How to calculate optimal batch size

Question

Sometimes I run into a problem:

OOM when allocating tensor with shape

e.q.

OOM when allocating tensor wi

Answer 1

to define function to find batch size for training the model

def FindBatchSize(model):
    """#model: model architecture, that is yet to be trained"""
    import os, sys, psutil, gc, tensorflow, keras
    import numpy as np
    from keras import backend as K
    BatchFound= 16

    try:
        total_params= int(model.count_params());    GCPU= "CPU"
        #find whether gpu is available
        try:
            if K.tensorflow_backend._get_available_gpus()== []:
                GCPU= "CPU";    #CPU and Cuda9GPU
            else:
                GCPU= "GPU"
        except:
            from tensorflow.python.client import device_lib;    #Cuda8GPU
            def get_available_gpus():
                local_device_protos= device_lib.list_local_devices()
                return [x.name for x in local_device_protos if x.device_type == 'GPU']
            if "gpu" not in str(get_available_gpus()).lower():
                GCPU= "CPU"
            else:
                GCPU= "GPU"

        #decide batch size on the basis of GPU availability and model complexity
        if (GCPU== "GPU") and (os.cpu_count() >15) and (total_params <1000000):
            BatchFound= 64    
        if (os.cpu_count() <16) and (total_params <500000):
            BatchFound= 64  
        if (GCPU== "GPU") and (os.cpu_count() >15) and (total_params <2000000) and (total_params >=1000000):
            BatchFound= 32      
        if (GCPU== "GPU") and (os.cpu_count() >15) and (total_params >=2000000) and (total_params <10000000):
            BatchFound= 16  
        if (GCPU== "GPU") and (os.cpu_count() >15) and (total_params >=10000000):
            BatchFound= 8       
        if (os.cpu_count() <16) and (total_params >5000000):
            BatchFound= 8    
        if total_params >100000000:
            BatchFound= 1

    except:
        pass
    try:

        #find percentage of memory used
        memoryused= psutil.virtual_memory()
        memoryused= float(str(memoryused).replace(" ", "").split("percent=")[1].split(",")[0])
        if memoryused >75.0:
            BatchFound= 8
        if memoryused >85.0:
            BatchFound= 4
        if memoryused >90.0:
            BatchFound= 2
        if total_params >100000000:
            BatchFound= 1
        print("Batch Size:  "+ str(BatchFound));    gc.collect()
    except:
        pass

    memoryused= [];    total_params= [];    GCPU= "";
    del memoryused, total_params, GCPU;    gc.collect()
    return BatchFound



#####################################################################################################
#####################################################################################################