ResNet-18 Caffemodel @ilsvrc12 shrt 256 with Top-1 69% Top-5 89%

resnet-18-caffemodel-on-imagenet's People

Contributors

Stargazers

Watchers

Forkers

mingensiie githubfragments 2016xjtuzyt abrams90 niufuren algpower camel007 lubinboooos willamezhang zhengshou marvis walkoncross zhangleiedu farmingyard superhero1991 ssjatmhmy x0chen sysuzyq yousongzhu ihsan149 lollywang apereiracv yowhatever dandanjing jiangwqcooler yxftju dasona december-boy lcdsmao leempan whcsteam leehungxd wh-forker hongzhenwang sysau yuanh1990 aojunzhou amose-yao turengege fireae superxiaoying lqs19881030 jianweilin jiahuanchen hhgxx123 patrickket aquachieh feiwenbo chenquan-cq xuyunlu1030 sosoho mqchen1993 undercontroller nealvis peternara wywu wanglaotou hp-93 yangyanglisjtu jaosonma blankworld sjcircle zzmc johnhush ww-zwj wolfworld6 lakehui lareinahe dcnsw agdyangkang cuicaicai hqleeustc csyhhu ppfeng dz1135508698 dreadlord1984 oneteenager aramilcat k9sret qiaoxie pandinosaurus legendzzzzz softwaregift hawl666 andyliu93 jijiangyan jackyblackme bochengtsai zhahang0 bohanzhuang davilla7 waiting111 maxuehao zhangxinnan lchia joecth tinyloop laycoding jinliemma haiyang21

resnet-18-caffemodel-on-imagenet's Issues

Failed to parse NetParameter file: ResNet-18-model.caffemodel

F0420 14:02:31.106763 3624 upgrade_proto.cpp:86] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: ResNet-18-model.caffemodel
***Check failure stack trace: ***

Predictions are wrong

Hi,
I used your pre-trained model for inference but the results are very odd. None of the top 5 class are matching the actual labels.
Is there any kind of preprocessing that you implemented?

Not matching published results

Hi,
I tried both256 preprocessing, evaluated model on imagenet dataset and got Top1=66.626, Top5=87.556 which are short by around 1% than what is published(67.574% | 88.1001).
I used opencv for preprocessing and did similar to what is mentioned in deploy.prototxt file.
If possible can you please share evaluation script for this model which will generate published results.

10-crop or single-crop

I didn't get that high accuracy.so ,i want find some reasons. i firstly think that is data augment。

problem about fine tuning on UCF101 dataset

Can you show your training log about this model? I'm exploiting it as a pre-training model for fine tuning on UCF101 RGB dataset, the learning rate starts with 0.002,decreases to its 1/10 every 10,000 iterations,stops at 30,000 iterations,max iterations is 150,000.But the result is not pleasant,the loss decreases slowly as well as the error of test.

Test with Inf but train normally

Hi,

I tested your model and got following results.

I1204 15:02:51.487152 20681 caffe.cpp:309] Loss: 1.29169
I1204 15:02:51.487195 20681 caffe.cpp:321] acc/top-1 = 0.68608
I1204 15:02:51.487213 20681 caffe.cpp:321] acc/top-5 = 0.887702
I1204 15:02:51.487231 20681 caffe.cpp:321] loss = 1.29169 (* 1 = 1.29169 loss)

So far so good. Then, I was trying to apply some pruning technique to your model.

The training loss converges from 7.32351 to 1.74956, but the test loss remains 87.2697 since the beginning. As expected, the test accuracy is always ~0.005 for top-5 and ~0.001 for top-1.

I compared the L2-norm on single batch of training data and single testing data:

Test
data 186565.44
label 3736.5166
label_data_1_split_0 3736.5166
label_data_1_split_1 3736.5166
label_data_1_split_2 3736.5166
conv1 21728764.0
pool1 13620027.0
pool1_pool1_0_split_0 13620027.0
pool1_pool1_0_split_1 13620027.0
...
fc1000 inf
fc1000_fc1000_0_split_0 inf
fc1000_fc1000_0_split_1 inf
fc1000_fc1000_0_split_2 inf
loss 87.33654
acc/top-1 0.0
acc/top-5 0.0

Train
data 299836.56
label 6460.825
conv1 2865.9963
pool1 1788.9178
pool1_pool1_0_split_0 1788.9178
pool1_pool1_0_split_1 1788.9178
res2a_branch1 1357.2897
res2a_branch2a 822.31744
res2a_branch2b 1204.2449
...
fc1000 783.6228
loss 1.5208726

Do you have any idea what is the problem? Any feedback would be appreciated. Thanks!

Check failed: target_blobs.size() == source_layer.blobs_size() (2 vs. 1) Incompatible number of blobs for layer conv1

When i finetune the Resnet18 from the pre-model,there has a problem:
Check failed: target_blobs.size() == source_layer.blobs_size() (2 vs. 1) Incompatible number of blobs for layer conv1
and i add the bias_term,it can not solve it,so how to do?

.caffemodel training dataset

Hi,
you provided a caffemodel file for Resnet-18. I want to know, what part of Imgenet you used for training??

how to get the model？

how can i get the model？？

Resnet-18 model link on OneDrive

Hi,

Are you able to re-share pre-trained model on OneDrive? The link is no longer valid.

Thanks.

请问，怎么实现shrt 256方式的数据增广

你好，我刚接触caffe，不太清楚shrt 256是如何实现的，是在create_imagenet.sh中加以修改吗？

solver proto

do u have the solver proto? I've tried to train resnet18 with caffe but the max acc in validation set was 50%.

concerning preprocessing the data ?

Hi, to my best knowledge Caffe only supports symmetric resizing (i.e resizing KxK (e,g 256x256)).
How did you resize all images? Can you share your changes to Caffe or any scripts for that?
Best Regards

Unknown bottom blob 'gt_boxes' (layer 'rpn-data', bottom index 1)

Hi I am trying to train Resnet -18 from sratch on Pascal-VOC dataset using train.prototxt -

name: "ResNet-18"

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': 40"
}
}

layer {
bottom: "data"
top: "conv1"
name: "conv1"
type: "Convolution"
convolution_param {
num_output: 64
kernel_size: 7
pad: 3
stride: 2
}
}

layer {
bottom: "conv1"
top: "conv1"
name: "bn_conv1"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "conv1"
top: "conv1"
name: "scale_conv1"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "conv1"
top: "conv1"
name: "conv1_relu"
type: "ReLU"
}

layer {
bottom: "conv1"
top: "pool1"
name: "pool1"
type: "Pooling"
pooling_param {
kernel_size: 3
stride: 2
pool: MAX
}
}

layer {
bottom: "pool1"
top: "res2a_branch1"
name: "res2a_branch1"
type: "Convolution"
convolution_param {
num_output: 64
kernel_size: 1
pad: 0
stride: 1
bias_term: false
}
}

layer {
bottom: "res2a_branch1"
top: "res2a_branch1"
name: "bn2a_branch1"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res2a_branch1"
top: "res2a_branch1"
name: "scale2a_branch1"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "pool1"
top: "res2a_branch2a"
name: "res2a_branch2a"
type: "Convolution"
convolution_param {
num_output: 64
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}

layer {
bottom: "res2a_branch2a"
top: "res2a_branch2a"
name: "bn2a_branch2a"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res2a_branch2a"
top: "res2a_branch2a"
name: "scale2a_branch2a"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res2a_branch2a"
top: "res2a_branch2a"
name: "res2a_branch2a_relu"
type: "ReLU"
}

layer {
bottom: "res2a_branch2a"
top: "res2a_branch2b"
name: "res2a_branch2b"
type: "Convolution"
convolution_param {
num_output: 64
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}

layer {
bottom: "res2a_branch2b"
top: "res2a_branch2b"
name: "bn2a_branch2b"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res2a_branch2b"
top: "res2a_branch2b"
name: "scale2a_branch2b"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res2a_branch1"
bottom: "res2a_branch2b"
top: "res2a"
name: "res2a"
type: "Eltwise"
}

layer {
bottom: "res2a"
top: "res2a"
name: "res2a_relu"
type: "ReLU"
}

layer {
bottom: "res2a"
top: "res2b_branch2a"
name: "res2b_branch2a"
type: "Convolution"
convolution_param {
num_output: 64
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}

layer {
bottom: "res2b_branch2a"
top: "res2b_branch2a"
name: "bn2b_branch2a"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res2b_branch2a"
top: "res2b_branch2a"
name: "scale2b_branch2a"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res2b_branch2a"
top: "res2b_branch2a"
name: "res2b_branch2a_relu"
type: "ReLU"
}

layer {
bottom: "res2b_branch2a"
top: "res2b_branch2b"
name: "res2b_branch2b"
type: "Convolution"
convolution_param {
num_output: 64
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}

layer {
bottom: "res2b_branch2b"
top: "res2b_branch2b"
name: "bn2b_branch2b"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res2b_branch2b"
top: "res2b_branch2b"
name: "scale2b_branch2b"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res2a"
bottom: "res2b_branch2b"
top: "res2b"
name: "res2b"
type: "Eltwise"
}

layer {
bottom: "res2b"
top: "res2b"
name: "res2b_relu"
type: "ReLU"
}

layer {
bottom: "res2b"
top: "res3a_branch1"
name: "res3a_branch1"
type: "Convolution"
convolution_param {
num_output: 128
kernel_size: 1
pad: 0
stride: 2
bias_term: false
}
}

layer {
bottom: "res3a_branch1"
top: "res3a_branch1"
name: "bn3a_branch1"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res3a_branch1"
top: "res3a_branch1"
name: "scale3a_branch1"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res2b"
top: "res3a_branch2a"
name: "res3a_branch2a"
type: "Convolution"
convolution_param {
num_output: 128
kernel_size: 3
pad: 1
stride: 2
bias_term: false
}
}

layer {
bottom: "res3a_branch2a"
top: "res3a_branch2a"
name: "bn3a_branch2a"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res3a_branch2a"
top: "res3a_branch2a"
name: "scale3a_branch2a"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res3a_branch2a"
top: "res3a_branch2a"
name: "res3a_branch2a_relu"
type: "ReLU"
}

layer {
bottom: "res3a_branch2a"
top: "res3a_branch2b"
name: "res3a_branch2b"
type: "Convolution"
convolution_param {
num_output: 128
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}

layer {
bottom: "res3a_branch2b"
top: "res3a_branch2b"
name: "bn3a_branch2b"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res3a_branch2b"
top: "res3a_branch2b"
name: "scale3a_branch2b"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res3a_branch1"
bottom: "res3a_branch2b"
top: "res3a"
name: "res3a"
type: "Eltwise"
}

layer {
bottom: "res3a"
top: "res3a"
name: "res3a_relu"
type: "ReLU"
}

layer {
bottom: "res3a"
top: "res3b_branch2a"
name: "res3b_branch2a"
type: "Convolution"
convolution_param {
num_output: 128
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}

layer {
bottom: "res3b_branch2a"
top: "res3b_branch2a"
name: "bn3b_branch2a"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res3b_branch2a"
top: "res3b_branch2a"
name: "scale3b_branch2a"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res3b_branch2a"
top: "res3b_branch2a"
name: "res3b_branch2a_relu"
type: "ReLU"
}

layer {
bottom: "res3b_branch2a"
top: "res3b_branch2b"
name: "res3b_branch2b"
type: "Convolution"
convolution_param {
num_output: 128
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}

layer {
bottom: "res3b_branch2b"
top: "res3b_branch2b"
name: "bn3b_branch2b"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res3b_branch2b"
top: "res3b_branch2b"
name: "scale3b_branch2b"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res3a"
bottom: "res3b_branch2b"
top: "res3b"
name: "res3b"
type: "Eltwise"
}

layer {
bottom: "res3b"
top: "res3b"
name: "res3b_relu"
type: "ReLU"
}

layer {
bottom: "res3b"
top: "res4a_branch1"
name: "res4a_branch1"
type: "Convolution"
convolution_param {
num_output: 256
kernel_size: 1
pad: 0
stride: 2
bias_term: false
}
}

layer {
bottom: "res4a_branch1"
top: "res4a_branch1"
name: "bn4a_branch1"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res4a_branch1"
top: "res4a_branch1"
name: "scale4a_branch1"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res3b"
top: "res4a_branch2a"
name: "res4a_branch2a"
type: "Convolution"
convolution_param {
num_output: 256
kernel_size: 3
pad: 1
stride: 2
bias_term: false
}
}

layer {
bottom: "res4a_branch2a"
top: "res4a_branch2a"
name: "bn4a_branch2a"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res4a_branch2a"
top: "res4a_branch2a"
name: "scale4a_branch2a"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res4a_branch2a"
top: "res4a_branch2a"
name: "res4a_branch2a_relu"
type: "ReLU"
}

layer {
bottom: "res4a_branch2a"
top: "res4a_branch2b"
name: "res4a_branch2b"
type: "Convolution"
convolution_param {
num_output: 256
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}

layer {
bottom: "res4a_branch2b"
top: "res4a_branch2b"
name: "bn4a_branch2b"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res4a_branch2b"
top: "res4a_branch2b"
name: "scale4a_branch2b"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res4a_branch1"
bottom: "res4a_branch2b"
top: "res4a"
name: "res4a"
type: "Eltwise"
}

layer {
bottom: "res4a"
top: "res4a"
name: "res4a_relu"
type: "ReLU"
}

layer {
bottom: "res4a"
top: "res4b_branch2a"
name: "res4b_branch2a"
type: "Convolution"
convolution_param {
num_output: 256
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}

layer {
bottom: "res4b_branch2a"
top: "res4b_branch2a"
name: "bn4b_branch2a"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res4b_branch2a"
top: "res4b_branch2a"
name: "scale4b_branch2a"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res4b_branch2a"
top: "res4b_branch2a"
name: "res4b_branch2a_relu"
type: "ReLU"
}

layer {
bottom: "res4b_branch2a"
top: "res4b_branch2b"
name: "res4b_branch2b"
type: "Convolution"
convolution_param {
num_output: 256
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}

layer {
bottom: "res4b_branch2b"
top: "res4b_branch2b"
name: "bn4b_branch2b"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res4b_branch2b"
top: "res4b_branch2b"
name: "scale4b_branch2b"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res4a"
bottom: "res4b_branch2b"
top: "res4b"
name: "res4b"
type: "Eltwise"
}

layer {
bottom: "res4b"
top: "res4b"
name: "res4b_relu"
type: "ReLU"
}

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: 'debug-data'

type: 'Python'

bottom: 'data'

bottom: 'rpn_rois'

bottom: 'rpn_scores'

python_param {

module: 'rpn.debug_layer'

layer: 'RPNDebugLayer'

}

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': 40"
}
}

Stop Resnet till conv4x and add ROIpooling

layer {
name: "roi_pool5"
type: "ROIPooling"
bottom: "res4b"
bottom: "rois"
top: "roipool5"
roi_pooling_param {
pooled_w: 14
pooled_h: 14
spatial_scale: 0.0625 # 1/16
}
}

Resume Resnet conv5x layers after ROIpooling layers

layer {
bottom: "roipool5"
top: "res5a_branch1"
name: "res5a_branch1"
type: "Convolution"
convolution_param {
num_output: 512
kernel_size: 1
pad: 0
stride: 2
bias_term: false
}
}

layer {
bottom: "res5a_branch1"
top: "res5a_branch1"
name: "bn5a_branch1"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res5a_branch1"
top: "res5a_branch1"
name: "scale5a_branch1"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "roipool5"
top: "res5a_branch2a"
name: "res5a_branch2a"
type: "Convolution"
convolution_param {
num_output: 512
kernel_size: 3
pad: 1
stride: 2
bias_term: false
}
}

layer {
bottom: "res5a_branch2a"
top: "res5a_branch2a"
name: "bn5a_branch2a"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res5a_branch2a"
top: "res5a_branch2a"
name: "scale5a_branch2a"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res5a_branch2a"
top: "res5a_branch2a"
name: "res5a_branch2a_relu"
type: "ReLU"
}

layer {
bottom: "res5a_branch2a"
top: "res5a_branch2b"
name: "res5a_branch2b"
type: "Convolution"
convolution_param {
num_output: 512
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}

layer {
bottom: "res5a_branch2b"
top: "res5a_branch2b"
name: "bn5a_branch2b"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res5a_branch2b"
top: "res5a_branch2b"
name: "scale5a_branch2b"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res5a_branch1"
bottom: "res5a_branch2b"
top: "res5a"
name: "res5a"
type: "Eltwise"
}

layer {
bottom: "res5a"
top: "res5a"
name: "res5a_relu"
type: "ReLU"
}

layer {
bottom: "res5a"
top: "res5b_branch2a"
name: "res5b_branch2a"
type: "Convolution"
convolution_param {
num_output: 512
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}

layer {
bottom: "res5b_branch2a"
top: "res5b_branch2a"
name: "bn5b_branch2a"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res5b_branch2a"
top: "res5b_branch2a"
name: "scale5b_branch2a"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res5b_branch2a"
top: "res5b_branch2a"
name: "res5b_branch2a_relu"
type: "ReLU"
}

layer {
bottom: "res5b_branch2a"
top: "res5b_branch2b"
name: "res5b_branch2b"
type: "Convolution"
convolution_param {
num_output: 512
kernel_size: 3
pad: 1
stride: 1
bias_term: false
}
}

layer {
bottom: "res5b_branch2b"
top: "res5b_branch2b"
name: "bn5b_branch2b"
type: "BatchNorm"
batch_norm_param {
use_global_stats: true
}
}

layer {
bottom: "res5b_branch2b"
top: "res5b_branch2b"
name: "scale5b_branch2b"
type: "Scale"
scale_param {
bias_term: true
}
}

layer {
bottom: "res5a"
bottom: "res5b_branch2b"
top: "res5b"
name: "res5b"
type: "Eltwise"
}

layer {
bottom: "res5b"
top: "res5b"
name: "res5b_relu"
type: "ReLU"
}

layer {
bottom: "res5b"
top: "pool5"
name: "pool5"
type: "Pooling"
pooling_param {
kernel_size: 7
stride: 1
pool: AVE
}
}

######### Add faster RCNN cls and bbox layer

layer {
name: "cls_score_uefa"
type: "InnerProduct"
bottom: "pool5"
top: "cls_score_uefa"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
inner_product_param {
num_output: 40
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}

layer {
name: "bbox_pred_uefa"
type: "InnerProduct"
bottom: "pool5"
top: "bbox_pred_uefa"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
inner_product_param {
num_output: 160
weight_filler {
type: "gaussian"
std: 0.001
}
bias_filler {
type: "constant"
value: 0
}
}
}

layer {
name: "loss_cls"
type: "SoftmaxWithLoss"
bottom: "cls_score_uefa"
bottom: "labels"
propagate_down: 1
propagate_down: 0
top: "loss_cls"
loss_weight: 1
}

layer {
name: "loss_bbox"
type: "SmoothL1Loss"
bottom: "bbox_pred_uefa"
bottom: "bbox_targets"
bottom: "bbox_inside_weights"
bottom: "bbox_outside_weights"
top: "loss_bbox"
loss_weight: 1
}

And test.prototxt is -

name: "ResNet-18"

input: "data"
input_shape {
dim: 1
dim: 3
dim: 1280
dim: 720
}

input: "im_info"
input_shape {
dim: 1
dim: 3
}