How to limit loop to specified number of iterations?

Question

I am working on self driving car in nfs using neural network.

I have training data in hdf5 format. Using tensorflow to train model.

At first I thought it will take 100 but it is not stopping after 100.

Do I have to stop it manually (ctrl+C)?

import h5py 
import numpy as np 
import tensorflow as tf 
from googlenet import googlenet
#from alexnet import alexnet

# Training Parameters
learning_rate = 0.001
WIDTH = 200
HEIGHT = 150
EPOCHS = 100
MODEL_NAME = "draj_mod"

f = h5py.File("wasd_training_data.hdf5", "r")
print("File loaded")
model = googlenet(WIDTH, HEIGHT, learning_rate)

DATASET_COUNTER = 0 
for dataset in f.keys():
    DATASET_COUNTER+=1

DATASET_COUNTER = int(DATASET_COUNTER/2) 

for i in range(EPOCHS):
    for counter in range(DATASET_COUNTER):
        #HDF5 data is stored as dataset_#_X or dataset_#_Y
        label_X = "dataset" + str(counter) + "_X"
        label_Y = "dataset" + str(counter) + "_Y"

        data_X = np.array(f[label_X])
        data_Y = np.array(f[label_Y])

        train_data_X = data_X[:-500].reshape(-1, WIDTH, HEIGHT, 3)
        train_data_Y = data_Y[:-500]

        test_data_X = data_X[-500:].reshape(-1, WIDTH, HEIGHT, 3)
        test_data_Y = data_Y[-500:]

        model.fit({'input' : train_data_X}, {'targets' : train_data_Y}, n_epoch = 1, validation_set=({'input': test_data_X}, {'targets': test_data_Y}), snapshot_step = 1000, show_metric=True, run_id=MODEL_NAME)
    if(i%5 == 0):
        model.save(MODEL_NAME)

    # tensorboard --logdir=foo:F:/Workspace/nfssd/log
    #model.fit(X, Y, n_epoch=1000, validation_set=0.1, shuffle=True,
    #        show_metric=True, batch_size=64, snapshot_step=200,
    #        snapshot_epoch=False, run_id='googlenet_oxflowers17')

EPOCHS * DATASET_COUNTER

Maxim
– Maxim

2018-02-24 08:22:24 +00:00
Commented Feb 24, 2018 at 8:22 — Maxim
– Maxim, Commented Feb 24, 2018 at 8:22

Aman Khan · Accepted Answer · 2018-02-24 09:34:18Z

1

As you are calling the below-mentioned lines inside nested loop hence it will be called EPOCHS*DATASET_COUNTER times.

model.fit({'input' : train_data_X}, {'targets' : train_data_Y}, n_epoch = 1, validation_set=({'input': test_data_X}, {'targets': test_data_Y}), snapshot_step = 1000, show_metric=True, run_id=MODEL_NAME)

If you wish to run it only hundred times, please accumulate all your dataset in one and then call it outside the second loop (DATASET-COUNTER) and directly inside the first loop (EPOCH one).

answered Feb 24, 2018 at 9:34

Aman Khan

381 silver badge7 bronze badges

Sign up to request clarification or add additional context in comments.

1 Comment

Dhiraj Patil Over a year ago

can you please tell me which line of code i should directly write inside first loop? is that the one you mentioned?

Collectives™ on Stack Overflow

How to limit loop to specified number of iterations?

1 Answer 1

1 Comment

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

1 Comment

Your Answer

Sign up or log in

Post as a guest

Related