Skip to content

Instantly share code, notes, and snippets.

Embed
What would you like to do?
DeepDrive - Vision model that drives in GTAV
name caffemodel caffemodel_url license sha1 caffe_commit gist_id
DeepDrive
caffe_deep_drive_train_iter_35352.caffemodel
MIT
448c5fe310a8ac954f2dbb7d6e19733edad63c6f
843575eca2582fc30588ceaf31c987ad7707033d
66e69c10c9ec82b299279bc7609544d2

This model stays inside the lane and stops for traffic in various weather and lighting conditions in GTAV when viewing images streamed from a hood-mounted camera. It was trained on top of BVLC's reference AlexNet model. See deepdrive.io for complete details.

License

MIT

name: "GTANet"
# Can be used with pretrained Caffenet (AlexNet architecture).
# Layers with names containing 'gtanet' are not transferred from Caffenet.
layer {
name: "gta_frames_input_layer"
type: "HDF5Data"
top: "images"
top: "targets"
hdf5_data_param {
source: "data/deep_drive/full_train_h5_list.txt"
batch_size: 64
shuffle: true
}
include { phase:TRAIN }
}
layer {
name: "gta_frames_input_layer"
type: "HDF5Data"
top: "images"
top: "targets"
hdf5_data_param {
source: "data/deep_drive/full_test_h5_list.txt"
batch_size: 64
}
include { phase:TEST }
}
layer {
name: "conv1"
type: "Convolution"
bottom: "images"
top: "conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 96
kernel_size: 11
stride: 4
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "pool1"
type: "Pooling"
bottom: "conv1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "norm1"
type: "LRN"
bottom: "pool1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "norm1"
top: "conv2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "pool2"
type: "Pooling"
bottom: "conv2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "norm2"
type: "LRN"
bottom: "pool2"
top: "norm2"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "norm2"
top: "conv3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu4"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv4"
top: "conv5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu5"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "pool5"
type: "Pooling"
bottom: "conv5"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "fc6_gtanet"
type: "InnerProduct"
bottom: "pool5"
top: "fc6"
param {
lr_mult: 1 # learning rate multiplier for the filters
decay_mult: 1 # weight decay multiplier for the filters
}
param {
lr_mult: 2 # learning rate multiplier for the biases
decay_mult: 0 # weight decay multiplier for the biases
}
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu6_gtanet"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop6_gtanet"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7_gtanet"
type: "InnerProduct"
bottom: "fc6"
top: "fc7"
param {
lr_mult: 1 # learning rate multiplier for the filters
decay_mult: 1 # weight decay multiplier for the filters
}
param {
lr_mult: 2 # learning rate multiplier for the biases
decay_mult: 0 # weight decay multiplier for the biases
}
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 1
}
}
}
layer {
name: "relu7_gtanet"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "drop7_gtanet"
type: "Dropout"
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.05
}
}
# The output layer is a fully-connected linear layer with a single output for each valid action.
layer {
name: "gtanet_fctop"
type: "InnerProduct"
bottom: "fc7"
top: "gtanet_fctop"
param {
lr_mult: 1 # learning rate multiplier for the filters
decay_mult: 1 # weight decay multiplier for the filters
}
param {
lr_mult: 2 # learning rate multiplier for the biases
decay_mult: 0 # weight decay multiplier for the biases
}
inner_product_param {
num_output: 6 # Number of output neurons
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "loss"
type: "EuclideanLoss"
bottom: "gtanet_fctop"
bottom: "targets"
top: "loss"
}
net: "examples/deep_drive/deep_drive_model.prototxt"
test_iter: 1000
test_interval: 2000
type: "Adam"
momentum: 0.8
momentum2: 0.9
base_lr: 0.0002
# manually decay to the following when learning subsides
#base_lr: 0.00002
#base_lr: 0.000002
#base_lr: 0.0000002
#base_lr: 0.00000002
#base_lr: 0.000000002
lr_policy: "step" # learning rate policy: drop the learning rate in "steps"
# by a factor of gamma every stepsize iterations
gamma: 0.1 # drop the learning rate by this factor
stepsize: 20000 # drop the learning rate by above every stepsize iterations
snapshot: 20000
snapshot_prefix: "caffe_deep_drive_train"
max_iter: 50000000
weight_decay: 0.0005
display: 40
solver_mode: GPU
test_initialization: false
#debug_info: true
@Chagall

This comment has been minimized.

Copy link

commented Aug 8, 2016

super cool!!

@tebzito

This comment has been minimized.

Copy link

commented Nov 24, 2016

If you don't mind me asking, where can I get the deepdrive.tfweights?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.