##VGG19 model for Keras
This is the Keras model of the 19-layer network used by the VGG team in the ILSVRC-2014 competition.
It has been obtained by directly converting the Caffe model provived by the authors.
Details about the network architecture can be found in the following arXiv paper:
Very Deep Convolutional Networks for Large-Scale Image Recognition
K. Simonyan, A. Zisserman
##VGG19 model for Keras
This is the Keras model of the 19-layer network used by the VGG team in the ILSVRC-2014 competition.
It has been obtained by directly converting the Caffe model provived by the authors.
Details about the network architecture can be found in the following arXiv paper:
Very Deep Convolutional Networks for Large-Scale Image Recognition
K. Simonyan, A. Zisserman
| #!/bin/bash | |
| NVIDIA_DRIVER_VERSION=352.63 | |
| NVIDIA_CUDA_VERSION=7.5 | |
| NVIDIA_CUDA_FULL_VERSION=7.5.18 | |
| sudo yum update -y | |
| sudo yum groupinstall -y "Development tools" | |
| sudo yum install kernel-devel-`uname -r` |
| motion | description |
|---|---|
| h | Count characters left |
| l | Count characters right |
| ^ | To the first character of the line |
| $ | To the last character of the line |
| f<char> | To the counth character occurrence to the right. F<char> to the counth character occurrence to the left |
| t<char> | To 1 character just before the counth character occurrence to the right |
Motion, keyboard commands and shortcuts for VI Improved
| #!/bin/bash | |
| ## This gist contains step by step instructions to install cuda v9.0 and cudnn 7.2 in ubuntu 18.04 | |
| ### steps #### | |
| # verify the system has a cuda-capable gpu | |
| # download and install the nvidia cuda toolkit and cudnn | |
| # setup environmental variables | |
| # verify the installation | |
| ### |
| from functools import lru_cache | |
| @lru_cache(None) | |
| def fib_top_down(n): | |
| if n==0: return 0 | |
| if n==1: return 1 | |
| return fib_top_down(n-1)+fib_top_down(n-2) | |
| def fib_bottom_up(n): | |
| if n==0: return 0 | |
| if n==1: return 1 |
| # dp bottom up | |
| class Solution: | |
| def numWays(self, steps: int, arrLen: int) -> int: | |
| MOD = 1000000007 | |
| if arrLen == 1:return 1 | |
| n = min(251, arrLen) | |
| dp = [[0 for x in range(steps+1)] for y in range(n)] | |
| dp[0][0] = 1 | |
| for i in range(1, steps+1): | |
| dp[0][i] = (dp[0][i-1]+dp[1][i-1]) % MOD |
| """ | |
| DP top down | |
| dp(pos, step) = sum(dp(pos+1, step-1), dp(pos-1, step-1), dp(pos, step-1)) | |
| """ | |
| from functools import lru_cache | |
| class Solution: | |
| def numWays(self, steps: int, arrLen: int) -> int: | |
| MOD = 10**9 + 7 | |
| @lru_cache(None) | |
| def dp(pos, steps): |
| class Solution: | |
| def numWays(self, steps: int, arrLen: int) -> int: | |
| MOD = 10**9 + 7 | |
| POS = min(steps//2+1, arrLen) | |
| dp = collections.defaultdict(int) | |
| def bfs(pos, step): | |
| cur_level = {(pos, step)} | |
| dp[(pos, step)] = 1 | |
| while cur_level: | |
| nxt_level = set() |