chuanqi305 MobileNetv2-SSDLite issues

chuanqi305 / MobileNetv2-SSDLite

Caffe implementation of SSD and SSDLite detection on MobileNetv2, converted from tensorflow.

MIT License

448 stars 231 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

module 'caffe' has no attribute 'Net'

#66 HesahmGamal opened 2 years ago
0
pretrain model

#65 KelvinHuang666 opened 4 years ago
0
make XML for negative sample ？

#64 weilanShi opened 4 years ago
0
mAP for ssd and ssdlite caffe models without any finetuning?

#63 fcakir opened 4 years ago
0
What is the size of parameter file for mobilenetv2_ssdlite?

#62 2696120622 opened 4 years ago
1
delete

#61 StrugglingForBetter opened 4 years ago
0
delete

#60 StrugglingForBetter opened 4 years ago
0
mAP on VOC07 test dataset

#59 notabigfish opened 4 years ago
0
why trained model can't detect objects correctly?

#58 StrugglingForBetter opened 4 years ago
0
1.5 has type float, but expected one of: int, long ?

#57 match08 opened 5 years ago
1
Mobilenetv2-sssdlit is slower than Mobilnetssd !! why ?!

#56 moemen95 closed 3 years ago
0
Question about slice and silence ops

#55 kazenokizi opened 5 years ago
0
SSDLite --size 0.75 issue

#54 ShechemKS opened 5 years ago
1
Check failed: label < num_classes

#53 FSet89 opened 5 years ago
1
batchnorm sub

#52 roadcode closed 5 years ago
0
input size width!=height

#51 moaljazaery opened 5 years ago
0
trained model there are no detections

#50 lucasjinreal opened 5 years ago
2
share the link to the pretrained model

#49 peterpaniff opened 5 years ago
5
ValueError: cannot reshape array of size 36288 into shape (273,576,1,1)？

#48 ChenjingYu1993 opened 5 years ago
0
MobileNetV2-SSD output error

#47 nistarlwc opened 5 years ago
0
what is silence layer ?

#46 ujsyehao opened 5 years ago
0
Check failed: num_priors_ * num_classes_ == bottom[1]->channels()

#45 gongdalinux opened 5 years ago
0
Check failed: fd != -1 (-1 vs. -1) File not found

#44 corleonechensiyu opened 5 years ago
3
IOError: [Errno 2] No such file or directory: 'output/Conv_bn_moving_mean.dat'

#43 corleonechensiyu opened 5 years ago
8
Questuion: model reshaping caffe model in dump_tensorflow_weights.py

#42 ShihweiChen opened 5 years ago
0
Check failed: target_blobs.size() == source_layer.blobs_size() (1 vs. 2) Incompatible number of blobs for layer Conv

#41 youngxiao closed 5 years ago
10
Error Encountered. CONCAT: input dimensions dont agree!

#40 salcanmor opened 5 years ago
0
SSDlite: No such file 'output/BoxPredictor_0_BoxEncodingPredictor_depthwise_biases.dat'

#39 moaljazaery opened 5 years ago
0
No such file or directory: 'output/Conv_bn_moving_mean.dat'

#38 biycyr closed 5 years ago
4
Input size issue

#37 biycyr opened 6 years ago
2
which case need reduce_boxes_ to be set

#36 tianylijun opened 6 years ago
0
No max_size for the conv_13/expand related prior box?

#35 d-li14 closed 6 years ago
4
result box has offset for ssdlite_mobilenet_v2_coco net

#34 tianylijun closed 6 years ago
4
Is it possible to add the weights and config file for this model ?

#33 anandcu3 opened 6 years ago
0
demo_caffe in c++ code instead of python

#32 liwei46 closed 6 years ago
2
training loss doesn't decrease after several hundreds steps

#31 Chanbluky opened 6 years ago
8
why it is much slower when i training mobilenetv2-ssdlite than v1,it all most cost one day can only iterate 5000 times,but according to the paper it should much faster,isn't it?

#30 baiboat opened 6 years ago
4
demo caffe bgr -> rgb

#29 snownus opened 6 years ago
0
dump_tensorflow_weights.py with error

#28 he-chen opened 6 years ago
2
use (stride=2 + slice layer) in caffe instead of stride=1 in tensorflow

#27 ujsyehao opened 6 years ago
0
Is there a bug in dump_tensorflow_weights.py for the first box predictor layer ?

#26 seedlingfl opened 6 years ago
2
The loss value didn't drop when it came down to about 7.X?

#25 wangzhe0623 opened 6 years ago
14
Error when creating deploy.caffemodel with two classes using load_caffe_weights.py, ValueError: cannot reshape array of size 157248 into shape (6,576,1,1)

#24 chinthysl opened 6 years ago
3
Why the loss doesn't goes downwhile training?

#23 ZhuLingfeng1993 opened 6 years ago
4
Issue converting retrained ssd_mobilenet_v2 to caffe model

#22 maxritter opened 6 years ago
5
src/caffe/layers/cudnn_conv_layer.cpp:108:58:error:'cudnnSetConvolutionGroupCount' was not declared in this scope

#21 leonshek opened 6 years ago
4
mobilenetv2-ssd 0.25 training

#20 qinghua2016 opened 6 years ago
0
为什么mobileNetV1-ssdlite比mobileNetV1-ssd的mAP提高那么多？

#19 lxg2015 opened 6 years ago
2
Out of Memory?

#18 zserlin opened 6 years ago
3
why the inference time of MobileNetv2 is larger than MobileNetv1????

#17 yuanze-lin opened 6 years ago
1