## @package convnet_benchmarks
# Module caffe2.python.convnet_benchmarks
"""
Benchmark for common convnets.

Speed on Titan X, with 10 warmup steps and 10 main steps and with different
versions of cudnn, are as follows (time reported below is per-batch time,
forward / forward+backward):

                    CuDNN V3        CuDNN v4
AlexNet         32.5 / 108.0    27.4 /  90.1
OverFeat       113.0 / 342.3    91.7 / 276.5
Inception      134.5 / 485.8   125.7 / 450.6
VGG (batch 64) 200.8 / 650.0   164.1 / 551.7

Speed on Inception with varied batch sizes and CuDNN v4 is as follows:

Batch Size   Speed per batch     Speed per image
 16             22.8 /  72.7         1.43 / 4.54
 32             38.0 / 127.5         1.19 / 3.98
 64             67.2 / 233.6         1.05 / 3.65
128            125.7 / 450.6         0.98 / 3.52

Speed on Tesla M40, which 10 warmup steps and 10 main steps and with cudnn
v4, is as follows:

AlexNet         68.4 / 218.1
OverFeat       210.5 / 630.3
Inception      300.2 / 1122.2
VGG (batch 64) 405.8 / 1327.7

(Note that these numbers involve a "full" backprop, i.e. the gradient
with respect to the input image is also computed.)

To get the numbers, simply run:

for MODEL in AlexNet OverFeat Inception; do
  PYTHONPATH=../gen:$PYTHONPATH python convnet_benchmarks.py \
    --batch_size 128 --model $MODEL --forward_only True
done
for MODEL in AlexNet OverFeat Inception; do
  PYTHONPATH=../gen:$PYTHONPATH python convnet_benchmarks.py \
    --batch_size 128 --model $MODEL
done
PYTHONPATH=../gen:$PYTHONPATH python convnet_benchmarks.py \
  --batch_size 64 --model VGGA --forward_only True
PYTHONPATH=../gen:$PYTHONPATH python convnet_benchmarks.py \
  --batch_size 64 --model VGGA

for BS in 16 32 64 128; do
  PYTHONPATH=../gen:$PYTHONPATH python convnet_benchmarks.py \
    --batch_size $BS --model Inception --forward_only True
  PYTHONPATH=../gen:$PYTHONPATH python convnet_benchmarks.py \
    --batch_size $BS --model Inception
done

Note that VGG needs to be run at batch 64 due to memory limit on the backward
pass.
"""

import argparse

from caffe2.python import workspace, brew, model_helper


def MLP(order, cudnn_ws):
    model = model_helper.ModelHelper(name="MLP")
    d = 256
    depth = 20
    width = 3
    for i in range(depth):
        for j in range(width):
            current = "fc_{}_{}".format(i, j) if i > 0 else "data"
            next_ = "fc_{}_{}".format(i + 1, j)
            brew.fc(
                model,
                current,
                next_,
                dim_in=d,
                dim_out=d,
                weight_init=('XavierFill', {}),
                bias_init=('XavierFill', {}),
            )
    brew.sum(
        model, ["fc_{}_{}".format(depth, j) for j in range(width)], ["sum"]
    )
    brew.fc(
        model,
        "sum",
        "last",
        dim_in=d,
        dim_out=1000,
        weight_init=('XavierFill', {}),
        bias_init=('XavierFill', {}),
    )
    xent = model.net.LabelCrossEntropy(["last", "label"], "xent")
    model.net.AveragedLoss(xent, "loss")
    return model, d


def AlexNet(order, cudnn_ws):
    my_arg_scope = {
        'order': order,
        'use_cudnn': True,
        'cudnn_exhaustive_search': True,
    }
    if cudnn_ws:
        my_arg_scope['ws_nbytes_limit'] = cudnn_ws
    model = model_helper.ModelHelper(
        name="alexnet",
        arg_scope=my_arg_scope,
    )
    conv1 = brew.conv(
        model,
        "data",
        "conv1",
        3,
        64,
        11, ('XavierFill', {}), ('ConstantFill', {}),
        stride=4,
        pad=2
    )
    relu1 = brew.relu(model, conv1, "conv1")
    pool1 = brew.max_pool(model, relu1, "pool1", kernel=3, stride=2)
    conv2 = brew.conv(
        model,
        pool1,
        "conv2",
        64,
        192,
        5,
        ('XavierFill', {}),
        ('ConstantFill', {}),
        pad=2
    )
    relu2 = brew.relu(model, conv2, "conv2")
    pool2 = brew.max_pool(model, relu2, "pool2", kernel=3, stride=2)
    conv3 = brew.conv(
        model,
        pool2,
        "conv3",
        192,
        384,
        3,
        ('XavierFill', {}),
        ('ConstantFill', {}),
        pad=1
    )
    relu3 = brew.relu(model, conv3, "conv3")
    conv4 = brew.conv(
        model,
        relu3,
        "conv4",
        384,
        256,
        3,
        ('XavierFill', {}),
        ('ConstantFill', {}),
        pad=1
    )
    relu4 = brew.relu(model, conv4, "conv4")
    conv5 = brew.conv(
        model,
        relu4,
        "conv5",
        256,
        256,
        3,
        ('XavierFill', {}),
        ('ConstantFill', {}),
        pad=1
    )
    relu5 = brew.relu(model, conv5, "conv5")
    pool5 = brew.max_pool(model, relu5, "pool5", kernel=3, stride=2)
    fc6 = brew.fc(
        model,
        pool5, "fc6", 256 * 6 * 6, 4096, ('XavierFill', {}),
        ('ConstantFill', {})
    )
    relu6 = brew.relu(model, fc6, "fc6")
    fc7 = brew.fc(
        model, relu6, "fc7", 4096, 4096, ('XavierFill', {}), ('ConstantFill', {})
    )
    relu7 = brew.relu(model, fc7, "fc7")
    fc8 = brew.fc(
        model, relu7, "fc8", 4096, 1000, ('XavierFill', {}), ('ConstantFill', {})
    )
    pred = brew.softmax(model, fc8, "pred")
    xent = model.net.LabelCrossEntropy([pred, "label"], "xent")
    model.net.AveragedLoss(xent, "loss")
    return model, 224


def OverFeat(order, cudnn_ws):
    my_arg_scope = {
        'order': order,
        'use_cudnn': True,
        'cudnn_exhaustive_search': True,
    }
    if cudnn_ws:
        my_arg_scope['ws_nbytes_limit'] = cudnn_ws
    model = model_helper.ModelHelper(
        name="overfeat",
        arg_scope=my_arg_scope,
    )
    conv1 = brew.conv(
        model,
        "data",
        "conv1",
        3,
        96,
        11,
        ('XavierFill', {}),
        ('ConstantFill', {}),
        stride=4,
    )
    relu1 = brew.relu(model, conv1, "conv1")
    pool1 = brew.max_pool(model, relu1, "pool1", kernel=2, stride=2)
    conv2 = brew.conv(
        model, pool1, "conv2", 96, 256, 5, ('XavierFill', {}),
        ('ConstantFill', {})
    )
    relu2 = brew.relu(model, conv2, "conv2")
    pool2 = brew.max_pool(model, relu2, "pool2", kernel=2, stride=2)
    conv3 = brew.conv(
        model,
        pool2,
        "conv3",
        256,
        512,
        3,
        ('XavierFill', {}),
        ('ConstantFill', {}),
        pad=1,
    )
    relu3 = brew.relu(model, conv3, "conv3")
    conv4 = brew.conv(
        model,
        relu3,
        "conv4",
        512,
        1024,
        3,
        ('XavierFill', {}),
        ('ConstantFill', {}),
        pad=1,
    )
    relu4 = brew.relu(model, conv4, "conv4")
    conv5 = brew.conv(
        model,
        relu4,
        "conv5",
        1024,
        1024,
        3,
        ('XavierFill', {}),
        ('ConstantFill', {}),
        pad=1,
    )
    relu5 = brew.relu(model, conv5, "conv5")
    pool5 = brew.max_pool(model, relu5, "pool5", kernel=2, stride=2)
    fc6 = brew.fc(
        model, pool5, "fc6", 1024 * 6 * 6, 3072, ('XavierFill', {}),
        ('ConstantFill', {})
    )
    relu6 = brew.relu(model, fc6, "fc6")
    fc7 = brew.fc(
        model, relu6, "fc7", 3072, 4096, ('XavierFill', {}), ('ConstantFill', {})
    )
    relu7 = brew.relu(model, fc7, "fc7")
    fc8 = brew.fc(
        model, relu7, "fc8", 4096, 1000, ('XavierFill', {}), ('ConstantFill', {})
    )
    pred = brew.softmax(model, fc8, "pred")
    xent = model.net.LabelCrossEntropy([pred, "label"], "xent")
    model.net.AveragedLoss(xent, "loss")
    return model, 231


def VGGA(order, cudnn_ws):
    my_arg_scope = {
        'order': order,
        'use_cudnn': True,
        'cudnn_exhaustive_search': True,
    }
    if cudnn_ws:
        my_arg_scope['ws_nbytes_limit'] = cudnn_ws
    model = model_helper.ModelHelper(
        name="vgga",
        arg_scope=my_arg_scope,
    )
    conv1 = brew.conv(
        model,
        "data",
        "conv1",
        3,
        64,
        3,
        ('XavierFill', {}),
        ('ConstantFill', {}),
        pad=1,
    )
    relu1 = brew.relu(model, conv1, "conv1")
    pool1 = brew.max_pool(model, relu1, "pool1", kernel=2, stride=2)
    conv2 = brew.conv(
        model,
        pool1,
        "conv2",
        64,
        128,
        3,
        ('XavierFill', {}),
        ('ConstantFill', {}),
        pad=1,
    )
    relu2 = brew.relu(model, conv2, "conv2")
    pool2 = brew.max_pool(model, relu2, "pool2", kernel=2, stride=2)
    conv3 = brew.conv(
        model,
        pool2,
        "conv3",
        128,
        256,
        3,
        ('XavierFill', {}),
        ('ConstantFill', {}),
        pad=1,
    )
    relu3 = brew.relu(model, conv3, "conv3")
    conv4 = brew.conv(
        model,
        relu3,
        "conv4",
        256,
        256,
        3,
        ('XavierFill', {}),
        ('ConstantFill', {}),
        pad=1,
    )
    relu4 = brew.relu(model, conv4, "conv4")
    pool4 = brew.max_pool(model, relu4, "pool4", kernel=2, stride=2)
    conv5 = brew.conv(
        model,
        pool4,