, -1, -1, cfg.DATASET.DATA_DIM],
-                dtype='float32',
-                append_batch_size=False)
-            image, valid_shape, origin_shape = export_preprocess(
-                origin_image)
+                dtype='float32')
+            image, valid_shape, origin_shape = export_preprocess(origin_image)
 
         else:
-            image = fluid.layers.data(
-                name='image', shape=image_shape, dtype='float32')
-        label = fluid.layers.data(
-            name='label', shape=grt_shape, dtype='int32')
-        mask = fluid.layers.data(
-            name='mask', shape=grt_shape, dtype='int32')
+            image = fluid.data(name='image', shape=image_shape, dtype='float32')
+        label = fluid.data(name='label', shape=grt_shape, dtype='int32')
+        mask = fluid.data(name='mask', shape=grt_shape, dtype='int32')
 
-
-    # use PyReader when doing traning and evaluation
+    # use DataLoader.from_generator when doing traning and evaluation
     if ModelPhase.is_train(phase) or ModelPhase.is_eval(phase):
-        py_reader = None
+        data_loader = None
         if not cfg.SLIM.KNOWLEDGE_DISTILL_IS_TEACHER:
-            py_reader = fluid.io.PyReader(
+            data_loader = fluid.io.DataLoader.from_generator(
                 feed_list=[image, label, mask],
                 capacity=cfg.DATALOADER.BUF_SIZE,
                 iterable=False,
@@ -219,16 +216,14 @@ def build_model(main_prog=None, start_prog=None, phase=ModelPhase.TRAIN, **kwarg
     if class_num > 2 and (("dice_loss" in loss_type) or
                           ("bce_loss" in loss_type)):
         raise Exception(
-            "dice loss and bce loss is only applicable to binary classfication"
-        )
+            "dice loss and bce loss is only applicable to binary classfication")
 
     # 在两类分割情况下，当loss函数选择dice_loss或bce_loss的时候，最后logit输出通道数设置为1
     if ("dice_loss" in loss_type) or ("bce_loss" in loss_type):
         class_num = 1
         if "softmax_loss" in loss_type:
             raise Exception(
-                "softmax loss can not combine with dice loss or bce loss"
-            )
+                "softmax loss can not combine with dice loss or bce loss")
     logits = seg_model(image, class_num)
 
     # 根据选择的loss函数计算相应的损失函数
@@ -289,10 +284,7 @@ def build_model(main_prog=None, start_prog=None, phase=ModelPhase.TRAIN, **kwarg
             logit, axes=[2, 3], starts=[0, 0], ends=valid_shape)
 
         logit = fluid.layers.resize_bilinear(
-            logit,
-            out_shape=origin_shape,
-            align_corners=False,
-            align_mode=0)
+            logit, out_shape=origin_shape, align_corners=False, align_mode=0)
         logit = fluid.layers.argmax(logit, axis=1)
         return origin_image, logit
 
@@ -312,7 +304,7 @@ def build_model(main_prog=None, start_prog=None, phase=ModelPhase.TRAIN, **kwarg
         return pred, logit
 
     if ModelPhase.is_eval(phase):
-        return py_reader, avg_loss, pred, label, mask
+        return data_loader, avg_loss, pred, label, mask
 
     if ModelPhase.is_train(phase):
         decayed_lr = None
@@ -321,7 +313,7 @@ def build_model(main_prog=None, start_prog=None, phase=ModelPhase.TRAIN, **kwarg
             decayed_lr = optimizer.optimise(avg_loss)
         # optimizer = solver.Solver(main_prog, start_prog)
         # decayed_lr = optimizer.optimise(avg_loss)
-        return py_reader, avg_loss, decayed_lr, pred, label, mask, image
+        return data_loader, avg_loss, decayed_lr, pred, label, mask, image
 
 
 def to_int(string, dest="I"):

slim/distillation/train_distill.py

@@ -48,6 +48,7 @@ from utils import dist_utils
 import solver
 from paddleslim.dist.single_distiller import merge, l2_loss
 
+
 def parse_args():
     parser = argparse.ArgumentParser(description='PaddleSeg training')
     parser.add_argument(
@@ -260,8 +261,9 @@ def train(cfg):
     batch_size_per_dev = cfg.BATCH_SIZE // dev_count
     print_info("batch_size_per_dev: {}".format(batch_size_per_dev))
 
-    py_reader, loss, lr, pred, grts, masks, image = build_model(phase=ModelPhase.TRAIN)
-    py_reader.decorate_sample_generator(
+    data_loader, loss, lr, pred, grts, masks, image = build_model(
+        phase=ModelPhase.TRAIN)
+    data_loader.set_sample_generator(
         data_generator, batch_size=batch_size_per_dev, drop_last=drop_last)
 
     exe = fluid.Executor(place)
@@ -274,8 +276,12 @@ def train(cfg):
     with fluid.program_guard(teacher_program, teacher_startup_program):
         with fluid.unique_name.guard():
             _, teacher_loss, _, _, _, _, _ = build_model(
-                teacher_program, teacher_startup_program, phase=ModelPhase.TRAIN, image=image,
-                label=grts, mask=masks)
+                teacher_program,
+                teacher_startup_program,
+                phase=ModelPhase.TRAIN,
+                image=image,
+                label=grts,
+                mask=masks)
 
     exe.run(teacher_startup_program)
 
@@ -293,7 +299,9 @@ def train(cfg):
         'mask': 'mask',
     }
     merge(teacher_program, fluid.default_main_program(), data_name_map, place)
-    distill_pairs = [['teacher_bilinear_interp_2.tmp_0', 'bilinear_interp_0.tmp_0']]
+    distill_pairs = [[
+        'teacher_bilinear_interp_2.tmp_0', 'bilinear_interp_0.tmp_0'
+    ]]
 
     def distill(pairs, weight):
         """
@@ -322,7 +330,8 @@ def train(cfg):
     build_strategy.fuse_all_optimizer_ops = False
     build_strategy.fuse_elewise_add_act_ops = True
     if cfg.NUM_TRAINERS > 1 and args.use_gpu:
-        dist_utils.prepare_for_multi_process(exe, build_strategy, fluid.default_main_program())
+        dist_utils.prepare_for_multi_process(exe, build_strategy,
+                                             fluid.default_main_program())
         exec_strategy.num_threads = 1
 
     if cfg.TRAIN.SYNC_BATCH_NORM and args.use_gpu:
@@ -334,10 +343,11 @@ def train(cfg):
             print_info(
                 "Sync BatchNorm strategy will not be effective if GPU device"
                 " count <= 1")
-    compiled_train_prog = fluid.CompiledProgram(fluid.default_main_program()).with_data_parallel(
-        loss_name=all_loss.name,
-        exec_strategy=exec_strategy,
-        build_strategy=build_strategy)
+    compiled_train_prog = fluid.CompiledProgram(
+        fluid.default_main_program()).with_data_parallel(
+            loss_name=all_loss.name,
+            exec_strategy=exec_strategy,
+            build_strategy=build_strategy)
 
     # Resume training
     begin_epoch = cfg.SOLVER.BEGIN_EPOCH
@@ -387,7 +397,9 @@ def train(cfg):
             format(cfg.TRAIN.PRETRAINED_MODEL_DIR))
 
     #fetch_list = [avg_loss.name, lr.name]
-    fetch_list = [loss.name, 'teacher_' + teacher_loss.name, distill_loss.name, lr.name]
+    fetch_list = [
+        loss.name, 'teacher_' + teacher_loss.name, distill_loss.name, lr.name
+    ]
 
     if args.debug:
         # Fetch more variable info and use streaming confusion matrix to
@@ -431,7 +443,7 @@ def train(cfg):
         print_info("Use multi-thread reader")
 
     for epoch in range(begin_epoch, cfg.SOLVER.NUM_EPOCHS + 1):
-        py_reader.start()
+        data_loader.start()
         while True:
             try:
                 if args.debug:
@@ -491,7 +503,8 @@ def train(cfg):
                         speed = args.log_steps / timer.elapsed_time()
                         print((
                             "epoch={} step={} lr={:.5f} loss={:.4f} teacher loss={:.4f} distill loss={:.4f} step/sec={:.3f} | ETA {}"
-                        ).format(epoch, global_step, lr[0], avg_loss, avg_t_loss, avg_d_loss, speed,
+                        ).format(epoch, global_step, lr[0], avg_loss,
+                                 avg_t_loss, avg_d_loss, speed,
                                  calculate_eta(all_step - global_step, speed)))
                         if args.use_tb:
                             log_writer.add_scalar('Train/loss', avg_loss,
@@ -507,7 +520,7 @@ def train(cfg):
                         timer.restart()
 
             except fluid.core.EOFException:
-                py_reader.reset()
+                data_loader.reset()
                 break
             except Exception as e:
                 print(e)

slim/nas/README.md

@@ -46,7 +46,7 @@ SLIM:
 ## 训练与评估
 执行以下命令，边训练边评估
 ```shell
-CUDA_VISIBLE_DEVICES=0 python -u ./slim/nas/train_nas.py --log_steps 10 --cfg configs/deeplabv3p_mobilenetv2_cityscapes.yaml --use_gpu --use_mpio \
+CUDA_VISIBLE_DEVICES=0 python -u ./slim/nas/train_nas.py --log_steps 10 --cfg configs/deeplabv3p_mobilenetv2_cityscapes.yaml --use_gpu \
 SLIM.NAS_PORT 23333 \
 SLIM.NAS_ADDRESS "" \
 SLIM.NAS_SEARCH_STEPS 2 \

slim/nas/eval_nas.py

@@ -45,6 +45,7 @@ from metrics import ConfusionMatrix
 
 from mobilenetv2_search_space import MobileNetV2SpaceSeg
 
+
 def parse_args():
     parser = argparse.ArgumentParser(description='PaddleSeg model evalution')
     parser.add_argument(
@@ -98,10 +99,10 @@ def evaluate(cfg, ckpt_dir=None, use_gpu=False, use_mpio=False, **kwargs):
         for b in data_gen:
             yield b[0], b[1], b[2]
 
-    py_reader, avg_loss, pred, grts, masks = build_model(
+    data_loader, avg_loss, pred, grts, masks = build_model(
         test_prog, startup_prog, phase=ModelPhase.EVAL, arch=kwargs['arch'])
 
-    py_reader.decorate_sample_generator(
+    data_loader.set_sample_generator(
         data_generator, drop_last=False, batch_size=cfg.BATCH_SIZE)
 
     # Get device environment
@@ -134,7 +135,7 @@ def evaluate(cfg, ckpt_dir=None, use_gpu=False, use_mpio=False, **kwargs):
     all_step = cfg.DATASET.TEST_TOTAL_IMAGES // cfg.BATCH_SIZE + 1
     timer = Timer()
     timer.start()
-    py_reader.start()
+    data_loader.start()
     while True:
         try:
             step += 1

slim/nas/model_builder.py

@@ -74,9 +74,7 @@ def seg_model(image, class_num, arch):
     if model_name == 'deeplabv3p':
         logits = deeplab.deeplabv3p_nas(image, class_num, arch)
     else:
-        raise Exception(
-            "unknow model name, only support deeplabv3p"
-        )
+        raise Exception("unknow model name, only support deeplabv3p")
     return logits
 
 
@@ -156,8 +154,8 @@ def build_model(main_prog, start_prog, phase=ModelPhase.TRAIN, arch=None):
         width = cfg.EVAL_CROP_SIZE[0]
         height = cfg.EVAL_CROP_SIZE[1]
 
-    image_shape = [cfg.DATASET.DATA_DIM, height, width]
-    grt_shape = [1, height, width]
+    image_shape = [-1, cfg.DATASET.DATA_DIM, height, width]
+    grt_shape = [-1, 1, height, width]
     class_num = cfg.DATASET.NUM_CLASSES
 
     with fluid.program_guard(main_prog, start_prog):
@@ -165,25 +163,22 @@ def build_model(main_prog, start_prog, phase=ModelPhase.TRAIN, arch=None):
             # 在导出模型的时候，增加图像标准化预处理,减小预测部署时图像的处理流程
             # 预测部署时只须对输入图像增加batch_size维度即可
             if ModelPhase.is_predict(phase):
-                origin_image = fluid.layers.data(
+                origin_image = fluid.data(
                     name='image',
                     shape=[-1, -1, -1, cfg.DATASET.DATA_DIM],
-                    dtype='float32',
-                    append_batch_size=False)
+                    dtype='float32')
                 image, valid_shape, origin_shape = export_preprocess(
                     origin_image)
 
             else:
-                image = fluid.layers.data(
+                image = fluid.data(
                     name='image', shape=image_shape, dtype='float32')
-            label = fluid.layers.data(
-                name='label', shape=grt_shape, dtype='int32')
-            mask = fluid.layers.data(
-                name='mask', shape=grt_shape, dtype='int32')
+            label = fluid.data(name='label', shape=grt_shape, dtype='int32')
+            mask = fluid.data(name='mask', shape=grt_shape, dtype='int32')
 
-            # use PyReader when doing traning and evaluation
+            # use DataLoader.from_generator when doing traning and evaluation
             if ModelPhase.is_train(phase) or ModelPhase.is_eval(phase):
-                py_reader = fluid.io.PyReader(
+                data_loader = fluid.io.DataLoader.from_generator(
                     feed_list=[image, label, mask],
                     capacity=cfg.DATALOADER.BUF_SIZE,
                     iterable=False,
@@ -217,7 +212,8 @@ def build_model(main_prog, start_prog, phase=ModelPhase.TRAIN, arch=None):
                 if "softmax_loss" in loss_type:
                     weight = cfg.SOLVER.CROSS_ENTROPY_WEIGHT
                     avg_loss_list.append(
-                        multi_softmax_with_loss(logits, label, mask, class_num, weight))
+                        multi_softmax_with_loss(logits, label, mask, class_num,
+                                                weight))
                     loss_valid = True
                     valid_loss.append("softmax_loss")
                 if "dice_loss" in loss_type:
@@ -290,12 +286,12 @@ def build_model(main_prog, start_prog, phase=ModelPhase.TRAIN, arch=None):
                 return pred, logit
 
             if ModelPhase.is_eval(phase):
-                return py_reader, avg_loss, pred, label, mask
+                return data_loader, avg_loss, pred, label, mask
 
             if ModelPhase.is_train(phase):
                 optimizer = solver.Solver(main_prog, start_prog)
                 decayed_lr = optimizer.optimise(avg_loss)
-                return py_reader, avg_loss, decayed_lr, pred, label, mask
+                return data_loader, avg_loss, decayed_lr, pred, label, mask
 
 
 def to_int(string, dest="I"):

slim/nas/train_nas.py

@@ -54,6 +54,7 @@ from paddleslim.analysis import flops
 from paddleslim.nas.sa_nas import SANAS
 from paddleslim.nas import search_space
 
+
 def parse_args():
     parser = argparse.ArgumentParser(description='PaddleSeg training')
     parser.add_argument(
@@ -269,21 +270,24 @@ def train(cfg):
 
     port = cfg.SLIM.NAS_PORT
     server_address = (cfg.SLIM.NAS_ADDRESS, port)
-    sa_nas = SANAS(config, server_addr=server_address, search_steps=cfg.SLIM.NAS_SEARCH_STEPS,
-                   is_server=cfg.SLIM.NAS_IS_SERVER)
+    sa_nas = SANAS(
+        config,
+        server_addr=server_address,
+        search_steps=cfg.SLIM.NAS_SEARCH_STEPS,
+        is_server=cfg.SLIM.NAS_IS_SERVER)
     for step in range(cfg.SLIM.NAS_SEARCH_STEPS):
         arch = sa_nas.next_archs()[0]
 
         start_prog = fluid.Program()
         train_prog = fluid.Program()
 
-        py_reader, avg_loss, lr, pred, grts, masks = build_model(
+        data_loader, avg_loss, lr, pred, grts, masks = build_model(
             train_prog, start_prog, arch=arch, phase=ModelPhase.TRAIN)
 
         cur_flops = flops(train_prog)
         print('current step:', step, 'flops:', cur_flops)
 
-        py_reader.decorate_sample_generator(
+        data_loader.set_sample_generator(
             data_generator, batch_size=batch_size_per_dev, drop_last=drop_last)
 
         exe = fluid.Executor(place)
@@ -297,7 +301,8 @@ def train(cfg):
         build_strategy = fluid.BuildStrategy()
 
         if cfg.NUM_TRAINERS > 1 and args.use_gpu:
-            dist_utils.prepare_for_multi_process(exe, build_strategy, train_prog)
+            dist_utils.prepare_for_multi_process(exe, build_strategy,
+                                                 train_prog)
             exec_strategy.num_threads = 1
 
         if cfg.TRAIN.SYNC_BATCH_NORM and args.use_gpu:
@@ -309,10 +314,11 @@ def train(cfg):
                 print_info(
                     "Sync BatchNorm strategy will not be effective if GPU device"
                     " count <= 1")
-        compiled_train_prog = fluid.CompiledProgram(train_prog).with_data_parallel(
-            loss_name=avg_loss.name,
-            exec_strategy=exec_strategy,
-            build_strategy=build_strategy)
+        compiled_train_prog = fluid.CompiledProgram(
+            train_prog).with_data_parallel(
+                loss_name=avg_loss.name,
+                exec_strategy=exec_strategy,
+                build_strategy=build_strategy)
 
         # Resume training
         begin_epoch = cfg.SOLVER.BEGIN_EPOCH
@@ -353,13 +359,14 @@ def train(cfg):
                 print_info(
                     "Parameter[{}] don't exist or shape does not match current network, skip"
                     " to load it.".format(var.name))
-            print_info("{}/{} pretrained parameters loaded successfully!".format(
-                len(load_vars),
-                len(load_vars) + len(load_fail_vars)))
+            print_info(
+                "{}/{} pretrained parameters loaded successfully!".format(
+                    len(load_vars),
+                    len(load_vars) + len(load_fail_vars)))
         else:
             print_info(
                 'Pretrained model dir {} not exists, training from scratch...'.
-                    format(cfg.TRAIN.PRETRAINED_MODEL_DIR))
+                format(cfg.TRAIN.PRETRAINED_MODEL_DIR))
 
         fetch_list = [avg_loss.name, lr.name]
 
@@ -374,8 +381,8 @@ def train(cfg):
         timer.start()
         if begin_epoch > cfg.SOLVER.NUM_EPOCHS:
             raise ValueError(
-                ("begin epoch[{}] is larger than cfg.SOLVER.NUM_EPOCHS[{}]").format(
-                    begin_epoch, cfg.SOLVER.NUM_EPOCHS))
+                ("begin epoch[{}] is larger than cfg.SOLVER.NUM_EPOCHS[{}]"
+                 ).format(begin_epoch, cfg.SOLVER.NUM_EPOCHS))
 
         if args.use_mpio:
             print_info("Use multiprocess reader")
@@ -384,7 +391,7 @@ def train(cfg):
 
         best_miou = 0.0
         for epoch in range(begin_epoch, cfg.SOLVER.NUM_EPOCHS + 1):
-            py_reader.start()
+            data_loader.start()
             while True:
                 try:
                     loss, lr = exe.run(
@@ -398,21 +405,22 @@ def train(cfg):
                         avg_loss /= args.log_steps
                         speed = args.log_steps / timer.elapsed_time()
                         print((
-                                  "epoch={} step={} lr={:.5f} loss={:.4f} step/sec={:.3f} | ETA {}"
-                              ).format(epoch, global_step, lr[0], avg_loss, speed,
-                                       calculate_eta(all_step - global_step, speed)))
+                            "epoch={} step={} lr={:.5f} loss={:.4f} step/sec={:.3f} | ETA {}"
+                        ).format(epoch, global_step, lr[0], avg_loss, speed,
+                                 calculate_eta(all_step - global_step, speed)))
 
                         sys.stdout.flush()
                         avg_loss = 0.0
                         timer.restart()
 
                 except fluid.core.EOFException:
-                    py_reader.reset()
+                    data_loader.reset()
                     break
                 except Exception as e:
                     print(e)
             if epoch > cfg.SLIM.NAS_START_EVAL_EPOCH:
-                ckpt_dir = save_checkpoint(exe, train_prog, '{}_tmp'.format(port))
+                ckpt_dir = save_checkpoint(exe, train_prog,
+                                           '{}_tmp'.format(port))
                 _, mean_iou, _, mean_acc = evaluate(
                     cfg=cfg,
                     arch=arch,
@@ -420,7 +428,8 @@ def train(cfg):
                     use_gpu=args.use_gpu,
                     use_mpio=args.use_mpio)
                 if best_miou < mean_iou:
-                    print('search step {}, epoch {} best iou {}'.format(step, epoch, mean_iou))
+                    print('search step {}, epoch {} best iou {}'.format(
+                        step, epoch, mean_iou))
                     best_miou = mean_iou
 
         sa_nas.reward(float(best_miou))

slim/prune/README.md

@@ -46,7 +46,7 @@ SLIM.PRUNE_RATIOS '[0.1,0.1,0.1]'
 
 ```shell
 CUDA_VISIBLE_DEVICES=0 
-python -u ./slim/prune/eval_prune.py --cfg configs/cityscape_fast_scnn.yaml --use_gpu --use_mpio \
+python -u ./slim/prune/eval_prune.py --cfg configs/cityscape_fast_scnn.yaml --use_gpu \
 TEST.TEST_MODEL your_trained_model \
 ```
 

slim/prune/eval_prune.py

@@ -45,6 +45,7 @@ from metrics import ConfusionMatrix
 
 from paddleslim.prune import load_model
 
+
 def parse_args():
     parser = argparse.ArgumentParser(description='PaddleSeg model evalution')
     parser.add_argument(
@@ -98,10 +99,10 @@ def evaluate(cfg, ckpt_dir=None, use_gpu=False, use_mpio=False, **kwargs):
         for b in data_gen:
             yield b[0], b[1], b[2]
 
-    py_reader, avg_loss, pred, grts, masks = build_model(
+    data_loader, avg_loss, pred, grts, masks = build_model(
         test_prog, startup_prog, phase=ModelPhase.EVAL)
 
-    py_reader.decorate_sample_generator(
+    data_loader.set_sample_generator(
         data_generator, drop_last=False, batch_size=cfg.BATCH_SIZE)
 
     # Get device environment
@@ -134,7 +135,7 @@ def evaluate(cfg, ckpt_dir=None, use_gpu=False, use_mpio=False, **kwargs):
     all_step = cfg.DATASET.TEST_TOTAL_IMAGES // cfg.BATCH_SIZE + 1
     timer = Timer()
     timer.start()
-    py_reader.start()
+    data_loader.start()
     while True:
         try:
             step += 1

slim/prune/train_prune.py

@@ -50,6 +50,7 @@ from utils import dist_utils
 from paddleslim.prune import Pruner, save_model
 from paddleslim.analysis import flops
 
+
 def parse_args():
     parser = argparse.ArgumentParser(description='PaddleSeg training')
     parser.add_argument(
@@ -181,10 +182,12 @@ def load_checkpoint(exe, program):
 
     return begin_epoch
 
+
 def print_info(*msg):
     if cfg.TRAINER_ID == 0:
         print(*msg)
 
+
 def train(cfg):
     startup_prog = fluid.Program()
     train_prog = fluid.Program()
@@ -236,9 +239,9 @@ def train(cfg):
     batch_size_per_dev = cfg.BATCH_SIZE // dev_count
     print_info("batch_size_per_dev: {}".format(batch_size_per_dev))
 
-    py_reader, avg_loss, lr, pred, grts, masks = build_model(
+    data_loader, avg_loss, lr, pred, grts, masks = build_model(
         train_prog, startup_prog, phase=ModelPhase.TRAIN)
-    py_reader.decorate_sample_generator(
+    data_loader.set_sample_generator(
         data_generator, batch_size=batch_size_per_dev, drop_last=drop_last)
 
     exe = fluid.Executor(place)
@@ -261,8 +264,9 @@ def train(cfg):
             print_info("Sync BatchNorm strategy is effective.")
             build_strategy.sync_batch_norm = True
         else:
-            print_info("Sync BatchNorm strategy will not be effective if GPU device"
-                  " count <= 1")
+            print_info(
+                "Sync BatchNorm strategy will not be effective if GPU device"
+                " count <= 1")
 
     pruned_params = cfg.SLIM.PRUNE_PARAMS.strip().split(',')
     pruned_ratios = cfg.SLIM.PRUNE_RATIOS
@@ -311,14 +315,16 @@ def train(cfg):
         for var in load_vars:
             print_info("Parameter[{}] loaded sucessfully!".format(var.name))
         for var in load_fail_vars:
-            print_info("Parameter[{}] don't exist or shape does not match current network, skip"
-                  " to load it.".format(var.name))
+            print_info(
+                "Parameter[{}] don't exist or shape does not match current network, skip"
+                " to load it.".format(var.name))
         print_info("{}/{} pretrained parameters loaded successfully!".format(
             len(load_vars),
             len(load_vars) + len(load_fail_vars)))
     else:
-        print_info('Pretrained model dir {} not exists, training from scratch...'.
-              format(cfg.TRAIN.PRETRAINED_MODEL_DIR))
+        print_info(
+            'Pretrained model dir {} not exists, training from scratch...'.
+            format(cfg.TRAIN.PRETRAINED_MODEL_DIR))
 
     fetch_list = [avg_loss.name, lr.name]
     if args.debug:
@@ -371,7 +377,7 @@ def train(cfg):
         print_info("Use multi-thread reader")
 
     for epoch in range(begin_epoch, cfg.SOLVER.NUM_EPOCHS + 1):
-        py_reader.start()
+        data_loader.start()
         while True:
             try:
                 if args.debug:
@@ -441,7 +447,7 @@ def train(cfg):
                         timer.restart()
 
             except fluid.core.EOFException:
-                py_reader.reset()
+                data_loader.reset()
                 break
             except Exception as e:
                 print(e)
@@ -477,6 +483,7 @@ def train(cfg):
     if cfg.TRAINER_ID == 0:
         save_prune_checkpoint(exe, train_prog, 'final')
 
+
 def main(args):
     if args.cfg_file is not None:
         cfg.update_from_file(args.cfg_file)

slim/quantization/eval_quant.py

@@ -105,10 +105,10 @@ def evaluate(cfg, ckpt_dir=None, use_gpu=False, use_mpio=False, **kwargs):
         for b in data_gen:
             yield b[0], b[1], b[2]
 
-    py_reader, avg_loss, pred, grts, masks = build_model(
+    data_loader, avg_loss, pred, grts, masks = build_model(
         test_prog, startup_prog, phase=ModelPhase.EVAL)
 
-    py_reader.decorate_sample_generator(
+    data_loader.set_sample_generator(
         data_generator, drop_last=False, batch_size=cfg.BATCH_SIZE)
 
     # Get device environment
@@ -152,7 +152,7 @@ def evaluate(cfg, ckpt_dir=None, use_gpu=False, use_mpio=False, **kwargs):
     all_step = cfg.DATASET.TEST_TOTAL_IMAGES // cfg.BATCH_SIZE + 1
     timer = Timer()
     timer.start()
-    py_reader.start()
+    data_loader.start()
     while True:
         try:
             step += 1

slim/quantization/train_quant.py

@@ -157,9 +157,9 @@ def train_quant(cfg):
     batch_size_per_dev = cfg.BATCH_SIZE // dev_count
     print_info("batch_size_per_dev: {}".format(batch_size_per_dev))
 
-    py_reader, avg_loss, lr, pred, grts, masks = build_model(
+    data_loader, avg_loss, lr, pred, grts, masks = build_model(
         train_prog, startup_prog, phase=ModelPhase.TRAIN)
-    py_reader.decorate_sample_generator(
+    data_loader.set_sample_generator(
         data_generator, batch_size=batch_size_per_dev, drop_last=drop_last)
 
     exe = fluid.Executor(place)
@@ -274,7 +274,7 @@ def train_quant(cfg):
         print_info("Use multi-thread reader")
 
     for epoch in range(begin_epoch, cfg.SOLVER.NUM_EPOCHS + 1):
-        py_reader.start()
+        data_loader.start()
         while True:
             try:
                 if args.debug:
@@ -326,7 +326,7 @@ def train_quant(cfg):
                         timer.restart()
 
             except fluid.core.EOFException:
-                py_reader.reset()
+                data_loader.reset()
                 break
             except Exception as e:
                 print(e)

turtorial/finetune_fast_scnn.md

@@ -114,6 +114,6 @@ python pdseg/eval.py --use_gpu --cfg ./configs/fast_scnn_pet.yaml
 | ICNet/bn |(1024, 2048) |8.76ms| 0.6831 |
 | Fast-SCNN/bn | (1024, 2048) |6.28ms| 0.6964 |
 
-上述测试环境为v100. 测试使用paddle的推理接口[zero_copy](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/advanced_usage/deploy/inference/python_infer_cn.html#id8)的方式，模型输出是类别，即argmax后的值。
+上述测试环境为v100. 测试使用paddle的推理接口[zero_copy](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/advanced_guide/inference_deployment/inference/python_infer_cn.html#id8)的方式，模型输出是类别，即argmax后的值。