ift6266: baseline/mlp/mlp_nist.py comparison

comparison baseline/mlp/mlp_nist.py @ 404:1509b9bba4cc

added digit/char error

author	xaviermuller
date	Wed, 28 Apr 2010 11:45:14 -0400
parents	60a4432b8071
children	195f95c3d461

comparison

equal deleted inserted replaced

-:a11692910312
+:1509b9bba4cc
 def mlp_get_nist_error(model_name='/u/mullerx/ift6266h10_sandbox_db/xvm_final_lr1_p073/8/best_model.npy.npz',
 data_set=0):
-# allocate symbolic variables for the data
-x = T.fmatrix()  # the data is presented as rasterized images
-y = T.lvector()  # the labels are presented as 1D vector of
-# [long int] labels
 # load the data set and create an mlp based on the dimensions of the model
 model=numpy.load(model_name)
 W1=model['W1']
 W2=model['W2']
 b1=model['b1']
 b2=model['b2']
-nb_hidden=b1.shape[0]
-input_dim=W1.shape[0]
+total_error_count=0.0
-nb_targets=b2.shape[0]
+total_exemple_count=0.0
-learning_rate=0.1
+nb_error_count=0.0
+nb_exemple_count=0.0
+char_error_count=0.0
+char_exemple_count=0.0
+min_error_count=0.0
+min_exemple_count=0.0
+maj_error_count=0.0
+maj_exemple_count=0.0
 if data_set==0:
 dataset=datasets.nist_all()
 elif data_set==1:
 dataset=datasets.nist_P07()
-classifier = MLP( input=x,\
-n_in=input_dim,\
-n_hidden=nb_hidden,\
-n_out=nb_targets,
-learning_rate=learning_rate)
-#overwrite weights with weigths from model
-classifier.W1.value=W1
-classifier.W2.value=W2
-classifier.b1.value=b1
-classifier.b2.value=b2
-cost = classifier.negative_log_likelihood(y) \
-+ 0.0 * classifier.L1 \
-+ 0.0 * classifier.L2_sqr
-# compiling a theano function that computes the mistakes that are made by
-# the model on a minibatch
-test_model = theano.function([x,y], classifier.errors(y))
 #get the test error
 #use a batch size of 1 so we can get the sub-class error
 #without messing with matrices (will be upgraded later)
 test_score=0
 temp=0
-for xt,yt in dataset.test(20):
+for xt,yt in dataset.test(1):
-test_score += test_model(xt,yt)
-temp = temp+1
+total_exemple_count = total_exemple_count +1
-test_score /= temp
+#get activation for layer 1
+a0=numpy.dot(numpy.transpose(W1),numpy.transpose(xt[0])) + b1
+#add non linear function to layer 1 activation
-return test_score*100
+a0_out=numpy.tanh(a0)
+#get activation for output layer
+a1= numpy.dot(numpy.transpose(W2),a0_out) + b2
+#add non linear function for output activation (softmax)
+a1_exp = numpy.exp(a1)
+sum_a1=numpy.sum(a1_exp)
+a1_out=a1_exp/sum_a1
+predicted_class=numpy.argmax(a1_out)
+wanted_class=yt[0]
+if(predicted_class!=wanted_class):
+total_error_count = total_error_count +1
+#treat digit error
+if(wanted_class<10):
+nb_exemple_count=nb_exemple_count + 1
+predicted_class=numpy.argmax(a1_out[0:10])
+if(predicted_class!=wanted_class):
+nb_error_count = nb_error_count +1
+if(wanted_class>9):
+char_exemple_count=char_exemple_count + 1
+predicted_class=numpy.argmax(a1_out[10:62])+10
+if((predicted_class!=wanted_class) and ((predicted_class+26)!=wanted_class) and ((predicted_class-26)!=wanted_class)):
+char_error_count = char_error_count +1
+print (('total error = %f') % ((total_error_count/total_exemple_count)*100.0))
+print (('number error = %f') % ((nb_error_count/nb_exemple_count)*100.0))
+print (('char error = %f') % ((char_error_count/char_exemple_count)*100.0))
+return (total_error_count/total_exemple_count)*100.0

Mercurial > ift6266

comparison baseline/mlp/mlp_nist.py @ 404:1509b9bba4cc