available here: http://kentanabe.github.io/netscope
This is a CNN Analyzer tool, based on Netscope by dgschwend, based on Netscope by ethereon. Netscope is a web-based tool for visualizing neural network topologies. It currently supports UC Berkeley's Caffe framework.
This fork adds support for following layers.
- axpy layer
- broadcast_add layer
- broadcast_mul layer
- DummyData layer
- DepthwiseConvolution layer
- Interp layer
- Pooling layer with round_mode or ceil_mode
- Scale layer with 2 bottom blobs.
- Sigmoid layer
- Slice layer
- Swish layer
- Tanh layer
- Netscope Quick Start Guide
- 🆕 Visualization of DPN-92
- 🆕 Visualization of EfficientNet-b0
- 🆕 Visualization of ERFNet
- 🆕 Visualization of MobileNetV3 with standard convolution
- 🆕 Visualization of MobileNetV3
- 🆕 Visualization of SENet ResNet 50 v1
- 🆕 Visualization of SENet ResNet 50
- 🆕 Visualization of ICNet for Real-Time Semantic Segmentation on High-Resolution Images
- 🆕 Visualization of Densenet121 (round_mode: FLOOR)
- 🆕 Visualization of Densenet121 (ceil_mode: false)
- Visualization of ZynqNet CNN
- Visualization of the Deep Convolutional Neural Network "SqueezeNet"
Released under the MIT license. All included network models provided under their respective licenses.