Merge branch 'master' of https://github.com/ECP-Candle/benchmarks

Author: brettinanl

Pilot2/P2B1/INSTALL.md

@@ -1,5 +1,8 @@
 ## Installing Keras framework
 
+Here is an alternate set of directions for using the Spack tool
+(spack.io) to install Keras and associated tools.
+
 ### Using spack
 
 ```
@@ -20,7 +23,6 @@ spack install py-matplotlib +image
 
 ```
 # Activate all of these tools in the spack python environment
-spack activate ipython
 spack activate py-ipython
 spack activate py-keras
 spack activate py-matplotlib

Pilot2/P2B2/INSTALL.md

@@ -1,5 +1,8 @@
 ## Installing Keras framework
 
+Here is an alternate set of directions for using the Spack tool
+(spack.io) to install Keras and associated tools.
+
 ### Using spack
 
 ```
@@ -20,7 +23,6 @@ spack install py-matplotlib +image
 
 ```
 # Activate all of these tools in the spack python environment
-spack activate ipython
 spack activate py-ipython
 spack activate py-keras
 spack activate py-matplotlib
@@ -31,5 +33,5 @@ module load py-ipython-5.1.0-gcc-4.9.3
 
 # Lauch ipython and then run the example
 ipython
-[1]: run p2b1_baseline_keras1.py
+[1]: run p2b2_baseline_keras1.py
 ```

Pilot2/README.md

@@ -6,7 +6,9 @@
 
 #### Description of the Data
 * Data source: MD Simulation output as PDB files (coarse-grained bead simulation)
-* Input dimensions: ~1.26e6 per time step (6000 lipids x 30 beads per lipid x (position + velocity + type))
+* Input dimensions:
+  * Long term target: ~1.26e6 per time step (6000 lipids x 30 beads per lipid x (position + velocity + type))
+  * Current: ~288e3 per time step (6000 lipids x 12 beads per lipid x (position + type))
 * Output dimensions: 500
 * Latent representation dimension:
 * Sample size: O(10^6) for simulation requiring O(10^8) time steps
@@ -17,8 +19,6 @@
 * 3-component-system (DPPC-DOPC-CHOL)
 * af-restraints-290k
 
-#### p2_small_baseline.npy
-
 #### 3K lipids, 10 microseconds simulation, ~3000 frames:
 * Disordered - 3k_run10_10us.35fs-DPPC.10-DOPC.70-CHOL.20.dir
 * Ordered - 3k_run32_10us.35fs-DPPC.50-DOPC.10-CHOL.40.dir
@@ -34,6 +34,9 @@
 * ```--data-set=3k_Disordered```
 * ```--data-set=3k_Ordered```
 * ```--data-set=3k_Ordered_and_gel```
+* ```--data-set=6k_Disordered```
+* ```--data-set=6k_Ordered```
+* ```--data-set=6k_Ordered_and_gel```
 
 ### Data Set Release Notice
 

Pilot3/P3B2/README.md

@@ -1,4 +1,4 @@
-## P3B1: RNN-LSTM: A Generative Model for Clinical Path Reports
+## P3B2: RNN-LSTM: A Generative Model for Clinical Path Reports
 **Overview**:Given a sample corpus of biomedical text such as clinical reports, build a deep learning network that can automatically generate synthetic text documents with valid clinical context.
 
 **Relationship to core problem**:Labeled data is quite challenging to come by, specifically for patient data, since manual annotations are time consuming; hence, a core capability we intend to build is a “gold-standard” annotated data that is generated by deep learning networks to tune our deep text comprehension applications.

README.md

@@ -15,7 +15,7 @@ Pilot3 (P3) benchmarks are formed out of problems and data at the population lev
 Each of the problems (P1,P2,P3) informed the implementation of specific benchmarks, so P1B3 would be benchmark three of problem 1.
 At this point, we will refer to a benchmark by it's problem area and benchmark number. So it's natural to talk of the P1B1 benchmark. Inside each benchmark directory, there exists a readme file that contains an overview of the benchmark, a description of the data and expected outcomes along with instructions for running the benchmark code.
 
-Over time, we will be adding implementations that make use of different tensor frameworks. The primary (baseline) benchmarks are implemented using tensorflow, and are named with '_baseline' in the name, for example p2b1_baseline.py. 
+Over time, we will be adding implementations that make use of different tensor frameworks. The primary (baseline) benchmarks are implemented using keras, and are named with '_baseline' in the name, for example p3b1_baseline_keras2.py. 
 
 Implementations that use alternative tensor frameworks, such as mxnet or neon, will have the name of the framework in the name. Examples can be seen in the P1B3 benchmark contribs/ directory, for example:
         p1b3_mxnet.py