diff --git a/REUNION/preProcData.py b/REUNION/preProcData.py
index e139774b2a7f33fbd4501cb3c0c25b5e349edd43..34742914741bb33712fbb6b686b4cfde4fec8952 100644
--- a/REUNION/preProcData.py
+++ b/REUNION/preProcData.py
@@ -8,7 +8,7 @@ def obtainVHSRData(vhsr_fileName, valid_pixels):
# I know that the minimum value of the BAND is 1
min_val = 1
scaling_factor = 5
- buffer_window = 6
+ buffer_window = 2 #6 if 65x65
data_vhsr = []
for k in range(len(valid_pixels)):
data_vhsr.append([])
diff --git a/REUNION/simpleCNN.py b/REUNION/simpleCNN.py
index e6cc8a6d8d99068bfde751c29445205d51f946fd..b2c75cde75b0a40fa09173b3ba3cf422d8ac7768 100644
--- a/REUNION/simpleCNN.py
+++ b/REUNION/simpleCNN.py
@@ -26,105 +26,95 @@ def getLabelFormat(Y):
return np.array(new_Y)
def CNN( x,height,width,n_filter,n_classes):
- conv1 = tf.layers.conv2d( inputs=x,
- filters=32,
- kernel_size=[5, 5],
- padding="same",
- activation=tf.nn.relu)
-
- pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2)
-
- conv2 = tf.layers.conv2d( inputs=pool1,
- filters=64,
- kernel_size=[5, 5],
- padding="same",
- activation=tf.nn.relu)
-
- pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)
+ pred = None
+
+ conv1 = tf.layers.conv2d( inputs = x, filters = n_filter, kernel_size = [ 7, 7 ], strides = (2, 2), padding = "same", activation = tf.nn.relu )
+ bn1 = tf.layers.batch_normalization(conv1)
+ n_filter += 48
+ conv2 = tf.layers.conv2d( inputs = bn1,
+ filters = n_filter,
+ kernel_size = [ 4, 4 ],
+ padding = "same",
+ activation = tf.nn.relu )
+ bn2 = tf.layers.batch_normalization(conv2)
+ n_filter -= 32
+ conv3 = tf.layers.conv2d( inputs = bn2,
+ filters = n_filter,
+ kernel_size = [ 3, 3 ],
+ padding = "same",
+ activation = tf.nn.relu )
+ bn3 = tf.layers.batch_normalization(conv3)
#vs max pool
- #pool2_flat = tf.reduce_max(conv2, [1,2])
- features = tf.reduce_max(pool2, [1,2])
-
- #features = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu)
- output = tf.layers.dense(inputs=features, units=n_classes)
- return output, features
-
-def checkTest( test_x, test_y, batch_size, sess ):
- iterations = test_x.shape[0]/batch_size
-
- if test_x.shape[0]%batch_size!=0:
- iterations+=1
-
- testacc = 0
- tot_pred = []
- for batch_id in range(iterations):
-
- batch_x, batch_y = getBatch(test_x, test_y, batch_size, batch_id )
- pred_temp = sess.run( prediction, feed_dict={ x:batch_x } )
-
- #TOT_PRED: accumulate max argument of each test prediciton evaluated by batch
- for el in pred_temp:
- tot_pred.append( np.argmax(el) )
-
- #GT: contains max argument of each testsplitRandDino.py ground truth
- gt = []
- for el in test_y:
- gt.append( np.argmax(el))
-
- tot_pred = tot_pred[0:len(gt)]
-
- test_KAPPA = cohen_kappa_score( gt, tot_pred )
- test_fs = f1_score( gt, tot_pred )
- test_acc = accuracy_score(gt, tot_pred, average='micro' )
- print "Test Accuracy ", test_acc
- return test_acc,test_fs,test_KAPPA
-
-
-
+ if tag_pool == "mean":
+ features = tf.reduce_mean(bn3, [1,2], name="features")
+ if tag_pool == "max":
+ features = tf.reduce_max(bn3, [1,2], name="features")
+
+ pred = tf.layers.dense(inputs=features, units=n_classes, name="prediction")
+ print "prediction",pred.get_shape()
+ #exit()
+ return pred, features
+
+# MAIN
+# Parameters
itr = int( sys.argv[1] )
p_split = 100*float( sys.argv[2] )
batch_size = int( sys.argv[3] )
hm_epochs= int( sys.argv[4] )
-
-n_filter = 32
+path_in_val = sys.argv[5]
+path_in_gt = sys.argv[6]
+tag_pool = sys.argv[7]
g_path = 'dataset/'
-#g_path = '../../../reunion_script/splits/'
+n_filter = 64
-f = open("logCNN%dbatch.txt"%batch_size,"a")
-var_train_x = g_path + 'VHSR/train_x%d_%d.npy'%(itr,p_split)
-var_train_y = g_path+'ground_truth/train_y%d_%d.npy'%(itr,p_split)
-
-var_test_x = g_path+'VHSR/test_x%d_%d.npy'%(itr,p_split)
-var_test_y = g_path+'ground_truth/test_y%d_%d.npy'%(itr,p_split)
+#paths
+var_train_x = path_in_val + 'train_x%d_%d.npy'%(itr,p_split)
+var_train_y = path_in_gt+'train_y%d_%d.npy'%(itr,p_split)
+#load dataset
#(90857,4,65,65)
train_x = np.load(var_train_x)
train_y = np.load(var_train_y)
-test_x = np.load(var_test_x)
-test_y = np.load(var_test_y)
+if path_in_val == './dataset/VHSR/':
-height = train_x.shape[2]
-width = height
-band = train_x.shape[1]
+ tag_band = '_'
+ # Network Parameters
+ height = train_x.shape[2]
+ width = height
+ band = train_x.shape[1]
+ n_classes = np.bincount( train_y ).shape[0]-1
+ #(90857,65,65,4)
+ train_x = np.swapaxes(train_x, 1, 3)
+else:
+ tag_band = 'NDVI_'
+ height = train_x.shape[1]
+ width = height
+ band = train_x.shape[3]
+ n_classes = np.bincount( train_y ).shape[0]-1
-print "train shape",train_x.shape
-print "width:%d"%width
-print "height%d"%height
-print "bands:%d"%band
+print "classes %d"%n_classes
-n_classes = np.bincount( test_y ).shape[0]-1
-print "n_classes:%d"%n_classes
+#format data
+train_y = getLabelFormat(train_y)
-#Graph input
-#drop_rate = tf.placeholder( tf.float32, [], name = "drop_rate" )
-#learning_rate = tf.placeholder(tf.float32, shape=[], name="learning_rate")
+directory = g_path+'SimpCnn%s_%s%d_%d/'%(tag_band, tag_pool, p_split, batch_size )
+if not os.path.exists(directory):
+ os.makedirs(directory)
-x = tf.placeholder("float",[None,height,width,band],name="x_cnn")
-y = tf.placeholder( tf.float32, [ None, n_classes ], name = "y" )
+path_out_model = directory+'modelTT%d/'%itr
+if not os.path.exists(path_out_model):
+ os.makedirs(path_out_model)
+
+#log file
+flog = open(directory+"log.txt","a")
+learning_rate = 0.001
+#tf_is_traing_pl = tf.placeholder(tf.bool, shape=(), name="is_training")
+x = tf.placeholder("float",[None,height,width,band],name="x")
+y = tf.placeholder( tf.float32, [ None, n_classes ], name = "y" )
sess = tf.InteractiveSession()
@@ -133,23 +123,20 @@ prediction, feat = CNN( x, height, width, n_filter, n_classes )
tensor1d = tf.nn.softmax_cross_entropy_with_logits(labels=y,logits=prediction)
cost = tf.reduce_mean(tensor1d)
-optimizer = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
+optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
correct = tf.equal(tf.argmax(prediction,1),tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct,tf.float64))
-tf.global_variables_initializer().run()
+#to have tensorboard
+tf.summary.scalar("cost function", cost)
+writer = tf.summary.FileWriter(path_out_model+"histogram_example")
+summaries = tf.summary.merge_all()
-train_y = getLabelFormat(train_y)
-test_y = getLabelFormat(test_y)
-print "train_y shape",train_y.shape
-print "test_y shape",test_y.shape
+tf.global_variables_initializer().run()
-#(90857,65,65,4)
-train_x = np.swapaxes(train_x, 1, 3)
-test_x = np.swapaxes(test_x, 1, 3)
-print "train_x shape",train_x.shape
-print "test_x shape",test_x.shape
+#initialise to save model
+saver = tf.train.Saver()
iterations = train_x.shape[0] / batch_size
@@ -157,6 +144,8 @@ if train_x.shape[0] % batch_size != 0:
iterations+=1
+best_loss = 50
+j = 0
for e in range(hm_epochs):
#shuffle input
train_x, train_y = shuffle(train_x, train_y)
@@ -165,20 +154,23 @@ for e in range(hm_epochs):
accuracy_ = 0
for batch_id in range( iterations ):
- #if batch_id%100==0:
- # print "iter %d su %d"%(batch_id, iterations)
+
batch_x, batch_y = getBatch(train_x, train_y, batch_size, batch_id )
- #print "batch_x = ",batch_x.shape
- #print "batch_y = ",batch_y.shape
- acc,_,c = sess.run([accuracy,optimizer,cost], feed_dict={x: batch_x, y:batch_y})
+ summ, acc, _, c = sess.run([summaries, accuracy, optimizer, cost], feed_dict={x: batch_x, y:batch_y})
accuracy_ += acc
lossfunc += c
+ writer.add_summary( summ, j )
+ j += 1
+
+ loss_epoch = float(lossfunc/iterations)
+ acc_epoch = float(accuracy_/iterations)
+ print "epoch %d Train loss:%f| Accuracy: %f"%( e, loss_epoch, acc_epoch )
+ flog.write( "epoch %d Train loss: %f| Accuracy: %f\n"%( e, loss_epoch, acc_epoch ) )
+
+ if loss_epoch < best_loss:
+ best_loss = loss_epoch
- print "epoch %d Train loss:%f| Accuracy: %f"%(e,lossfunc/iterations,accuracy_/iterations)
- #f.write("Train loss:%f| %f\n"%(lossfunc/iterations,accuracy_/iterations))
+ saver.save( sess, path_out_model+'model', global_step = itr )
-test_acc,test_fs,test_KAPPA = checkTest(test_x, test_y, batch_size, sess)
-print "%d\t%f\t%f\t%f\n"%( itr, test_acc, test_fs, test_KAPPA )
-f.write("%d\t%f\t%f\t%f\n"%( itr, test_acc, test_fs, test_KAPPA ))
-f.close()
+flog.close()