reformat the table

attractivechaos · Mar 4, 2017 · b5d6001 · b5d6001
1 parent bbcf905
commit b5d6001
Show file tree

Hide file tree

Showing 2 changed files with 16 additions and 17 deletions.
diff --git a/README.md b/README.md
@@ -170,40 +170,39 @@ int main(void)
   with Conda, too. Keras-1.2.2 and Tensorflow-1.0.0 were installed with pip. On
   both machines, Tiny-DNN was acquired from github on March 1st, 2017.
 
-* MNIST-mlp implements a simple MLP with one layer of 64 hidden neurons.
-  MNIST-cnn applies two convolutional layers with 32 3-by-3 kernels and ReLU
+* mnist-mlp implements a simple MLP with one layer of 64 hidden neurons.
+  mnist-cnn applies two convolutional layers with 32 3-by-3 kernels and ReLU
   activation, followed by 2-by-2 max pooling and one 128-neuron dense layer.
-  Mul100-rnn uses two GRUs of size 160. Both input and output are 2-D
+  mul100-rnn uses two GRUs of size 160. Both input and output are 2-D
   binary arrays of shape (14,2) -- 28 GRU operations for each of the 30000
   training samples.
 
-|Task       |Framework    |Machine|Device   |Real time|CPU time|Command line |
+|Task       |Framework    |Machine|Device   |Real     |CPU     |Command line |
 |:----------|:------------|:------|--------:|--------:|-------:|:------------|
-|MNIST-mlp  |KANN+SSE     |Linux  |1 CPU    | 31.3s   | 31.2s  |mlp -m20 -v0|
+|mnist-mlp  |KANN+SSE     |Linux  |1 CPU    | 31.3s   | 31.2s  |mlp -m20 -v0|
 |           |             |Mac    |1 CPU    | 27.1s   | 27.1s  ||
 |           |KANN+OpenBLAS|Linux  |1 CPU    | 18.8s   | 18.8s  ||
-|           |Theano+Keras |Linux  |1 CPU    | 33.7s   | 33.2s  |OMP_NUM_THREADS=1 keras/mlp.py -m20 -v0|
-|           |             |       |4 CPUs   | 32.0s   |121.3s  |OMP_NUM_THREADS=4 keras/mlp.py -m20 -v0|
+|           |Theano+Keras |Linux  |1 CPU    | 33.7s   | 33.2s  |keras/mlp.py -m20 -v0|
+|           |             |       |4 CPUs   | 32.0s   |121.3s  ||
 |           |             |Mac    |1 CPU    | 37.2s   | 35.2s  ||
 |           |             |       |2 CPUs   | 32.9s   | 62.0s  ||
-|           |TF+Keras     |Mac    |1-2 CPUs | 64.2s   |102.0s  |keras/mlp.py -m20|
 |           |TensorFlow   |Mac    |1 CPU    | 33.4s   | 33.4s  |tensorflow/mlp.py -m20|
 |           |             |       |2 CPUs   | 29.2s   | 50.6s  |tensorflow/mlp.py -m20 -t2|
 |           |Tiny-dnn     |Linux  |1 CPU    | 2m19s   | 2m18s  |tiny-dnn/mlp -m20|
 |           |Tiny-dnn+AVX |Linux  |1 CPU    | 1m34s   | 1m33s  ||
 |           |             |Mac    |1 CPU    | 2m17s   | 2m16s  ||
-|MNIST-cnn  |KANN+SSE     |Linux  |1 CPU    |57m57s   |57m53s  |mnist-cnn -v0 -m15|
+|mnist-cnn  |KANN+SSE     |Linux  |1 CPU    |57m57s   |57m53s  |mnist-cnn -v0 -m15|
 |           |             |       |4 CPUs   |19m09s   |68m17s  |mnist-cnn -v0 -t4 -m15|
-|           |Theano+Keras |Linux  |1 CPU    |37m12s   |37m09s  |OMP_NUM_THREADS=1 keras/mlp.py -Cm15 -v0|
-|           |             |       |4 CPUs   |24m24s   |97m22s  |OMP_NUM_THREADS=4 keras/mlp.py -Cm15 -v0|
+|           |Theano+Keras |Linux  |1 CPU    |37m12s   |37m09s  |keras/mlp.py -Cm15 -v0|
+|           |             |       |4 CPUs   |24m24s   |97m22s  ||
 |           |             |       |1 GPU    |2m57s    |        |keras/mlp.py -Cm15 -v0|
 |           |Tiny-dnn+AVX |Linux  |1 CPU    |300m40s  |300m23s |tiny-dnn/mlp -Cm15|
-|Mul100-rnn |KANN+SSE     |Linux  |1 CPU    |40m05s   |40m02s  |rnn-bit -l2 -n160 -m25 -Nd0|
+|mul100-rnn |KANN+SSE     |Linux  |1 CPU    |40m05s   |40m02s  |rnn-bit -l2 -n160 -m25 -Nd0|
 |           |             |       |4 CPUs   |12m13s   |44m40s  |rnn-bit -l2 -n160 -t4 -m25 -Nd0|
 |           |KANN+OpenBLAS|Linux  |1 CPU    |22m58s   |22m56s  |rnn-bit -l2 -n160 -m25 -Nd0|
 |           |             |       |4 CPUs   |8m18s    |31m26s  |rnn-bit -l2 -n160 -t4 -m25 -Nd0|
-|           |Theano+Keras |Linux  |1 CPU    |27m30s   |27m27s  |OMP_NUM_THREADS=1 keras/rnn-bit.py -l2 -n160 -m25|
-|           |             |       |4 CPUs   |19m52s   |77m45s  |OMP_NUM_THREADS=4 keras/rnn-bit.py -l2 -n160 -m25|
+|           |Theano+Keras |Linux  |1 CPU    |27m30s   |27m27s  |keras/rnn-bit.py -l2 -n160 -m25|
+|           |             |       |4 CPUs   |19m52s   |77m45s  ||
 
 * In the single thread mode, Theano is about 50% faster than KANN probably due
   to efficient matrix multiplication (aka. `sgemm`) implemented in MKL. As is

diff --git a/examples/README.md b/examples/README.md
@@ -61,16 +61,16 @@ like the python version.
 ### Character-level text generation with RNN
 
 Implemented in [textgen.c](textgen.c). This is not a standard model in that the
-initial hidden states depend on the previous output. It tends to memorize short
-text better.
+initial hidden states depend on the previous output. It tends to memorize text
+better.
 ```sh
 ./textgen -o acc.kan accelerando.txt
 ./textgen -i acc.kan
 ```
 You can also found a bigger model in kann-models. It can generate meaningful
 text even with near-to-zero temperature.
 ```sh
-./textgen -i acc-l3-n256r.kan -T 1e-6
+./textgen -i kann-models/acc-l3-n256r.kan -T 1e-6
 ```
 
 [data]: https://github.com/attractivechaos/kann