Merged -- no conflict

doc/hpcs2011_tutorial/logreg_example.py

@@ -6,7 +6,7 @@ rng = numpy.random
 N = 400
 feats = 784
 D = (rng.randn(N, feats).astype(theano.config.floatX), rng.randint(size=N,low=0, high=2).astype(theano.config.floatX))
-training_steps = 10
+training_steps = 10000
 
 # Declare Theano symbolic variables
 x = T.matrix("x")
@@ -15,8 +15,8 @@ w = theano.shared(rng.randn(feats).astype(theano.config.floatX), name="w")
 b = theano.shared(numpy.asarray(0., dtype=theano.config.floatX), name="b")
 x.tag.test_value = D[0]
 y.tag.test_value = D[1]
-print "Initial model:"
-print w.get_value(), b.get_value()
+#print "Initial model:"
+#print w.get_value(), b.get_value()
 
 
 # Construct Theano expression graph
@@ -30,15 +30,25 @@ gw,gb = T.grad(cost, [w,b])
 train = theano.function(
             inputs=[x,y],
             outputs=[prediction, xent],
-            updates={w:w-0.1*gw, b:b-0.1*gb},
+            updates={w:w-0.01*gw, b:b-0.01*gb},
             name = "train")
 predict = theano.function(inputs=[x], outputs=prediction,
             name = "predict")
 
+if any( [x.op.__class__.__name__=='Gemv' for x in train.maker.env.toposort()]):
+    print 'Used the cpu'
+elif any( [x.op.__class__.__name__=='GpuGemm' for x in train.maker.env.toposort()]):
+    print 'Used the gpu'
+else:
+    print 'ERROR, not able to tell if theano used the cpu or the gpu'
+    print train.maker.env.toposort()
+
+
+
 for i in range(training_steps):
     pred, err = train(D[0], D[1])
-print "Final model:"
-print w.get_value(), b.get_value()
+#print "Final model:"
+#print w.get_value(), b.get_value()
 
 print "target values for D"
 print D[1]

doc/hpcs2011_tutorial/pycuda_simple.py

+import pycuda.autoinit
+import pycuda.driver as drv
+import numpy
+
+from pycuda.compiler import SourceModule
+mod = SourceModule("""
+__global__ void multiply_them(float *dest, float *a, float *b)
+{
+  const int i = threadIdx.x;
+  dest[i] = a[i] * b[i];
+}
+""")
+
+multiply_them = mod.get_function("multiply_them")
+
+a = numpy.random.randn(400).astype(numpy.float32)
+b = numpy.random.randn(400).astype(numpy.float32)
+
+dest = numpy.zeros_like(a)
+multiply_them(
+        drv.Out(dest), drv.In(a), drv.In(b),
+        block=(400,1,1), grid=(1,1))
+
+assert numpy.allclose(dest, a*b)
+print dest

doc/hpcs2011_tutorial/scan_poly.py

+import numpy
+
+import theano
+import theano.tensor as T
+
+coefficients = theano.tensor.vector("coefficients")
+x = T.scalar("x"); max_coefficients_supported = 10000
+
+# Generate the components of the polynomial
+full_range=theano.tensor.arange(max_coefficients_supported)
+components, updates = theano.scan(fn=lambda coeff, power, free_var:
+                                     coeff * (free_var ** power),
+                                  outputs_info=None,
+                                  sequences=[coefficients, full_range],
+                                  non_sequences=x)
+polynomial = components.sum()
+calculate_polynomial = theano.function(inputs=[coefficients, x],
+                                       outputs=polynomial)
+
+test_coeff = numpy.asarray([1, 0, 2], dtype=numpy.float32)
+print calculate_polynomial(test_coeff, 3)
+# 19.0

doc/hpcs2011_tutorial/scan_pow.py

+import theano
+import theano.tensor as T
+
+k = T.iscalar("k"); A = T.vector("A")
+
+def inner_fct(prior_result, A): return prior_result * A
+# Symbolic description of the result
+result, updates = theano.scan(fn=inner_fct,
+                              outputs_info=T.ones_like(A),
+                              non_sequences=A, n_steps=k)
+
+# Scan has provided us with A**1 through A**k.  Keep only the last
+# value. Scan notices this and does not waste memory saving them.
+final_result = result[-1]
+
+power = theano.function(inputs=[A,k], outputs=final_result,
+                        updates=updates)
+
+print power(range(10),2)

doc/index.txt

@@ -21,7 +21,9 @@ since 2007.  But it is also approachable enough to be used in the classroom
     :scale: 75%
     :align: left
 
-**NEW!** You can watch a quick (20 minute) introduction to Theano given as a talk at `SciPy 2010 <http://conference.scipy.org/scipy2010/>`_ via streaming (or downloaded) video:
+**NEW!** `HPCS 2011 Tutorial <http://www.iro.umontreal.ca/~lisa/pointeurs/tutorial_hpcs2011_fixed.pdf>`_. I included a few fix discovered while doing the Tutorial.
+
+You can watch a quick (20 minute) introduction to Theano given as a talk at `SciPy 2010 <http://conference.scipy.org/scipy2010/>`_ via streaming (or downloaded) video:
 
   `Transparent GPU Computing With Theano`_.
   James Bergstra, SciPy 2010, June 30, 2010.