How about GPU?

[Airotong]

I could run these code in my cpu tensorflow, but the training time is quite long. So I downloaded GPU tensorflow and wanted to run model_RGB.py again, but there were many peoblems. The most biggest problem is ResourceExhaustedError:OMM when allocating tensor with shape[3000,4000]. I want to know if these codes just for CPU? And we cannot simply apply them to GPU environment? Thank you for your reply! I am new to video description.

[siyilingting]

Hi, @Airotong , I have encountered a similar situation. Is this problem solved?

[knwng]

ResourceExhaustedError means you don't have enough GPU memory, you can try to use smaller data shape or upgrade your GPU

[Airotong]

How could I set the data size? I used smaller batch_size, but it lead to the same problem.

[siyilingting]

@Airotong You can try this. train_op = tf.train.AdamOptimizer(learning_rate).minimize(tf_loss,aggregation_method=tf.AggregationMethod.EXPERIMENTAL_ACCUMULATE_N) or train_op = tf.train.AdamOptimizer(learning_rate).minimize(tf_loss, aggregation_method=tf.AggregationMethod.EXPERIMENTAL_TREE) Maybe can solve your problem.

[Airotong]

Thank you for your reply! But I still met the same problem though I usedtrain_op = tf.train.AdamOptimizer(learning_rate).minimize(tf_loss,aggregation_method=tf.AggregationMethod.EXPERIMENTAL_ACCUMULATE_N) or train_op = tf.train.AdamOptimizer(learning_rate).minimize(tf_loss, aggregation_method=tf.AggregationMethod.EXPERIMENTAL_TREE)