Hello,
and Help!
I am stuck in Lesson3 trying to train fc_model.
Since combined sizes of trn and val _features exceed 10GB my computer can’t cope with it.
Besides, it is preposterous to clog memory with such huge arrays being used only in sequential way… that’s what a disk is for! I think…
I tried to write small generator to access bclozed previously arrays: train_convlayer_features.bc and valid_convlayer_features.bc and benefit from fit_generator to train fc_model.
Here’s code, maybe someone with better understanding of Python generators and bcolz can help me find why the bloody thingy is yielding one and same sample?
def flow_from_bcoltz(path,output_labels,batch_size):
i=0
n=len(output_labels)
b= bcolz.open(path)
while True:
j=i+batch_size
if j>n: j=n
res1, res2 = b[i:j], output_labels[i:j]
if j-i < batch_size:
j = batch_size - (n-i)
res1, res2 = np.vstack((res1,b[0:j])), np.vstack((res2,output_labels[0:j]))
j=0
i=j
yield res1,res2
I spent quite a lot of time before I noticed… :)) being surprised by a huge overfitting!
Peter