You need to train a computer vision model that predicts the type of government ID present in a given image using a GPU-powered virtual machine on Compute
Engine. You use the following parameters:
✑ Optimizer: SGD
✑ Image shape = 224ֳ—224
✑ Batch size = 64
✑ Epochs = 10
✑ Verbose =2
During training you encounter the following error: ResourceExhaustedError: Out Of Memory (OOM) when allocating tensor. What should you do?
When encountering a ResourceExhaustedError: Out Of Memory (OOM) during the training of a computer vision model, reducing the batch size is a common and effective solution. Decreasing the batch size reduces the amount of memory required for each training iteration, helping to avoid memory overflow issues. Other adjustments, like changing the image shape, might also alleviate the problem, but they might also degrade the model's performance. Adjusting the optimizer or learning rate typically does not affect memory usage as significantly as altering the batch size.
B. I think you want to reduce batch size. Learning rate and optimizer shouldn't really impact memory utilisation. Decreasing image size (A) would work, but might be costly in terms final performance
B. https://stackoverflow.com/questions/59394947/how-to-fix-resourceexhaustederror-oom-when-allocating-tensor/59395251#:~:text=OOM%20stands%20for%20%22out%20of,in%20your%20Dense%20%2C%20Conv2D%20layers
B is correct, it uses less memory. A works too but depending on what you need you will loose perfomance (just like maartenalexander said) so I think it is not recommended.
B is correct. Letter D can be used, as we reduced the image size but this will directly impact the model's performance. Another point is that when doing this, if you are using a model via Keras's `Functional API` you need to change the definition of the input and also apply pre-processing on the image to reduce its size . In other words: much more work than the letter B.
to fix memory overflow you need to reduce batch size also reduce input resolution is valid but reducing image size can harm model performance , so answer is B
Initially, I though D. ,decreasing image size, would be the correct one, but now that I am reviewing the test I think maartenalexander is correct in saying reduced image size might decrease final performance, so I'd go with B eventually.
B is my option. But, D seems not wrong. Reducing batch size or reducing image size bot can reduce memory usage. But, the former seems much easier.
The answer is B Since you are using an SGD, you can use a batch size of 1 ref: https://stackoverflow.com/questions/63139072/batch-size-for-stochastic-gradient-descent-is-length-of-training-data-and-not-1
Went with B
Reduce the image shape != Reduce the image Size.
Creating alerts to monitor for skew in the input data can help to detect when the distribution of the data has changed and the model's performance is affected. Once a skew is detected, retraining the model with the new data can improve its performance.
Sorry it's not the response for this question. it's the response for the previous question.
By reducing the batch size, the amount of memory required for each iteration of the training process is reduced
B is correct
no doubt went to B
B) Reduce the batch size.