SqueezeNet implementation for Faster RCNN #345
Comments
|
Please update if you get this working. Thanks |
|
@huvers ,I tried many possible methods of net architecture,none of them is effective, do you figure it out? |
|
@mengzhangjian - Not yet, I'm still working on it too. I'll put up a $100 bounty through paypal to whomever can get this working :) |
|
@mengzhangjian I am working on this right now, what is a result you achieve on which dataset? |
|
@karaspd ,I use it for face detection in WIDER face dataset, in the above config, I got nothing. |
|
@mengzhangjian it is a little bit strange. I am training and testing on kitti dataset with 3 different object difficulties. I used the squeezenet v1.1 and I placed roi-pool layer after fire9 with pooled_w: 7 |
|
@karaspd Would you mind sharing your train.prototxt for SqueezeNetv1.1 ? |
|
@karaspd Hrmmm, that wouldn't run for my case (I modified it for 5 classes). How did you come up with "rpn_cls_score" to output 120? |
|
if you want to consider 60 anchors you need to change scales and aspect ratio in rpn codes. However you can ignore it and just consider 9 anchors like before and test if you have any problem. change 120 to 18 and 240 to 36. |
|
@karaspd Yes, I've tried changing them back to the usual 18 and 36 (as well as the rpn_cls_prob_reshape layer back to 18), but I'm still seeing no convergence in learning, and an error on the validation set: File "/home/huvers/PycharmProjects/py-faster-rcnn/tools/../lib/datasets/voc_eval.py", line 148, in voc_eval The same data works just fine training with VGG16. Regardless, thanks for your help. |
|
I saw this error before, are you sure you are using a right pre-trained network? squeezenetv1.1? |
|
Yes, it is Squeezenetv1.1. So I discovered it was actually the learning rate that was giving it issues. Originally, lr = .001, which was apparently too much. Reducing this to lr = .0001 led to convergence and the previous error disappeared. Currently running a large number of iterations to see how well it ultimately performs on my custom dataset. |
|
That's great, let me know about your results. |
|
@karaspd Thank you for your contribution,I will test for my face data and tell you the result. |
|
Hi @mengzhangjian @huvers, how is the training going? Did you get any interesting results? |
|
Hi @karaspd My results haven't been very good so far. On my custom data (5 classes) VGG16 would achieve map=.80, while Squeezenet v1.1 can only do map=.55. I have to turn the confidence down very low for testing, and get a large number of false positives as a result. I've experimented by making pooled_w,h = 13, which did not work well (map=.38), as well as adjusting the number of rpn convolution features without success. Have you had better success? |
|
Hi @huvers, I am getting a large number of false positives same as you and the average map that I got on kitti dataset is 0.64. |
|
@karaspd ,Sorry for that.I just took holidays a few days, I test it for my face data and the detection result is effective,I will later get concrete result. Thanks |
|
Recently, I'm working on the integration of squeezenet and faster-rcnn. After checking your model @mengzhangjian ,I find out that after the roi-pooling layer ,you didn't add extra fully connected layer, would this decrease the detection performance? |
|
Hi @absorbguo @mengzhangjian were you able finally able to integrate SqueezeNet with faster RCNN ? is there a place where I can look at prototxt files ? |
@siddharthm83 am trying to use SqueezeNet with Faster RCNN.The following is my training prototxt.I modify the roi_pool layer:pooled_w:13,pooled_h:13.And the training process has no mistakes. While the detection result is very bad,can anyone help me solve this?
name: "VGG_ILSVRC_16_layers"
layer {
name: 'input-data'
type: 'Python'
top: 'data'
top: 'im_info'
top: 'gt_boxes'
python_param {
module: 'roi_data_layer.layer'
layer: 'RoIDataLayer'
param_str: "'num_classes': 2"
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
convolution_param {
num_output: 96
kernel_size: 7
stride: 2
weight_filler {
type: "xavier"
}
}
}
layer {
name: "relu_conv1"
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: "fire2/squeeze1x1"
type: "Convolution"
bottom: "pool1"
top: "fire2/squeeze1x1"
convolution_param {
num_output: 16
kernel_size: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire2/relu_squeeze1x1"
type: "ReLU"
bottom: "fire2/squeeze1x1"
top: "fire2/squeeze1x1"
}
layer {
name: "fire2/expand1x1"
type: "Convolution"
bottom: "fire2/squeeze1x1"
top: "fire2/expand1x1"
convolution_param {
num_output: 64
kernel_size: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire2/relu_expand1x1"
type: "ReLU"
bottom: "fire2/expand1x1"
top: "fire2/expand1x1"
}
layer {
name: "fire2/expand3x3"
type: "Convolution"
bottom: "fire2/squeeze1x1"
top: "fire2/expand3x3"
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire2/relu_expand3x3"
type: "ReLU"
bottom: "fire2/expand3x3"
top: "fire2/expand3x3"
}
layer {
name: "fire2/concat"
type: "Concat"
bottom: "fire2/expand1x1"
bottom: "fire2/expand3x3"
top: "fire2/concat"
}
layer {
name: "fire3/squeeze1x1"
type: "Convolution"
bottom: "fire2/concat"
top: "fire3/squeeze1x1"
convolution_param {
num_output: 16
kernel_size: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire3/relu_squeeze1x1"
type: "ReLU"
bottom: "fire3/squeeze1x1"
top: "fire3/squeeze1x1"
}
layer {
name: "fire3/expand1x1"
type: "Convolution"
bottom: "fire3/squeeze1x1"
top: "fire3/expand1x1"
convolution_param {
num_output: 64
kernel_size: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire3/relu_expand1x1"
type: "ReLU"
bottom: "fire3/expand1x1"
top: "fire3/expand1x1"
}
layer {
name: "fire3/expand3x3"
type: "Convolution"
bottom: "fire3/squeeze1x1"
top: "fire3/expand3x3"
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire3/relu_expand3x3"
type: "ReLU"
bottom: "fire3/expand3x3"
top: "fire3/expand3x3"
}
layer {
name: "fire3/concat"
type: "Concat"
bottom: "fire3/expand1x1"
bottom: "fire3/expand3x3"
top: "fire3/concat"
}
layer {
name: "fire4/squeeze1x1"
type: "Convolution"
bottom: "fire3/concat"
top: "fire4/squeeze1x1"
convolution_param {
num_output: 32
kernel_size: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire4/relu_squeeze1x1"
type: "ReLU"
bottom: "fire4/squeeze1x1"
top: "fire4/squeeze1x1"
}
layer {
name: "fire4/expand1x1"
type: "Convolution"
bottom: "fire4/squeeze1x1"
top: "fire4/expand1x1"
convolution_param {
num_output: 128
kernel_size: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire4/relu_expand1x1"
type: "ReLU"
bottom: "fire4/expand1x1"
top: "fire4/expand1x1"
}
layer {
name: "fire4/expand3x3"
type: "Convolution"
bottom: "fire4/squeeze1x1"
top: "fire4/expand3x3"
convolution_param {
num_output: 128
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire4/relu_expand3x3"
type: "ReLU"
bottom: "fire4/expand3x3"
top: "fire4/expand3x3"
}
layer {
name: "fire4/concat"
type: "Concat"
bottom: "fire4/expand1x1"
bottom: "fire4/expand3x3"
top: "fire4/concat"
}
layer {
name: "pool4"
type: "Pooling"
bottom: "fire4/concat"
top: "pool4"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "fire5/squeeze1x1"
type: "Convolution"
bottom: "pool4"
top: "fire5/squeeze1x1"
convolution_param {
num_output: 32
kernel_size: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire5/relu_squeeze1x1"
type: "ReLU"
bottom: "fire5/squeeze1x1"
top: "fire5/squeeze1x1"
}
layer {
name: "fire5/expand1x1"
type: "Convolution"
bottom: "fire5/squeeze1x1"
top: "fire5/expand1x1"
convolution_param {
num_output: 128
kernel_size: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire5/relu_expand1x1"
type: "ReLU"
bottom: "fire5/expand1x1"
top: "fire5/expand1x1"
}
layer {
name: "fire5/expand3x3"
type: "Convolution"
bottom: "fire5/squeeze1x1"
top: "fire5/expand3x3"
convolution_param {
num_output: 128
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire5/relu_expand3x3"
type: "ReLU"
bottom: "fire5/expand3x3"
top: "fire5/expand3x3"
}
layer {
name: "fire5/concat"
type: "Concat"
bottom: "fire5/expand1x1"
bottom: "fire5/expand3x3"
top: "fire5/concat"
}
layer {
name: "fire6/squeeze1x1"
type: "Convolution"
bottom: "fire5/concat"
top: "fire6/squeeze1x1"
convolution_param {
num_output: 48
kernel_size: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire6/relu_squeeze1x1"
type: "ReLU"
bottom: "fire6/squeeze1x1"
top: "fire6/squeeze1x1"
}
layer {
name: "fire6/expand1x1"
type: "Convolution"
bottom: "fire6/squeeze1x1"
top: "fire6/expand1x1"
convolution_param {
num_output: 192
kernel_size: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire6/relu_expand1x1"
type: "ReLU"
bottom: "fire6/expand1x1"
top: "fire6/expand1x1"
}
layer {
name: "fire6/expand3x3"
type: "Convolution"
bottom: "fire6/squeeze1x1"
top: "fire6/expand3x3"
convolution_param {
num_output: 192
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire6/relu_expand3x3"
type: "ReLU"
bottom: "fire6/expand3x3"
top: "fire6/expand3x3"
}
layer {
name: "fire6/concat"
type: "Concat"
bottom: "fire6/expand1x1"
bottom: "fire6/expand3x3"
top: "fire6/concat"
}
layer {
name: "fire7/squeeze1x1"
type: "Convolution"
bottom: "fire6/concat"
top: "fire7/squeeze1x1"
convolution_param {
num_output: 48
kernel_size: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire7/relu_squeeze1x1"
type: "ReLU"
bottom: "fire7/squeeze1x1"
top: "fire7/squeeze1x1"
}
layer {
name: "fire7/expand1x1"
type: "Convolution"
bottom: "fire7/squeeze1x1"
top: "fire7/expand1x1"
convolution_param {
num_output: 192
kernel_size: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire7/relu_expand1x1"
type: "ReLU"
bottom: "fire7/expand1x1"
top: "fire7/expand1x1"
}
layer {
name: "fire7/expand3x3"
type: "Convolution"
bottom: "fire7/squeeze1x1"
top: "fire7/expand3x3"
convolution_param {
num_output: 192
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire7/relu_expand3x3"
type: "ReLU"
bottom: "fire7/expand3x3"
top: "fire7/expand3x3"
}
layer {
name: "fire7/concat"
type: "Concat"
bottom: "fire7/expand1x1"
bottom: "fire7/expand3x3"
top: "fire7/concat"
}
layer {
name: "fire8/squeeze1x1"
type: "Convolution"
bottom: "fire7/concat"
top: "fire8/squeeze1x1"
convolution_param {
num_output: 64
kernel_size: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire8/relu_squeeze1x1"
type: "ReLU"
bottom: "fire8/squeeze1x1"
top: "fire8/squeeze1x1"
}
layer {
name: "fire8/expand1x1"
type: "Convolution"
bottom: "fire8/squeeze1x1"
top: "fire8/expand1x1"
convolution_param {
num_output: 256
kernel_size: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire8/relu_expand1x1"
type: "ReLU"
bottom: "fire8/expand1x1"
top: "fire8/expand1x1"
}
layer {
name: "fire8/expand3x3"
type: "Convolution"
bottom: "fire8/squeeze1x1"
top: "fire8/expand3x3"
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire8/relu_expand3x3"
type: "ReLU"
bottom: "fire8/expand3x3"
top: "fire8/expand3x3"
}
layer {
name: "fire8/concat"
type: "Concat"
bottom: "fire8/expand1x1"
bottom: "fire8/expand3x3"
top: "fire8/concat"
}
layer {
name: "pool8"
type: "Pooling"
bottom: "fire8/concat"
top: "pool8"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "fire9/squeeze1x1"
type: "Convolution"
bottom: "pool8"
top: "fire9/squeeze1x1"
convolution_param {
num_output: 64
kernel_size: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire9/relu_squeeze1x1"
type: "ReLU"
bottom: "fire9/squeeze1x1"
top: "fire9/squeeze1x1"
}
layer {
name: "fire9/expand1x1"
type: "Convolution"
bottom: "fire9/squeeze1x1"
top: "fire9/expand1x1"
convolution_param {
num_output: 256
kernel_size: 1
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire9/relu_expand1x1"
type: "ReLU"
bottom: "fire9/expand1x1"
top: "fire9/expand1x1"
}
layer {
name: "fire9/expand3x3"
type: "Convolution"
bottom: "fire9/squeeze1x1"
top: "fire9/expand3x3"
convolution_param {
num_output: 256
pad: 1
kernel_size: 3
weight_filler {
type: "xavier"
}
}
}
layer {
name: "fire9/relu_expand3x3"
type: "ReLU"
bottom: "fire9/expand3x3"
top: "fire9/expand3x3"
}
layer {
name: "fire9/concat"
type: "Concat"
bottom: "fire9/expand1x1"
bottom: "fire9/expand3x3"
top: "fire9/concat"
}
layer {
name: "drop9"
type: "Dropout"
bottom: "fire9/concat"
top: "fire9/concat"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "conv10"
type: "Convolution"
bottom: "fire9/concat"
top: "conv10"
convolution_param {
num_output: 1000
pad: 1
kernel_size: 1
weight_filler {
type: "gaussian"
mean: 0.0
std: 0.01
}
}
}
layer {
name: "relu_conv10"
type: "ReLU"
bottom: "conv10"
top: "conv10"
}
========= RPN ============
layer {
name: "rpn_conv/3x3"
type: "Convolution"
bottom: "conv10"
top: "rpn/output"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
convolution_param {
num_output: 512
kernel_size: 3 pad: 1 stride: 1
weight_filler { type: "gaussian" std: 0.01 }
bias_filler { type: "constant" value: 0 }
}
}
layer {
name: "rpn_relu/3x3"
type: "ReLU"
bottom: "rpn/output"
top: "rpn/output"
}
layer {
name: "rpn_cls_score"
type: "Convolution"
bottom: "rpn/output"
top: "rpn_cls_score"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
convolution_param {
num_output: 18 # 2(bg/fg) * 9(anchors)
kernel_size: 1 pad: 0 stride: 1
weight_filler { type: "gaussian" std: 0.01 }
bias_filler { type: "constant" value: 0 }
}
}
layer {
name: "rpn_bbox_pred"
type: "Convolution"
bottom: "rpn/output"
top: "rpn_bbox_pred"
param { lr_mult: 1.0 }
param { lr_mult: 2.0 }
convolution_param {
num_output: 36 # 4 * 9(anchors)
kernel_size: 1 pad: 0 stride: 1
weight_filler { type: "gaussian" std: 0.01 }
bias_filler { type: "constant" value: 0 }
}
}
layer {
bottom: "rpn_cls_score"
top: "rpn_cls_score_reshape"
name: "rpn_cls_score_reshape"
type: "Reshape"
reshape_param { shape { dim: 0 dim: 2 dim: -1 dim: 0 } }
}
layer {
name: 'rpn-data'
type: 'Python'
bottom: 'rpn_cls_score'
bottom: 'gt_boxes'
bottom: 'im_info'
bottom: 'data'
top: 'rpn_labels'
top: 'rpn_bbox_targets'
top: 'rpn_bbox_inside_weights'
top: 'rpn_bbox_outside_weights'
python_param {
module: 'rpn.anchor_target_layer'
layer: 'AnchorTargetLayer'
param_str: "'feat_stride': 16"
}
}
layer {
name: "rpn_loss_cls"
type: "SoftmaxWithLoss"
bottom: "rpn_cls_score_reshape"
bottom: "rpn_labels"
propagate_down: 1
propagate_down: 0
top: "rpn_cls_loss"
loss_weight: 1
loss_param {
ignore_label: -1
normalize: true
}
}
layer {
name: "rpn_loss_bbox"
type: "SmoothL1Loss"
bottom: "rpn_bbox_pred"
bottom: "rpn_bbox_targets"
bottom: 'rpn_bbox_inside_weights'
bottom: 'rpn_bbox_outside_weights'
top: "rpn_loss_bbox"
loss_weight: 1
smooth_l1_loss_param { sigma: 3.0 }
}
========= RoI Proposal ============
layer {
name: "rpn_cls_prob"
type: "Softmax"
bottom: "rpn_cls_score_reshape"
top: "rpn_cls_prob"
}
layer {
name: 'rpn_cls_prob_reshape'
type: 'Reshape'
bottom: 'rpn_cls_prob'
top: 'rpn_cls_prob_reshape'
reshape_param { shape { dim: 0 dim: 18 dim: -1 dim: 0 } }
}
layer {
name: 'proposal'
type: 'Python'
bottom: 'rpn_cls_prob_reshape'
bottom: 'rpn_bbox_pred'
bottom: 'im_info'
top: 'rpn_rois'
top: 'rpn_scores'
python_param {
module: 'rpn.proposal_layer'
layer: 'ProposalLayer'
param_str: "'feat_stride': 16"
}
}
layer {
name: 'roi-data'
type: 'Python'
bottom: 'rpn_rois'
bottom: 'gt_boxes'
top: 'rois'
top: 'labels'
top: 'bbox_targets'
top: 'bbox_inside_weights'
top: 'bbox_outside_weights'
python_param {
module: 'rpn.proposal_target_layer'
layer: 'ProposalTargetLayer'
param_str: "'num_classes': 2"
}
}
========= RCNN ============
layer {
name: "roi_pool5"
type: "ROIPooling"
bottom: "conv10"
bottom: "rois"
top: "pool10"
roi_pooling_param {
pooled_w: 13
pooled_h: 13
spatial_scale: 0.0625 # 1/16
}
}
layer {
name: "cls_score"
type: "InnerProduct"
bottom: "pool10"
top: "cls_score"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
inner_product_param {
num_output: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "bbox_pred"
type: "InnerProduct"
bottom: "pool10"
top: "bbox_pred"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
inner_product_param {
num_output: 8
weight_filler {
type: "gaussian"
std: 0.001
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "loss_cls"
type: "SoftmaxWithLoss"
bottom: "cls_score"
bottom: "labels"
propagate_down: 1
propagate_down: 0
top: "loss_cls"
loss_weight: 1
}
layer {
name: "loss_bbox"
type: "SmoothL1Loss"
bottom: "bbox_pred"
bottom: "bbox_targets"
bottom: "bbox_inside_weights"
bottom: "bbox_outside_weights"
top: "loss_bbox"
loss_weight: 1
}
The text was updated successfully, but these errors were encountered: