chuchienshu chuchienshu

## eval_interpsingleframe.py
"""
single frame interpolation.
"""
from time import time
import click
import cv2
import torch
from PIL import Image
import numpy as np
import model

## tmux-cheatsheet.markdown

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                chuchienshu
                / tmux-cheatsheet.markdown
            
            
              Created
              November 4, 2019 02:25
                — forked from ryerh/tmux-cheatsheet.markdown
            
              
                Tmux 快捷键 & 速查表 & 简明教程
              
          
    注意：本文内容适用于 Tmux 2.3 及以上的版本，但是绝大部分的特性低版本也都适用，鼠标支持、VI 模式、插件管理在低版本可能会与本文不兼容。
Tmux 快捷键 & 速查表 & 简明教程

启动新会话：
tmux [new -s 会话名 -n 窗口名]

恢复会话：

  
## l2ab
name: "LtoAB"
layer {
  name: "data"
  type: "Data"
  top: "data"
  include {    phase: TRAIN  }
  transform_param {
   mirror: true
   crop_size: 176
  }

## f2caffe
layer {
  name: "CustomData1"
  type: "CustomData"
  top: "blob0"   # Image 0
  top: "blob1"   # Image 1
  top: "blob2"   # Flow ground truth
  top: "unused1" # Occlusions, remove if not present
  include {
    phase: TRAIN
  }

## flownet2_deploy
input: "img0"
input: "img1"
input_shape {
  dim: 1
  dim: 3
  dim: 255
  dim: 366
}
input_shape {
  dim: 1

## flownet2
layer {
  name: "CustomData1"
  type: "CustomData"
  top: "blob0"   # Image 0
  top: "blob1"   # Image 1
  top: "blob2"   # Flow ground truth
  top: "unused1" # Occlusions, remove if not present
  include {
    phase: TRAIN
  }

## PSPNET
input: "data"
input_dim: 1
input_dim: 3
input_dim: 473
input_dim: 473

layer {
  name: "conv1_1_3x3_s2"
  type: "Convolution"
  bottom: "data"

## flownetS_train
layer {
  name: "CustomData1"
  type: "CustomData"
  top: "blob0"   # Image 0
  top: "blob1"   # Image 1
  top: "blob2"   # Flow ground truth
  top: "unused1" # Occlusions, remove if not present
  include {
    phase: TRAIN
  }

## flownetS
input: "img0"
input: "img1"
input_shape {
  dim: 1
  dim: 3
  dim: 256
  dim: 256
}
input_shape {
  dim: 1
	"""
	single frame interpolation.
	"""
	from time import time
	import click
	import cv2
	import torch
	from PIL import Image
	import numpy as np
	import model
	name: "LtoAB"
	layer {
	name: "data"
	type: "Data"
	top: "data"
	include { phase: TRAIN }
	transform_param {
	mirror: true
	crop_size: 176
	}
	layer {
	name: "CustomData1"
	type: "CustomData"
	top: "blob0" # Image 0
	top: "blob1" # Image 1
	top: "blob2" # Flow ground truth
	top: "unused1" # Occlusions, remove if not present
	include {
	phase: TRAIN
	}
	input: "img0"
	input: "img1"
	input_shape {
	dim: 1
	dim: 3
	dim: 255
	dim: 366
	}
	input_shape {
	dim: 1
	input: "data"
	input_dim: 1
	input_dim: 3
	input_dim: 473
	input_dim: 473

	layer {
	name: "conv1_1_3x3_s2"
	type: "Convolution"
	bottom: "data"