can not conver the bvlc_googlenet.caffemodel about feathercnn

[turbo0628]

Thanks for reporting. Seems that caffe cannot load its own protobuf, I'll check the problem in a few days.

[sxsxsx]

I'm glad to receive your reply，I solved this problem by using upgrade_net_proto_binary.exe to upgrade the bvlc_googlenet.caffemodel ，and it is successful to conver the caffemodel to the feathermodel，but I have new questions while running on the rk3288(armeabi-v7a)
host:ubantu16.04 NDK r17

1、bvlc_googlenet.feathermodel
Forward
layer conv1/7x7_s2 type Convolution spent 158.054167ms
layer conv1/relu_7x7 type ReLU spent 5.689833ms
layer pool1/3x3_s2 type Pooling spent 19.716958ms
layer pool1/norm1 type LRN spent 69.234666ms
layer conv2/3x3_reduce type Convolution spent 15.302583ms
layer conv2/relu_3x3_reduce type ReLU spent 1.325625ms
Too many args to microtask: 21!

2、my.feathermodel

/test32 my.feathermodel input_3x32x32.txt 20 1
WARNING: linker: ./test32: unused DT entry: type 0x1d arg 0x6ef
WARNING: linker: ./test32: unused DT entry: type 0x6ffffffe arg 0x19a8
WARNING: linker: ./test32: unused DT entry: type 0x6fffffff arg 0x2
++++++Start Loader++++++
Finished loading from file
-- Loading 39 layers
input num 1 input dim num 4
input_name data (n c h w) (1 3 32 32)
stride 1, 1
_bottom data
setup layer conv0
_bottom conv0
setup layer relu0
stride 1, 1
_bottom relu0
setup layer conv1/1
_bottom conv1/1
setup layer conv1/1_relu
stride 1, 1
_bottom conv1/1_relu
setup layer conv1/e1
_bottom conv1/e1
setup layer conv1/e1_relu
_bottom conv1/e1_relu
kernel (3 3) pad (0 0) stride (2 2) global_pooling 0
setup layer conv1/e1_pool
stride 2, 2
_bottom conv1/1_relu
setup layer conv1/s3
_bottom conv1/s3
setup layer conv1/s3_relu
_bottom conv1/e1_pool
_bottom conv1/s3_relu
setup layer conv1/concat
_bottom conv1/concat
setup layer conv1/concat_BN
stride 1, 1
_bottom conv1/concat_BN
setup layer conv2/1
_bottom conv2/1
setup layer conv2/1_relu
stride 1, 1
_bottom conv2/1_relu
setup layer conv2/e1
_bottom conv2/e1
setup layer conv2/e1_relu
_bottom conv2/e1_relu
kernel (3 3) pad (0 0) stride (2 2) global_pooling 0
setup layer conv2/e1_pool
stride 2, 2
_bottom conv2/1_relu
setup layer conv2/s3
_bottom conv2/s3
setup layer conv2/s3_relu
_bottom conv2/e1_pool
_bottom conv2/s3_relu
setup layer conv2/concat
_bottom conv2/concat
setup layer conv2/concat_BN
stride 1, 1
_bottom conv2/concat_BN
setup layer conv3/1
_bottom conv3/1
setup layer conv3/1_relu
stride 1, 1
_bottom conv3/1_relu
setup layer conv3/e1
_bottom conv3/e1
setup layer conv3/e1_relu
_bottom conv3/e1_relu
kernel (3 3) pad (0 0) stride (2 2) global_pooling 0
setup layer conv3/e1_pool
stride 2, 2
_bottom conv3/1_relu
setup layer conv3/s3
_bottom conv3/s3
setup layer conv3/s3_relu
_bottom conv3/e1_pool
_bottom conv3/s3_relu
setup layer conv3/concat
_bottom conv3/concat
setup layer conv3/concat_BN
stride 1, 1
_bottom conv3/concat_BN
setup layer conv_cls
Layer type PReLU not registered
setup layer relu_cls
_bottom relu_cls
setup layer conv_cls_BN
stride 1, 1
_bottom conv_cls_BN
setup layer fc_cls
_bottom fc_cls
setup layer cls_prob
stride 1, 1
_bottom conv3/concat_BN
setup layer conv_reg
Layer type PReLU not registered
setup layer relu_reg
_bottom relu_reg
setup layer conv_BN_reg
stride 1, 1
_bottom conv_BN_reg
setup layer fc_reg
Output shape 32 16 16
Output shape 64 8 8
Output shape 64 4 4
Segmentation fault