Some updates on readers

1. Shrink DoubleBufferReader's buffer size to 3.
2. Add BatchReader an option to discard leftover instances.
3. Fix a MultiPassReader bug on pass count.

paddle/fluid/operators/reader/create_batch_reader_op.cc

@@ -20,8 +20,11 @@ namespace reader {
 
 class BatchReader : public framework::DecoratedReader {
  public:
-  BatchReader(const std::shared_ptr<ReaderBase>& reader, int batch_size)
-      : DecoratedReader(reader), batch_size_(batch_size) {
+  BatchReader(const std::shared_ptr<ReaderBase>& reader, int batch_size,
+              bool discard_leftover)
+      : DecoratedReader(reader),
+        batch_size_(batch_size),
+        discard_leftover_(discard_leftover) {
     buffer_.reserve(batch_size_);
     Start();
   }
@@ -30,6 +33,7 @@ class BatchReader : public framework::DecoratedReader {
 
  private:
   int batch_size_;
+  bool discard_leftover_;
   std::vector<std::vector<framework::LoDTensor>> buffer_;
 };
 
@@ -47,8 +51,8 @@ class CreateBatchReaderOp : public framework::OperatorBase {
     }
     const auto& underlying_reader = scope.FindVar(Input("UnderlyingReader"))
                                         ->Get<framework::ReaderHolder>();
-    out->Reset(
-        new BatchReader(underlying_reader.Get(), Attr<int>("batch_size")));
+    out->Reset(new BatchReader(underlying_reader.Get(), Attr<int>("batch_size"),
+                               Attr<bool>("discard_leftover")));
   }
 };
 
@@ -58,6 +62,10 @@ class CreateBatchReaderOpMaker : public DecoratedReaderMakerBase {
     AddAttr<int>("batch_size",
                  "How many instances the batch reader yields each time.")
         .GreaterThan(0);
+    AddAttr<bool>("discard_leftover",
+                  "If true, the leftover instances that are not enough for a "
+                  "new batch will be discarded.")
+        .SetDefault(true);
     AddComment(R"DOC(
       CreateBatchReader Operator
 
@@ -78,6 +86,9 @@ void BatchReader::ReadNextImpl(std::vector<framework::LoDTensor>* out) {
       break;
     }
   }
+  if (discard_leftover_ && buffer_.size() < batch_size_) {
+    buffer_.clear();
+  }
   // Concat instances
   out->clear();
   if (buffer_.empty()) {

paddle/fluid/operators/reader/create_double_buffer_reader_op.cc

@@ -23,13 +23,13 @@ namespace reader {
 
 // 'Double buffer' means we shall maintain two batches of input data at the same
 // time. So the kCacheSize shoul be at least 2.
-static constexpr size_t kCacheSize = 5;
+static constexpr size_t kCacheSize = 3;
 // There will be two bacthes out of the channel during training:
 // 1. the one waiting to be sent to the channel
 // 2. the one just be received from the channel, which is also being used by
 // subsequent operators.
 // So the channel size should be kChacheSize - 2
-static constexpr size_t kChannelSize = 3;  // kCacheSize - 2
+static constexpr size_t kChannelSize = 1;  // kCacheSize - 2
 
 class DoubleBufferReader : public framework::DecoratedReader {
  public:

paddle/fluid/operators/reader/create_multi_pass_reader_op.cc

@@ -28,13 +28,11 @@ class MultiPassReader : public framework::DecoratedReader {
 
   void ReadNextImpl(std::vector<framework::LoDTensor>* out) override {
     reader_->ReadNext(out);
-    if (out->empty()) {
-      ++pass_count_;
-      if (pass_count_ < pass_num_) {
+    if (out->empty() && pass_count_ < pass_num_ - 1) {
       reader_->Shutdown();
       reader_->Start();
       reader_->ReadNext(out);
-      }
+      ++pass_count_;
     }
   }