mahyarnajibi/ssh issues and pull requests

#63 - Ssh

Issue - State: open - Opened by Jayden69420 over 4 years ago

#62 - Instructions for running demo

Issue - State: open - Opened by rabysam28 over 4 years ago - 1 comment

#61 - Traceback (most recent call last): File "main_train.py", line 57, in <module> imdb= get_imdb(args.db_name) File "lib/datasets/factory.py", line 18, in get_imdb return sets[name]() File "lib/datasets/factory.py", line 11, in <lambda> sets[name] = (lambda split=split: wider(split)) File "lib/datasets/wider.py", line 49, in init n_anno = int(annos[count]) ValueError: invalid literal for int() with base 10: '0--Parade/0_Parade_Parade_0_630.jpg\n

Issue - State: open - Opened by ImPiyushK over 5 years ago

#60 - ValueError: invalid literal for int() with base 10: '0--Parade/0_Parade_Parade_0_630.jpg\n'

Issue - State: open - Opened by yanjj16 over 5 years ago - 2 comments

#59 - 图片预处理问题

Issue - State: open - Opened by westnight over 5 years ago

#58 - CPU demo running

Issue - State: open - Opened by Jadranko95 almost 6 years ago

#57 - Network Speed

Issue - State: open - Opened by chungyau97 almost 6 years ago

#56 - i have datasets like voc ,how can i transform it to ’widerface‘ in order to train my own datasets

Issue - State: open - Opened by LU-K-Brant almost 6 years ago

#55 - Testing API is MATLAB code, but when i debug in main-test.py, I can't find the posion to call matlab API

Issue - State: open - Opened by graycrown about 6 years ago - 1 comment

#54 - ImportError: No module named cpu_nms

Issue - State: open - Opened by graycrown about 6 years ago - 12 comments

#53 - how to find landmark with SSH detector ?

Issue - State: open - Opened by luan1412167 about 6 years ago

#51 - tensorflow version for SSH?

Issue - State: closed - Opened by aa12356jm about 6 years ago - 2 comments

#50 - why the iteration is 21K ?

Issue - State: open - Opened by pyupcgithub about 6 years ago - 3 comments

#49 - About training?

Issue - State: open - Opened by bleakie about 6 years ago

#48 - About train my own data

Issue - State: open - Opened by pyupcgithub about 6 years ago - 1 comment

#47 - About the inconsistent between the train_ssh.prototxt and the test_ssh.prototxt

Issue - State: closed - Opened by powerlic about 6 years ago

#46 - SSH+Pyramid ? the default setting is without an imaege pyramid?

Issue - State: open - Opened by pyupcgithub about 6 years ago - 3 comments

#45 - What's the exact training batch size using default setting?

Issue - State: closed - Opened by pyupcgithub about 6 years ago - 5 comments

#44 - python demo.py error!!!

Issue - State: open - Opened by songyy137222 over 6 years ago - 7 comments

#43 - No face frame detected

Issue - State: closed - Opened by Cherry2410 over 6 years ago

#42 - why many faces of animals are deteted?

Issue - State: open - Opened by hongminli over 6 years ago

#41 - Error for unzip the model

Issue - State: open - Opened by sleepingidea over 6 years ago - 5 comments

#40 - FDDB dataset

Issue - State: open - Opened by foralliance over 6 years ago - 2 comments

#39 - Could this run on CPU?

Issue - State: open - Opened by exnx over 6 years ago - 2 comments

#38 - ahout anchor_target_layer.py

Issue - State: open - Opened by foralliance over 6 years ago

#37 - about bbox_transform.py

Issue - State: open - Opened by foralliance over 6 years ago

#36 - how can I run the demo on cpu?

Issue - State: closed - Opened by junedgar over 6 years ago - 6 comments

#35 - can't load VGG16.caffemodel

Issue - State: closed - Opened by junedgar over 6 years ago - 3 comments

#34 - Can ssh for one class object detection?

Issue - State: open - Opened by wzc118 over 6 years ago - 1 comment

#33 - type object 'NCCL' has no attribute 'new_uid'

Issue - State: closed - Opened by LaviLiu over 6 years ago - 2 comments

#32 - How to calculate AP with a different IoU?

Issue - State: closed - Opened by taotaoorange over 6 years ago

#31 - Feature map fusion without channel reduction?

Issue - State: closed - Opened by ghost over 6 years ago - 6 comments

#30 - test pretrain model

Issue - State: closed - Opened by billhyde over 6 years ago - 4 comments

#29 - download pretrain model error

Issue - State: closed - Opened by billhyde over 6 years ago - 4 comments

#28 - adding another detection layer on conv3_3

Issue - State: closed - Opened by ghost over 6 years ago - 1 comment

#27 - Test the model using video

Issue - State: open - Opened by pangyanhui923 over 6 years ago - 1 comment

#26 - How to calculate AP? I can't find it.

Issue - State: open - Opened by xinyaoguo over 6 years ago - 3 comments

#25 - SSH for multi class classification

Issue - State: open - Opened by abhishekvahadane almost 7 years ago - 5 comments

#24 - Visualization of training curves

Issue - State: open - Opened by abhishekvahadane almost 7 years ago

#23 - How to config training on one GPU

Issue - State: closed - Opened by liuwuliuyun almost 7 years ago - 5 comments

#22 - Had anyone come across the overlap box hasn't been removed?

Issue - State: open - Opened by Jolntu almost 7 years ago - 8 comments

#21 - caffe compiling error SmoothL1LossParameter

Issue - State: open - Opened by richipower almost 7 years ago - 1 comment

#20 - The model released seems go wrong;

Issue - State: closed - Opened by jianyin2016 almost 7 years ago - 1 comment

#19 - Link to download pretained model is broken

Issue - State: closed - Opened by hsienkaikuo almost 7 years ago - 5 comments

#18 - GPU configuration for SSH

Issue - State: closed - Opened by bockholt about 7 years ago - 6 comments

#17 - Can we remove `ohem` branches in the train net?

Issue - State: open - Opened by luoyetx about 7 years ago - 4 comments

#16 - Several bugs may exist

Issue - State: closed - Opened by mxmxlwlw about 7 years ago - 5 comments

#15 - compile caffe error

Issue - State: open - Opened by nerddd about 7 years ago - 1 comment

#14 - How to definite the Concat layer with three repeated propagate_down=false in python?

Issue - State: open - Opened by whcjb about 7 years ago

#13 - About the GPU memory?

Issue - State: open - Opened by hangkaitan about 7 years ago - 2 comments

#12 - ._caffe not found

Issue - State: open - Opened by vaishnavm217 about 7 years ago - 2 comments

#11 - can not reproduce the detection result in paper for WIDER hard subset

Issue - State: closed - Opened by kiloeye about 7 years ago - 5 comments

#10 - performance drops when i make some changes in SSH

Issue - State: closed - Opened by takecareofbigboss about 7 years ago - 6 comments

#9 - How about other Networks？

Issue - State: open - Opened by dkjsh about 7 years ago - 3 comments

#8 - FDDB dataset precision problem， got a lower precision

Issue - State: closed - Opened by whcjb about 7 years ago - 4 comments

#7 - How much GPU will be needed to run the demo.py?

Issue - State: closed - Opened by yanzi6969 about 7 years ago - 4 comments

#6 - demo.py crashes

Issue - State: closed - Opened by siebenkopf over 7 years ago - 9 comments

#5 - what's the conv5_128_crop for?

Issue - State: closed - Opened by julysix over 7 years ago - 2 comments

#4 - the parameter when evaluate FDDB.

Issue - State: closed - Opened by ForestWang over 7 years ago - 1 comment

#3 - Could i debug anchor_target_layer.py by pdb?

Issue - State: open - Opened by takecareofbigboss over 7 years ago - 3 comments

#2 - the caffemodel trained by your code is bigger than you release

Issue - State: open - Opened by zhangyunming over 7 years ago - 4 comments

#1 - Message type "caffe.LayerParameter" has no field named "smooth_l1_loss_param".

Issue - State: closed - Opened by lianlengyunyu over 7 years ago - 3 comments

GitHub / mahyarnajibi/ssh issues and pull requests