snailtyan / caffe-model-zoo

caffe pretrained models and prototxt

caffe-model-zoo

Caffe Pretrained Models can download from
Link:http://pan.baidu.com/s/1pL0ZIYJ
Password: xp68

caffe-model-zoo's Issues

query about models

Hi,

I want to ask that are your models all trained on Imagenet data? as I have checked the caffe inception v3 prototxt and it has output size 3. for imagenet it should be 1000. I just want to be sure about it..

I am also getting error while using the model for training. error states as:

math_functions.cu:79] Check failed: error == cudaSuccess (74 vs. 0) misaligned address
*** Check failure stack trace: ***
@ 0x7f4eb42265cd google::LogMessage::Fail()
@ 0x7f4eb4228433 google::LogMessage::SendToLog()
@ 0x7f4eb422615b google::LogMessage::Flush()
@ 0x7f4eb4228e1e google::LogMessageFatal::~LogMessageFatal()
@ 0x7f4eb4a23cba caffe::caffe_gpu_memcpy()
@ 0x7f4eb4a0536d caffe::SyncedMemory::gpu_data()
@ 0x7f4eb484e7b2 caffe::Blob<>::gpu_data()
@ 0x7f4eb4a71130 caffe::BiasLayer<>::Backward_gpu()
@ 0x7f4eb4a3a519 caffe::ScaleLayer<>::Backward_gpu()
@ 0x7f4eb49efde8 caffe::Net<>::BackwardFromTo()
@ 0x7f4eb49efe3f caffe::Net<>::Backward()
@ 0x7f4eb486f384 caffe::Solver<>::Step()
@ 0x7f4eb486ff1a caffe::Solver<>::Solve()
@ 0x40e57b train()
@ 0x40a6fd main
@ 0x7f4eb29bc830 __libc_start_main
@ 0x40b159 _start
@ (nil) (unknown)

Thanks in advance

README Image

Upload the models in google drive. We cant access baidu. Please

resnet50 prototxt和caffemodel并不对应

prototxt中最后的innerproduct层为my-classifier 但是caffemodel中却是原版的fc1000

如果训练数据用原图，那么new_width应该设置多大？

我以前在用googlenet(v1)训练时，是直接用的图像（ImageData）,没有转LMDB。

name: "GoogleNet"
layer {
  name: "data"
  type: "ImageData"
  top: "data"
  top: "label"
  include {
    phase: TRAIN
  }
  transform_param {
    mirror: true
    crop_size: 224
    mean_value: 104
    mean_value: 117
    mean_value: 123
  }
  image_data_param {
    source: "series_train_file_list.txt"
    batch_size: 32
    new_height: 256
    new_width: 256
    shuffle: true
  }
}

想问一下如果用v4训练，仍然用ImageData，crop_size设为299的话，new_width和new_height应该设为多大？

vgg模型是原版吗？

你好，我想问一下VGG16和VGG19里的my-fc8是什么，我用两个网络跑出的概率值都是[0.3334,0.3334,0.3334]，sofmax之前my-fc8的输出都是[0,0,0]

Bug in batch normalization layer

When in train_val.prototxt, use_global_stats should be set false, but in deploy.prototxt, use_global_stats should be set true.

When training models, sometimes loss would stay stable. For example:

I0705 14:57:14.980687   320 solver.cpp:218] Iteration 44 (2.60643 iter/s, 0.383667s/1 iters), loss = 0.263664
I0705 14:57:14.980741   320 solver.cpp:237]     Train net output #0: loss1/loss1 = 0.878881 (* 0.3 = 0.263664 loss)
I0705 14:57:14.980756   320 sgd_solver.cpp:105] Iteration 44, lr = 0.000956
I0705 14:57:15.365164   320 solver.cpp:218] Iteration 45 (2.60146 iter/s, 0.3844s/1 iters), loss = 20.7475
I0705 14:57:15.365226   320 solver.cpp:237]     Train net output #0: loss1/loss1 = 69.1584 (* 0.3 = 20.7475 loss)
I0705 14:57:15.365243   320 sgd_solver.cpp:105] Iteration 45, lr = 0.000955
I0705 14:57:15.759548   320 solver.cpp:218] Iteration 46 (2.53612 iter/s, 0.394303s/1 iters), loss = 0
I0705 14:57:15.759609   320 solver.cpp:237]     Train net output #0: loss1/loss1 = 0 (* 0.3 = 0 loss)
I0705 14:57:15.759624   320 sgd_solver.cpp:105] Iteration 46, lr = 0.000954
I0705 14:57:16.158644   320 solver.cpp:218] Iteration 47 (2.50621 iter/s, 0.39901s/1 iters), loss = 1.63756
I0705 14:57:16.158696   320 solver.cpp:237]     Train net output #0: loss1/loss1 = 5.45853 (* 0.3 = 1.63756 loss)
I0705 14:57:16.158715   320 sgd_solver.cpp:105] Iteration 47, lr = 0.000953
I0705 14:57:16.546782   320 solver.cpp:218] Iteration 48 (2.57693 iter/s, 0.388058s/1 iters), loss = 3.27512
I0705 14:57:16.546838   320 solver.cpp:237]     Train net output #0: loss1/loss1 = 10.9171 (* 0.3 = 3.27512 loss)
I0705 14:57:16.546855   320 sgd_solver.cpp:105] Iteration 48, lr = 0.000952
I0705 14:57:16.930493   320 solver.cpp:218] Iteration 49 (2.60667 iter/s, 0.383631s/1 iters), loss = 25.3822
I0705 14:57:16.930553   320 solver.cpp:237]     Train net output #0: loss1/loss1 = 84.6073 (* 0.3 = 25.3822 loss)
I0705 14:57:16.930568   320 sgd_solver.cpp:105] Iteration 49, lr = 0.000951
I0705 14:57:17.314102   320 solver.cpp:218] Iteration 50 (2.60741 iter/s, 0.383522s/1 iters), loss = 26.201
I0705 14:57:17.314185   320 solver.cpp:237]     Train net output #0: loss1/loss1 = 87.3365 (* 0.3 = 26.201 loss)

Website link does not work?

http://pan.baidu.com/s/1pL0ZIYJ

Link does not work?Where can I get pre trained weights?