The original weights of some Caffe models, ported to PyTorch.

Last update: Nov 04, 2022

Related tags

Overview

pytorch-caffe-models

This repo contains the original weights of some Caffe models, ported to PyTorch. Currently there are:

GoogLeNet (Going Deeper with Convolutions):

The GoogLeNet model in torchvision was trained from scratch by the PyTorch team with very different data preprocessing and has very differently scaled internal activations, which can be important when using the model as a feature extractor.

There is also a tool (dump_caffe_model.py) to dump Caffe model weights to a more portable format (pickles of NumPy arrays), which requires Caffe and its Python 3 bindings to be installed. A script to compute validation loss and accuracy (validate.py) is also included (the ImageNet validation set can be obtained from Academic Torrents).

Usage

Basic usage

This outputs logits for 1000 ImageNet classes for a black (zero) input image:

import pytorch_caffe_models

model, transform = pytorch_caffe_models.googlenet_bvlc()

model(transform(torch.zeros([1, 3, 224, 224])))

The original models were trained with BGR input data in the range 0-255, which had then been scaled to zero mean but not unit standard deviation. The model-specific transform returned by the pretrained model creation function expects RGB input data in the range 0-1 and it will differentiably rescale the input and convert from RGB to BGR.

Feature extraction

Using the new torchvision feature extraction utility:

from torchvision.models import feature_extraction

layer_names = feature_extraction.get_graph_node_names(model)[1]

Then pick your favorite layer (we can use inception_4c.conv_5x5)

model.eval().requires_grad_(False)
extractor = feature_extraction.create_feature_extractor(model, {'inception_4c.conv_5x5': 'out'})

input_image = torch.randn([1, 3, 224, 224]) / 50 + 0.5
input_image.requires_grad_()

features = extractor(transform(input_image))['out']
loss = -torch.sum(features**2) / 2
loss.backward()

input_image now has its .grad attribute populated and you can normalize and descend this gradient for DeepDream or other feature visualization methods. (The BVLC GoogLeNet model was the most popular model used for DeepDream.)

You might also like...

A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

Use this instead: https://github.com/facebookresearch/maskrcnn-benchmark A Pytorch Implementation of Detectron Example output of e2e_mask_rcnn-R-101-F

2.8k Dec 29, 2022

A python code to convert Keras pre-trained weights to Pytorch version

Weights_Keras_2_Pytorch 最近想在Pytorch项目里使用一下谷歌的NIMA，但是发现没有预训练好的pytorch权重，于是整理了一下将Keras预训练权重转为Pytorch的代码，目前是支持Keras的Conv2D, Dense, DepthwiseConv2D, Batch

2 Dec 16, 2021

DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight or group of weights, in order to achieve a given trade-off between model size and accuracy.

Differentiable Model Compression via Pseudo Quantization Noise DiffQ performs differentiable quantization using pseudo quantization noise. It can auto

145 Dec 30, 2022

Code for Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights

Piggyback: https://arxiv.org/abs/1801.06519 Pretrained masks and backbones are available here: https://uofi.box.com/s/c5kixsvtrghu9yj51yb1oe853ltdfz4q

165 Nov 22, 2022

Vanilla and Prototypical Networks with Random Weights for image classification on Omniglot and mini-ImageNet. Made with Python3.

vanilla-rw-protonets-project Vanilla Prototypical Networks and PNs with Random Weights for image classification on Omniglot and mini-ImageNet. Made wi

8 Aug 31, 2022

The original weights of some Caffe models, ported to PyTorch.

Related tags

Overview

pytorch-caffe-models

Usage

Basic usage

Feature extraction

You might also like...

A pytorch implementation of Detectron. Both training from scratch and inferring directly from pretrained Detectron weights are available.

A python code to convert Keras pre-trained weights to Pytorch version

DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight or group of weights, in order to achieve a given trade-off between model size and accuracy.

Code for Piggyback: Adapting a Single Network to Multiple Tasks by Learning to Mask Weights

Vanilla and Prototypical Networks with Random Weights for image classification on Omniglot and mini-ImageNet. Made with Python3.

Voice of Pajlada with model and weights.

High level network definitions with pre-trained weights in TensorFlow

A program that can analyze videos according to the weights you select

Inflated i3d network with inception backbone, weights transfered from tensorflow

Releases(models-2)

models-2(Jan 17, 2022)

Owner

Katherine Crowson

Use evolutionary algorithms instead of gridsearch in scikit-learn

This repo is a C++ version of yolov5_deepsort_tensorrt. Packing all C++ programs into .so files, using Python script to call C++ programs further.

A pyparsing-based library for parsing SOQL statements

Official PyTorch implementation of the paper: DeepSIM: Image Shape Manipulation from a Single Augmented Training Sample

This repository contains several image-to-image translation models, whcih were tested for RGB to NIR image generation. The models are Pix2Pix, Pix2PixHD, CycleGAN and PointWise.

PyTorch implementation of Tacotron speech synthesis model.

Official pytorch implementation of the AAAI 2021 paper Semantic Grouping Network for Video Captioning

3D HourGlass Networks for Human Pose Estimation Through Videos

Adjust Decision Boundary for Class Imbalanced Learning

PyTorch original implementation of Cross-lingual Language Model Pretraining.

tensorrt int8 量化yolov5 4.0 onnx模型

Object-aware Contrastive Learning for Debiased Scene Representation

Global Filter Networks for Image Classification

Web-interface + rest API for classification and regression (https://jeff1evesque.github.io/machine-learning.docs)

Code for "Multi-Compound Transformer for Accurate Biomedical Image Segmentation"

Weakly- and Semi-Supervised Panoptic Segmentation (ECCV18)

Optimizing synthesizer parameters using gradient approximation

Submodular Subset Selection for Active Domain Adaptation (ICCV 2021)

Roadmap to becoming a machine learning engineer in 2020

Contains supplementary materials for reproduce results in HMC divergence time estimation manuscript