loss = []
valid_loss = []
Train = DP.get_paths("/home/xvt131/Functions/Adhish_copy/Training-Rand")
Test = DP.get_paths("/home/xvt131/Functions/Adhish_copy/Validating-Rand")
for epoch in range(num_epochs):
print epoch
cur_loss = 0
val_loss = 0
confusion_valid = ConfusionMatrix(classes)
confusion_train = ConfusionMatrix(classes)
for im in Train:
B = np.array([])
Pos = np.empty((0, 1, 3))
Scan, Y_train, Post = DP.Sampling(im)
B = np.int32(np.append(B, Y_train))
Pos = np.float32(np.vstack((Pos, Post)))
random = np.arange(len(B))
Y_train = B[random]
Pos = Pos[random]
num_samples_train = Y_train.shape[0]
num_batches_train = num_samples_train // batch_size
for i in range(num_batches_train):
idx = range(i * batch_size, (i + 1) * batch_size)
pos_batch = Pos[idx]
target_batch = Y_train[idx]
batch_loss = f_train(pos_batch,
target_batch) #this will do the backprop pass
cur_loss += batch_loss[0] / num_samples_train
