ethereon / netscope Goto Github PK

View Code? Open in Web Editor NEW

942.0 942.0 324.0 473 KB

Neural network visualizer

Home Page: http://ethereon.github.io/netscope

CSS 7.67% JavaScript 68.13% HTML 1.83% CoffeeScript 22.38%

netscope's People

Contributors

Stargazers

Watchers

Forkers

gburachas leo-zhou dfhe2004 rollingstone sodabeta7 dgschwend zhec wadefelix neopenx lyken17 iamzhangzhuping wwwanghao out-laws giorking chagge zeyuan1987 wltongxing cleardusk anddywang poweic lucastheis qzhao tsingjinyun beige90 leonzfa gaow0007 hszhao xyy19920105 tonychouzju spillai paradisebb yifan254 bityangke deepcompute yogsin ljczhang zhengzhugithub saltsuger tensor-tang babooppa6 jorisgu erikbjare wlin9 phding kevin0932 zif520 chaofwang rotorliu livst muddlebee echoorchid rlnx liviust raaka1 rsly goldencwcui dengql songxinkai nhzlx zhangwenwen farivergit ngchc bhavesh2g kltsyn anymake lingcc yw155 akalra edwardzeng dreadlord1984 nunuke zgsxwsdxg gclouding c2huc2hu grseb9s melody86 freeape keyky sheng-xiao phecy bazhijing yao-ying suixiaodan ghzhangnj unsky zhenni boluoyu renxiangxiangx zhongxingpeng wh-forker sysau lxzh coocoky aaronjie taozhi2yaoyao mincore derekglk mudelin dwyatte cooliybob

netscope's Issues

Unsupported layer type: 'DepthwiseConvolution'.

Link to deploy.prototxt file

Make it compile with multiple labels

layer {
  name: "image"
  type: "OPData"
  top: "image"
  top: "label"
  top: "label2"
...
}

If you can make it work with this that would be great. my code has multiple tops. More than 2

multi bottom layer(not loss layer) not supported?

name: "net"
layer {
name: "data_layer"
type: "FaceData"
top: "image"
top: "landmark"
face_data_param {
group_size: 5
}
}
layer {
name: "color"
type: "Color"
bottom: "image"
top: "image_gray"
color_param {
color: GRAY
}
}
layer {
name: "warp_face_large"
type: "WarpFace"
bottom: "image_gray"
tottom: "landmark"
top: "image_large"
top: "landmark_large"
warp_face_param {
face_width: 128
face_height: 128
pad_width: 256
pad_height: 256
}
}
layer {
name: "resize"
type: "Resize"
bottom: "image_large"
tottom: "landmark_large"
top: "image_large_resize"
top: "landmark_large_resize"
resize_param {
new_width: 224
new_height: 224
}
}
layer {
name: "caffe"
type: "Caffe"
bottom: "image_large_resize"
top: "result_large"
caffe_param {
model_name: "google_large"
}
}

Implement ceil_mode for pooling layer.

The ceil_mode flag in caffe controls the behavior of pooling output volume. For example, imagine a layer output that is 64 x 64. In caffe, if a convolution id done with kernel_size = 3, pad = 1, stride = 2, the output size is 32 x 32. However, if if a pooling is done with kernel_size = 3, pad = 1, stride = 2, the output size is 33 x 33. This is with ceil_mode: true, the default. With ceil_mode: false, the output size is 32 x 32 (like convolution). In netscope, the output is 33 x 33 regardless of whether ceil_mode: true or ceil_mode: false.

There are a number of BVLC/caffe issues describing the problem:
#1318, #3656, #4252, #4781.
And these pull requests:
#4257, #3057.

The solution seems simple: https://github.com/BVLC/caffe/pull/3057/files

Can this same solution be implemented in netscope?

How do you get the calculation counts for each layers?

Hello, could you please tell me something about how to export the calculation quantity of each layers? especially the pooling and relu layers. Thanks a lot~

The website "http://ethereon.github.io/netscope" is unavailable now.

Is it closed?

Can I export the figure to PDF?

This a great tool!
I am wondering whether it can export the diagram to PDF?

Thanks!

Support visualization reshape and its later layer?

I wanna visualize my caffe prototxt but it seems that netscope doesn't support visualization of reshape and its later layers shape inference? I'm not sure for this point, thus I wanna ask does netscope support reshape layer?

Warning
Can't infer network data shapes. Can't infer output shape of the 'layer27-reshape' layer of type 'Reshape'. Unsupported layer type: 'Reshape'.

Thanks in advance 🙇

Visualize with custom layer

Thanks for sharing nice tool!

As you know, there are a lot of custom layers for various task with caffe.
So I just want to use netscope with the custom layers.
I think, there are some procedure to parse caffe's layer information in custom caffe to be used in netscope.
Could you give any hint for it?

Uncaught ReferenceError: dagreD3 is not defined

”Error Encountered
Uncaught ReferenceError: dagreD3 is not defined“

use chrome，a few days ago,shift+Enter cause such error？
how to fix it?

Question: Network analysis not appearing for certain networks.

Hi there!
Thanks for your tool, it's awesome to visualize networks and get to understand the caffe prototxt a bit further, while porting some of my gists I saw this, in this FCN there is a Network Analysis (check here)

But for a small one like LeNet there is no Network Analysis (check here). I feel I might not yet understand the tool in its completeness so I don't think it's a bug, but had that question bother me for a bit.

Any guidance is appreciated!

Do you have the plan to support caffe2?

Cannot display full of the network

Maybe I met a bug that the netscope cannot display full of my network based on RCNN.

http://ethereon.github.io/netscope/#/gist/eed9d59907f8d223e48dc76d48f92694

declare the `data` variable to DISPLAY the prototxt by URL "http://example.com/netscope/#/url/http://anotherserver/train.prototxt”

netscope/assets/js/netscope.js

Line 2907 in 644824a

return function() {

Hard to navigate large networks

Hard to navigate large networks like this:

net.txt

Some suggestion

It's an awesome work！
It will be better if the label shape could also be infered as the image shape. At now, it is limited to [1], which only caters to the classification application. However, semantic segmentation is a hot topic today where the input label map has the same size as input image. So, the support to the shape infering of label map (not only the image/feature map) will make netscope even much better! :)

UI Request - When hovering - Bolden line and connected layer

Sometimes in very complex networks, its hard to see where the layer we are hovering over is connected to. If you can bolden the line between the connected layer and the hovering layer, and maybe also bolden the connected layer, that would be cool

No support for "Flatten" layer?

It prompts a warning when I try to add a flatten layer to my network:
"Warning"
"Can't infer network data shapes. Can't infer output shape of the 'flatten_1' layer of type 'Flatten'. Unsupported layer type: 'Flatten'."

Unsupported layer type: 'Reshape'

I'm using following prototxt file but it's throwing me a warning:

name: "VGG_ILSVRC_16_layers"

input: "data"
input_shape {
  dim: 1
  dim: 3
  dim: 224
  dim: 224
}

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

layer {
  name: "conv1_1"
  type: "Convolution"
  bottom: "data"
  top: "conv1_1"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu1_1"
  type: "ReLU"
  bottom: "conv1_1"
  top: "conv1_1"
}
layer {
  name: "conv1_2"
  type: "Convolution"
  bottom: "conv1_1"
  top: "conv1_2"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 64
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu1_2"
  type: "ReLU"
  bottom: "conv1_2"
  top: "conv1_2"
}
layer {
  name: "pool1"
  type: "Pooling"
  bottom: "conv1_2"
  top: "pool1"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv2_1"
  type: "Convolution"
  bottom: "pool1"
  top: "conv2_1"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu2_1"
  type: "ReLU"
  bottom: "conv2_1"
  top: "conv2_1"
}
layer {
  name: "conv2_2"
  type: "Convolution"
  bottom: "conv2_1"
  top: "conv2_2"
  param {
    lr_mult: 0
    decay_mult: 0
  }
  param {
    lr_mult: 0
    decay_mult: 0
  }
  convolution_param {
    num_output: 128
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu2_2"
  type: "ReLU"
  bottom: "conv2_2"
  top: "conv2_2"
}
layer {
  name: "pool2"
  type: "Pooling"
  bottom: "conv2_2"
  top: "pool2"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv3_1"
  type: "Convolution"
  bottom: "pool2"
  top: "conv3_1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu3_1"
  type: "ReLU"
  bottom: "conv3_1"
  top: "conv3_1"
}
layer {
  name: "conv3_2"
  type: "Convolution"
  bottom: "conv3_1"
  top: "conv3_2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu3_2"
  type: "ReLU"
  bottom: "conv3_2"
  top: "conv3_2"
}
layer {
  name: "conv3_3"
  type: "Convolution"
  bottom: "conv3_2"
  top: "conv3_3"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 256
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu3_3"
  type: "ReLU"
  bottom: "conv3_3"
  top: "conv3_3"
}
layer {
  name: "pool3"
  type: "Pooling"
  bottom: "conv3_3"
  top: "pool3"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv4_1"
  type: "Convolution"
  bottom: "pool3"
  top: "conv4_1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu4_1"
  type: "ReLU"
  bottom: "conv4_1"
  top: "conv4_1"
}
layer {
  name: "conv4_2"
  type: "Convolution"
  bottom: "conv4_1"
  top: "conv4_2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu4_2"
  type: "ReLU"
  bottom: "conv4_2"
  top: "conv4_2"
}
layer {
  name: "conv4_3"
  type: "Convolution"
  bottom: "conv4_2"
  top: "conv4_3"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu4_3"
  type: "ReLU"
  bottom: "conv4_3"
  top: "conv4_3"
}
layer {
  name: "pool4"
  type: "Pooling"
  bottom: "conv4_3"
  top: "pool4"
  pooling_param {
    pool: MAX
    kernel_size: 2
    stride: 2
  }
}
layer {
  name: "conv5_1"
  type: "Convolution"
  bottom: "pool4"
  top: "conv5_1"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu5_1"
  type: "ReLU"
  bottom: "conv5_1"
  top: "conv5_1"
}
layer {
  name: "conv5_2"
  type: "Convolution"
  bottom: "conv5_1"
  top: "conv5_2"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu5_2"
  type: "ReLU"
  bottom: "conv5_2"
  top: "conv5_2"
}
layer {
  name: "conv5_3"
  type: "Convolution"
  bottom: "conv5_2"
  top: "conv5_3"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  convolution_param {
    num_output: 512
    pad: 1
    kernel_size: 3
  }
}
layer {
  name: "relu5_3"
  type: "ReLU"
  bottom: "conv5_3"
  top: "conv5_3"
}

#========= RPN ============

layer {
  name: "rpn_conv/3x3"
  type: "Convolution"
  bottom: "conv5_3"
  top: "rpn/output"
  param { lr_mult: 1.0 }
  param { lr_mult: 2.0 }
  convolution_param {
    num_output: 512
    kernel_size: 3 pad: 1 stride: 1
    weight_filler { type: "gaussian" std: 0.01 }
    bias_filler { type: "constant" value: 0 }
  }
}
layer {
  name: "rpn_relu/3x3"
  type: "ReLU"
  bottom: "rpn/output"
  top: "rpn/output"
}

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': 21"
  }
}

#========= RCNN ============

layer {
  name: "roi_pool5"
  type: "ROIPooling"
  bottom: "conv5_3"
  bottom: "rois"
  top: "pool5"
  roi_pooling_param {
    pooled_w: 7
    pooled_h: 7
    spatial_scale: 0.0625 # 1/16
  }
}
layer {
  name: "fc6"
  type: "InnerProduct"
  bottom: "pool5"
  top: "fc6"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 4096
  }
}
layer {
  name: "relu6"
  type: "ReLU"
  bottom: "fc6"
  top: "fc6"
}
layer {
  name: "drop6"
  type: "Dropout"
  bottom: "fc6"
  top: "fc6"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "fc7"
  type: "InnerProduct"
  bottom: "fc6"
  top: "fc7"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 4096
  }
}
layer {
  name: "relu7"
  type: "ReLU"
  bottom: "fc7"
  top: "fc7"
}
layer {
  name: "drop7"
  type: "Dropout"
  bottom: "fc7"
  top: "fc7"
  dropout_param {
    dropout_ratio: 0.5
  }
}
layer {
  name: "cls_score"
  type: "InnerProduct"
  bottom: "fc7"
  top: "cls_score"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 21
    weight_filler {
      type: "gaussian"
      std: 0.01
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "bbox_pred"
  type: "InnerProduct"
  bottom: "fc7"
  top: "bbox_pred"
  param {
    lr_mult: 1
  }
  param {
    lr_mult: 2
  }
  inner_product_param {
    num_output: 84
    weight_filler {
      type: "gaussian"
      std: 0.001
    }
    bias_filler {
      type: "constant"
      value: 0
    }
  }
}
layer {
  name: "loss_cls"
  type: "SoftmaxWithLoss"
  bottom: "cls_score"
  bottom: "labels"
  propagate_down: 1
  propagate_down: 0
  top: "loss_cls"
  loss_weight: 1
}
layer {
  name: "loss_bbox"
  type: "SmoothL1Loss"
  bottom: "bbox_pred"
  bottom: "bbox_targets"
  bottom: "bbox_inside_weights"
  bottom: "bbox_outside_weights"
  top: "loss_bbox"
  loss_weight: 1
}

Warning :

Can't infer network data shapes. Can't infer output shape of the 'rpn_cls_score_reshape' layer of type 'Reshape'. Unsupported layer type: 'Reshape'.

How to render a prototxt by url other than github

Atom Package

Thank you for creating this useful tool, it helps me a lot during my work.
Have you thought about deploying netscope as an Atom package?

Input Layer fail to parse shape for multi blobs

For Input layer, if only one blob is fine, but failed when output multi blobs.
For example:
layer {
name: "Input"
type: "Input"
top: "label"
top: "data"
input_param {
shape {
dim: 10
dim: 1
}
shape {
dim: 10
dim: 3
dim: 224
dim: 224
}
}
}

And this result in:

Parsing repeated fields

Hello @ethereon,

For repeated fields in a prototxt file, we may put the values between a pair of bracket, e.g. mean_value: [128, 128, 128]. When trying to visualize it, I got an error:

Error Encountered
Line 22, Column 17: Expected "'", """, "{", key or number but "[" found.

Is it possible to add support for this syntax? Thanks!

PReLU layer

Very useful tool, thanks, but it does not knows PReLU Layer (Shows message: "Unknown Layer: prelu" ), it would be great to append new layer types definitions.

Could I use it in a PC without Internet?

Display layer dimensions

Can you add a mechanism to specify the dimensions of input layers, so that one can see the layer dimensions propagated through the network? That would make netscope an extremely handy tool for designing network architecture (say, when attempting to match deconv layers with the input in autoencoders).

quickstart.html

Thans for this useful tool!
I just want to save the output Netscope.html to local.
But when i open the local Netscope.html, it will jump to quickstart.html. Actually, quickstart don't exist.
can you help me?

Eltwise layer with inplace operation

I have a modified layer EltwiseLayer that do inplace operation in the first bottom data and top data. In this case , this layer can't be shown correctly. Can the code fix for this case, please?

layer {
bottom: "bn4_2"
bottom: "bn4a"
top: "bn4_2"
name: "res4_2"
type: "Eltwise"
}

Is it convenient for you to add "Axpy" (weighted "Eltwise")and "BN" (similiar but not the origin "BatchNorm") layer support?

Many thanks !

Run netscope in localhost

Thanks for the great tool!
I would like to run this on my local machine but doesn't know how. I ran npm install and npm start but didn't know what to do next. How can I do so?