#pragma clang diagnostic push
#pragma ide diagnostic ignored "cppcoreguidelines-narrowing-conversions"
#pragma ide diagnostic ignored "hicpp-signed-bitwise"
#pragma GCC optimize ("Ofast,unroll-loops")
#pragma GCC optimize("no-stack-protector,fast-math")

#include <bits/stdc++.h>
using namespace std;
typedef long long ll;
typedef pair<ll, ll> pll;
typedef pair<int, int> pii;
typedef pair<double, double> pdd;
typedef vector<int> vi;
typedef vector<ll> vll;
typedef vector<double> vd;
typedef vector<string> vs;
typedef vector<vi> vvi;
typedef vector<vvi> vvvi;
typedef vector<vll> vvll;
typedef vector<vvll> vvvll;
typedef vector<pii> vpii;
typedef vector<vpii> vvpii;
typedef vector<pll> vpll;
typedef vector<vpll> vvpll;
typedef vector<pdd> vpdd;
typedef vector<vd> vvd;
#define yn(ans) printf("%s\n", (ans)?"Yes":"No");
#define YN(ans) printf("%s\n", (ans)?"YES":"NO");
template<class T> bool chmax(T &a, T b) {
	if (a >= b) return false;
	a = b; return true;
}
template<class T> bool chmin(T &a, T b) {
	if (a <= b) return false;
	a = b; return true;
}
#define FOR(i, s, e, t) for ((i) = (s); (i) < (e); (i) += (t)) 
#define REP(i, e) for (int i = 0; i < (e); ++i) 
#define REP1(i, s, e) for (int i = (s); i < (e); ++i)
#define RREP(i, e) for (int i = (e); i >= 0; --i)
#define RREP1(i, e, s) for (int i = (e); i >= (s); --i)
#define all(v) v.begin(), v.end()
#define pb push_back
#define qb pop_back
#define pf push_front
#define qf pop_front
#define maxe max_element
#define mine min_element
ll inf = 1e18;
#define DEBUG printf("%d\n", __LINE__); fflush(stdout);
template<class T> void print(vector<T> &v, bool withSize = false) {
	if (withSize) cout << v.size() << endl;
	REP(i, v.size()) cout << v[i] << " "; 
	cout << endl;
}
mt19937_64 rng((unsigned int) chrono::steady_clock::now().time_since_epoch().count());

int __FAST_IO__ = []() {
	std::ios::sync_with_stdio(0);
	std::cin.tie(0);
	std::cout.tie(0);
	return 0;
}();

#define TESTS int t; cin >> t; while (t--)
#define TEST 
int main() {
    TEST {
    	int H, W;
    	cin >> H >> W;
    	vvi v(H, vi(W)), c(H, vi(W, -1));
    	REP(i, H) REP(j, W) cin >> v[i][j];
    	vvi moves = {{1, 0}, {-1, 0}, {0, 1}, {0, -1}};
    	typedef array<int, 3> node;
    	priority_queue<node, vector<node>, greater<node>> pq, pq2;
    	
    	auto upd = [&](priority_queue<node, vector<node>, greater<node>> &q, int color, int x, int y) {
    	//	printf("paint %d %d %d\n", x, y, color);
    		c[x][y] = color;
    		for (auto &m: moves) {
    			int nx = x + m[0], ny = y + m[1];
    			if (nx >= 0 && nx < H && ny >= 0 && ny < W) {
    				if (c[nx][ny] == -1) q.push({v[nx][ny], nx, ny});
    				else if (c[nx][ny] != color) throw 1;
    			}
    		}	
    	};
    	
    	upd(pq, 1, 0, 0);
    	upd(pq2, 0, H - 1, W - 1);
    	int ans = 0;
    	while (1) {
    		try {
    			while (1) {
	    			if (pq.empty()) goto finish;
	    			auto p = pq.top();
	    			pq.pop();
	    			int x = p[1], y = p[2];
	    			//printf("q1 %d %d %d\n", x, y, c[x][y]);
	    			if (c[x][y] == -1) {
	    				ans++;
	    				upd(pq, 1, x, y);
    					
    					break;
	    			}
    			}
    			
	    			
    		} catch (int e) {
    			break;
    		}
    		try {
    			while (1) {
	    			if (pq2.empty()) goto finish;
	    			auto p = pq2.top();
	    			pq2.pop();
	    			int x = p[1], y = p[2];
	    			//printf("q2 %d %d %d\n", x, y, c[x][y]);
	    			if (c[x][y] == -1) {
	    				ans++;
	    				upd(pq2, 0, x, y);
    					break;
	    			}
    			}
    		} catch (int e) {
    			break;
    		}
    	}
    	finish:
    	printf("%d\n", ans);
    }
    
    return 0;
}