-
Recently, @GaofengCheng has been doing some interesting experiments with dropout and BLSTMs, and getting nice improvements. He was using a dropout schedule in which you start with zero dropout, ramp …
-
I am trying to implement a LSTM based speech recognizer. So far I could set up bidirectional LSTM (i think it is working as a bidirectional LSTM) by following the example in Merge layer. Now I want to…
-
我有一个网络。当我截取其中某一段子网络时，可以正常用capi调用并predict。
当我把完整的网络取出来时，infer时报错。
```c
what(): Attribute 'sub_block' is required! at [Paddle/paddle/fluid/framework/attribute.h:241]
PaddlePaddle Call Stacks:
…
-
Problem:
(1) tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimensions must be equal, but are 1488 and 992 for 'model/blstm/stack_bidirectional_rnn/cell_0/bidirectional_rnn/fw/fw/whil…
-
Hello @zackhy
when I run following command
python test.py --test_data_file=./data/data.csv --run_dir=./runs/1111111111 --clf=clf-10000
I got this error->unrecognizedflagerror:Unknown command line …
-
```python
place = fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
program, feed_target_names, fetch_targets = fluid.io.load_inference_model('fluid_model', ex…
-
Hi community,
I add a new ComputationNode named BiVfsmnNode to implement FSMN (Feedforward Sequential Memory Network)[1], but now I can't get results that I expect by this new BiVfsmnNode. Maybe I …
-
I've downloaded last Merlin's commits and now have a problem with duration model training. When I set architecture like this:
hidden_layer_size : [1024, 1024, 1024, 1024, 384]
hidden_layer_type : …
-
i understand that much of the new Tesseract 4.0 is using a customized implementation of Ocropus, relying basically on the new LSTM recognition engine.
But the main problem is that most of the decis…
ghost updated
6 years ago
-
Multilingual documents are common in the computer age of today. Plethora of these
documents exist in the form of translations, books, operational manuals, etc. The
abundance of these multilingual do…