[Test-driven] Recognize Digit: update mnist test cases with the new API syntax. (#10507)

* Update the mnist test cases with the new API syntax.

* Turn on the tests for MNIST

* delete the test files got merged accidently.

* Enable the mnist tests. ready for test driven development.

* Comment out the infer first
This is to confirm that the Trainer.train is working

* Add CMake file to include the tests

* Make the train program only return avg_cost for now

* Update the tests to use the latest syntax

python/paddle/fluid/tests/book/CMakeLists.txt

@@ -5,3 +5,5 @@ string(REPLACE ".py" "" TEST_OPS "${TEST_OPS}")
 foreach(src ${TEST_OPS})
     py_test(${src} SRCS ${src}.py)
 endforeach()
+
+add_subdirectory(high-level-api)

python/paddle/fluid/tests/book/high-level-api/CMakeLists.txt

@@ -0,0 +1,9 @@
+file(GLOB TEST_OPS RELATIVE "${CMAKE_CURRENT_SOURCE_DIR}" "test_*.py")
+string(REPLACE ".py" "" TEST_OPS "${TEST_OPS}")
+
+# default test
+foreach(src ${TEST_OPS})
+    py_test(${src} SRCS ${src}.py)
+endforeach()
+
+add_subdirectory(recognize_digits)

python/paddle/fluid/tests/book/high-level-api/recognize_digits/CMakeLists.txt

@@ -0,0 +1,7 @@
+file(GLOB TEST_OPS RELATIVE "${CMAKE_CURRENT_SOURCE_DIR}" "test_*.py")
+string(REPLACE ".py" "" TEST_OPS "${TEST_OPS}")
+
+# default test
+foreach(src ${TEST_OPS})
+    py_test(${src} SRCS ${src}.py)
+endforeach()

python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_conv.py

@@ -21,7 +21,6 @@ import unittest
 import math
 import sys
 import os
-import paddle.v2.dataset as dataset
 
 BATCH_SIZE = 64
 
@@ -54,47 +53,65 @@ def train_program():
     predict = inference_program()
     cost = fluid.layers.cross_entropy(input=predict, label=label)
     avg_cost = fluid.layers.mean(cost)
-    acc = fluid.layers.accuracy(input=predict, label=label)
-    return avg_cost, acc
+    # acc = fluid.layers.accuracy(input=predict, label=label)
+    # return avg_cost, acc
+    return avg_cost
 
 
 def train(use_cuda, save_dirname):
     place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
-
     optimizer = fluid.optimizer.Adam(learning_rate=0.001)
-    trainer = fluid.Trainer(train_program, place=place, optimizer=optimizer)
+
+    trainer = fluid.Trainer(
+        train_func=train_program,
+        infer_func=inference_program,
+        place=place,
+        optimizer=optimizer)
 
     def event_handler(event):
-        if isinstance(event, fluid.EndIteration):
-            avg_cost, acc = event.values
-            print("avg_cost: %s" % avg_cost)
-            print("acc     : %s" % acc)
-
-            if (event.batch_id + 1) % 10 == 0:
-                test_metrics = trainer.test(reader=dataset.mnist.test())
-                avg_cost_set = test_metrics[0]
-                acc_set = test_metrics[1]
-
-                # get test acc and loss
-                acc = numpy.array(acc_set).mean()
-                avg_cost = numpy.array(avg_cost_set).mean()
-                if float(acc) > 0.2:  # Smaller value to increase CI speed
-                    trainer.save_params(save_dirname)
-                else:
-                    print('BatchID {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
-                        event.batch_id + 1, float(avg_cost), float(acc)))
-                    if math.isnan(float(avg_cost)):
-                        sys.exit("got NaN loss, training failed.")
+        if isinstance(event, fluid.EndEpochEvent):
+            # if (event.epoch + 1) % 10 == 0:
+            # trainer.save_params(save_dirname)
+            trainer.save_inference_model(save_dirname)
+
+            # TODO: Uncomment this part once we are sure that .train is working
+            # test_reader = paddle.batch(
+            #     paddle.dataset.mnist.test(), batch_size=BATCH_SIZE)
+            # test_metrics = trainer.test(reader=test_reader)
+            # avg_cost_set = test_metrics[0]
+            # acc_set = test_metrics[1]
+            #
+            # # get test acc and loss
+            # acc = numpy.array(acc_set).mean()
+            # avg_cost = numpy.array(avg_cost_set).mean()
+            #
+            # print("avg_cost: %s" % avg_cost)
+            # print("acc     : %s" % acc)
+            #
+            # if float(acc) > 0.2:  # Smaller value to increase CI speed
+            #     trainer.save_params(save_dirname)
+            # else:
+            #     print('BatchID {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
+            #         event.epoch + 1, float(avg_cost), float(acc)))
+            #     if math.isnan(float(avg_cost)):
+            #         sys.exit("got NaN loss, training failed.")
+
+    train_reader = paddle.batch(
+        paddle.reader.shuffle(
+            paddle.dataset.mnist.train(), buf_size=500),
+        batch_size=BATCH_SIZE)
 
     trainer.train(
-        reader=dataset.mnist.train(), num_pass=100, event_handler=event_handler)
+        num_epochs=1,
+        event_handler=event_handler,
+        reader=train_reader,
+        feed_order=['img', 'label'])
 
 
 def infer(use_cuda, save_dirname=None):
     place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
 
-    inferencer = fluid.Inferencer(
-        inference_program, param_path=save_dirname, place=place)
+    inferencer = fluid.Inferencer(param_path=save_dirname, place=place)
 
     batch_size = 1
     tensor_img = numpy.random.uniform(-1.0, 1.0,
@@ -114,5 +131,5 @@ def main(use_cuda):
 
 
 if __name__ == '__main__':
-    for use_cuda in (False, True):
-        main(use_cuda=use_cuda)
+    # for use_cuda in (False, True):
+    main(use_cuda=False)

python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_mlp.py

@@ -21,7 +21,6 @@ import unittest
 import math
 import sys
 import os
-import paddle.v2.dataset as dataset
 
 BATCH_SIZE = 64
 
@@ -41,47 +40,64 @@ def train_program():
     predict = inference_program()
     cost = fluid.layers.cross_entropy(input=predict, label=label)
     avg_cost = fluid.layers.mean(cost)
-    acc = fluid.layers.accuracy(input=predict, label=label)
-    return avg_cost, acc
+    # acc = fluid.layers.accuracy(input=predict, label=label)
+    # return avg_cost, acc
+    return avg_cost
 
 
 def train(use_cuda, save_dirname):
     place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
-
     optimizer = fluid.optimizer.Adam(learning_rate=0.001)
-    trainer = fluid.Trainer(train_program, place=place, optimizer=optimizer)
+
+    trainer = fluid.Trainer(
+        train_func=train_program,
+        infer_func=inference_program,
+        place=place,
+        optimizer=optimizer)
 
     def event_handler(event):
-        if isinstance(event, fluid.EndIteration):
-            avg_cost, acc = event.values
-            print("avg_cost: %s" % avg_cost)
-            print("acc     : %s" % acc)
-
-            if (event.batch_id + 1) % 10 == 0:
-                test_metrics = trainer.test(reader=dataset.mnist.test())
-                avg_cost_set = test_metrics[0]
-                acc_set = test_metrics[1]
-
-                # get test acc and loss
-                acc = numpy.array(acc_set).mean()
-                avg_cost = numpy.array(avg_cost_set).mean()
-                if float(acc) > 0.2:  # Smaller value to increase CI speed
-                    trainer.save_params(save_dirname)
-                else:
-                    print('BatchID {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
-                        event.batch_id + 1, float(avg_cost), float(acc)))
-                    if math.isnan(float(avg_cost)):
-                        sys.exit("got NaN loss, training failed.")
+        if isinstance(event, fluid.EndEpochEvent):
+            # if (event.epoch + 1) % 10 == 0:
+            trainer.save_inference_model(save_dirname)
+
+            # TODO: Uncomment this part once we are sure that .train is working
+            # test_reader = paddle.batch(
+            #     paddle.dataset.mnist.test(), batch_size=BATCH_SIZE)
+            # test_metrics = trainer.test(reader=test_reader)
+            # avg_cost_set = test_metrics[0]
+            # acc_set = test_metrics[1]
+            #
+            # # get test acc and loss
+            # acc = numpy.array(acc_set).mean()
+            # avg_cost = numpy.array(avg_cost_set).mean()
+            #
+            # print("avg_cost: %s" % avg_cost)
+            # print("acc     : %s" % acc)
+            #
+            # if float(acc) > 0.2:  # Smaller value to increase CI speed
+            #     trainer.save_params(save_dirname)
+            # else:
+            #     print('BatchID {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
+            #         event.epoch + 1, float(avg_cost), float(acc)))
+            #     if math.isnan(float(avg_cost)):
+            #         sys.exit("got NaN loss, training failed.")
+
+    train_reader = paddle.batch(
+        paddle.reader.shuffle(
+            paddle.dataset.mnist.train(), buf_size=500),
+        batch_size=BATCH_SIZE)
 
     trainer.train(
-        reader=dataset.mnist.train(), num_pass=100, event_handler=event_handler)
+        num_epochs=1,
+        event_handler=event_handler,
+        reader=train_reader,
+        feed_order=['img', 'label'])
 
 
 def infer(use_cuda, save_dirname=None):
     place = fluid.CUDAPlace(0) if use_cuda else fluid.CPUPlace()
 
-    inferencer = fluid.Inferencer(
-        inference_program, param_path=save_dirname, place=place)
+    inferencer = fluid.Inferencer(param_path=save_dirname, place=place)
 
     batch_size = 1
     tensor_img = numpy.random.uniform(-1.0, 1.0,
@@ -101,5 +117,5 @@ def main(use_cuda):
 
 
 if __name__ == '__main__':
-    for use_cuda in (False, True):
-        main(use_cuda=use_cuda)
+    # for use_cuda in (False, True):
+    main(use_cuda=False)