fix demo/prune log (PaddlePaddle#599)

* fix prune doc

* fix prune demo batchsize

* fix lr (PaddlePaddle#593)

* fix lr schedule in prune demo (PaddlePaddle#595)

* fix prune demo batchsize

* fix lr shcedule in prune demo
;

Co-authored-by: wanghaoshuang <wanghaoshuang@baidu.com>

* remove softmax from demo/models (PaddlePaddle#596)

* fix prune demo batchsize

* fix lr shcedule in prune demo
;

* remove softmax from demo/models

Co-authored-by: wanghaoshuang <wanghaoshuang@baidu.com>

* fix prune demo log

Co-authored-by: wanghaoshuang <wanghaoshuang@baidu.com>

demo/prune/train.py

@@ -239,7 +239,7 @@ def train(epoch, program):
 
     for i in range(args.num_epochs):
         train(i, train_program)
-        if i % args.test_period == 0:
+        if (i + 1) % args.test_period == 0:
             test(i, pruned_val_program)
             save_model(exe, pruned_val_program,
                        os.path.join(args.model_path, str(i)))