Deep Neural Network Prediction

Step 1. Genernate random parameters and Run them sequentially : $ python3 collect_data.py -gp -ep -pp -pl pooling -num 10 -shuffle -d 1080ti

Step 2. Data Timeline parser : $ python3 preprocess_data.py -pt -pl pooling -d 1080ti

Step 3. Combine all raw data : $ python3 preprocess_data.py -c -pl pooling -d 1080ti

Step 4. Split raw data to train and test data as performance prediction inputs $ python3 preprocess_data.py -sp -pl pooling -d 1080ti

Step 5. Train Model :

python3 train_model.py -ftf ./utils/Feature_Target/conv_pre.json -log2file 1 -e 1000 -st 400 -sg 0.5 -lf maple -n perfnetA -pd 1080ti -pl convolution -psl pre
    
python3 train_model.py -ftf ./utils/Feature_Target/conv_exe.json -log2file 1 -e 1000 -st 400 -sg 0.5 -lf maple -n perfnetA -pd 1080ti -pl convolution -psl exe
        
python3 train_model.py -ftf ./utils/Feature_Target/conv_post.json -log2file 1 -e 1000 -st 400 -sg 0.5 -lf maple -n perfnetA -pd 1080ti -pl convolution -psl post

Step 6. Generate model csv file :

python3 verify_model.py -gmc --model lenet -b 1

Step 7. Predict model csv file :

python3 verify_model.py -pdm -n perfnetA -d 1080ti -l -eva -lf maple --model lenet -b 1

Or you can use script to predict all models with all batches:

python3 predict_script.py -n perfnetA -d 1080ti -lf maple

Predict the latency time of the deep learning models

Related tags

Overview

Deep Neural Network Prediction

Owner

QAQ

official Pytorch implementation of ICCV 2021 paper FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting.

50-days-of-Statistics-for-Data-Science - This repository consist of a 50-day program

LRBoost is a scikit-learn compatible approach to performing linear residual based stacking/boosting.

Proximal Backpropagation - a neural network training algorithm that takes implicit instead of explicit gradient steps

Unofficial PyTorch code for BasicVSR

Code of our paper "Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning"

A multi-functional library for full-stack Deep Learning. Simplifies Model Building, API development, and Model Deployment.

[SIGGRAPH Asia 2019] Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning

Implementation of TimeSformer, a pure attention-based solution for video classification

BigbrotherBENL - Face recognition on the Big Brother episodes in Belgium and the Netherlands.

Tf alloc - Simplication of GPU allocation for Tensorflow2

Official repo for the work titled "SharinGAN: Combining Synthetic and Real Data for Unsupervised GeometryEstimation"

End-To-End Memory Network using Tensorflow

HSC4D: Human-centered 4D Scene Capture in Large-scale Indoor-outdoor Space Using Wearable IMUs and LiDAR. CVPR 2022

Code release for our paper, "SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo"

Deepfake Scanner by Deepware.

Universal Adversarial Triggers for Attacking and Analyzing NLP (EMNLP 2019)

From Fidelity to Perceptual Quality: A Semi-Supervised Approach for Low-Light Image Enhancement (CVPR'2020)

An LSTM based GAN for Human motion synthesis

Reviving Iterative Training with Mask Guidance for Interactive Segmentation