File size: 11,553 Bytes
8efb28e | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 | #include "mtmd-debug.h"
#include "arg.h"
#include "debug.h"
#include "log.h"
#include "common.h"
#include "llama.h"
#include "ggml.h"
#include "mtmd.h"
#include "mtmd-helper.h"
#include <vector>
#include <cmath>
#include <limits.h>
#include <cinttypes>
#include <clocale>
// INTERNAL TOOL FOR DEBUGGING PURPOSES ONLY
// NOT INTENDED FOR PUBLIC USE
static void show_additional_info(int /*argc*/, char ** argv) {
LOG(
"Internal debugging tool for mtmd; See mtmd-debug.md for the pytorch equivalent code\n"
"Note: we repurpose some args from other examples, they will have different meaning here\n"
"\n"
"Usage: %s -m <model> --mmproj <mmproj> -p <mode> -n <size> --image <image> --audio <audio>\n"
"\n"
" -n <size>: number of pixels per edge for image (always square image), or number of samples for audio\n"
"\n"
" -p \"encode\" (debugging encode pass, default case):\n"
" --image can be:\n"
" \"white\", \"black\", \"gray\": filled 1.0f, 0.0f and 0.5f respectively\n"
" \"red\", \"green\", \"blue\": filled with respective colors\n"
" \"cb\": checkerboard pattern, alternate 1.0f and 0.0f\n"
" \"rainbow\": raspberry-pi-like rainbow pattern\n"
" --audio can be:\n"
" \"one\", \"zero\", \"half\": filled 1.0f, 0.0f and 0.5f respectively\n"
" \"1010\": checkerboard pattern, alternate 1.0f and 0.0f\n"
"\n"
" -p \"preproc\" (debugging preprocessing pass):\n"
" --image can be:\n"
" \"white\", \"black\", \"gray\": filled image with respective colors\n"
" \"cb\": checkerboard pattern\n"
" --audio can be:\n"
" \"one\", \"zero\", \"half\": filled 1.0f, 0.0f and 0.5f respectively\n"
" \"440\": sine wave with 440 Hz frequency\n"
"\n",
argv[0]
);
}
int main(int argc, char ** argv) {
std::setlocale(LC_NUMERIC, "C");
ggml_time_init();
common_params params;
common_init();
if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_MTMD, show_additional_info)) {
return 1;
}
mtmd_helper_log_set(common_log_default_callback, nullptr);
if (params.mmproj.path.empty()) {
show_additional_info(argc, argv);
LOG_ERR("ERR: Missing --mmproj argument\n");
return 1;
}
ggml_backend_load_all();
LOG_INF("%s: loading model: %s\n", __func__, params.model.path.c_str());
mtmd::context_ptr ctx_mtmd;
common_init_result_ptr llama_init;
common_debug_cb_user_data cb_data;
llama_init = common_init_from_params(params);
{
auto * model = llama_init->model();
const char * clip_path = params.mmproj.path.c_str();
mtmd_context_params mparams = mtmd_context_params_default();
mparams.use_gpu = params.mmproj_use_gpu;
mparams.print_timings = true;
mparams.n_threads = params.cpuparams.n_threads;
mparams.flash_attn_type = params.flash_attn_type;
mparams.warmup = params.warmup;
mparams.image_min_tokens = params.image_min_tokens;
mparams.image_max_tokens = params.image_max_tokens;
{
// always enable debug callback
mparams.cb_eval_user_data = &cb_data;
mparams.cb_eval = common_debug_cb_eval;
}
ctx_mtmd.reset(mtmd_init_from_file(clip_path, model, mparams));
if (!ctx_mtmd.get()) {
LOG_ERR("Failed to load vision model from %s\n", clip_path);
exit(1);
}
}
std::string input;
int32_t inp_size = params.n_predict;
if (params.image.empty()) {
LOG_ERR("ERR: At least one of --image or --audio must be specified\n");
return 1;
}
if (inp_size <= 0) {
LOG_ERR("ERR: Invalid size specified with -n, must be greater than 0\n");
return 1;
}
input = params.image[0];
if (params.prompt.empty() || params.prompt == "encode") {
std::vector<std::vector<float>> image;
std::vector<float> samples;
if (input == "black") {
for (int i = 0; i < inp_size; ++i) {
auto row = std::vector<float>(inp_size * 3, 0.0f);
image.push_back(row);
}
} else if (input == "white") {
for (int i = 0; i < inp_size; ++i) {
auto row = std::vector<float>(inp_size * 3, 1.0f);
image.push_back(row);
}
} else if (input == "gray") {
for (int i = 0; i < inp_size; ++i) {
auto row = std::vector<float>(inp_size * 3, 0.5f);
image.push_back(row);
}
} else if (input == "cb") {
for (int i = 0; i < inp_size; ++i) {
auto row = std::vector<float>(inp_size * 3, 0.0f);
image.push_back(row);
}
for (int y = 0; y < inp_size; ++y) {
for (int x = 0; x < inp_size; ++x) {
float v = ((x + y) % 2) ? 0.0f : 1.0f;
image[y][x * 3 + 0] = v;
image[y][x * 3 + 1] = v;
image[y][x * 3 + 2] = v;
}
}
} else if (input == "red") {
for (int i = 0; i < inp_size; ++i) {
auto row = std::vector<float>(inp_size * 3, 0.0f);
for (int j = 0; j < inp_size; ++j) {
row[j * 3 + 0] = 1.0f; // R channel
}
image.push_back(row);
}
} else if (input == "green") {
for (int i = 0; i < inp_size; ++i) {
auto row = std::vector<float>(inp_size * 3, 0.0f);
for (int j = 0; j < inp_size; ++j) {
row[j * 3 + 1] = 1.0f; // G channel
}
image.push_back(row);
}
} else if (input == "blue") {
for (int i = 0; i < inp_size; ++i) {
auto row = std::vector<float>(inp_size * 3, 0.0f);
for (int j = 0; j < inp_size; ++j) {
row[j * 3 + 2] = 1.0f; // B channel
}
image.push_back(row);
}
} else if (input == "rainbow") {
for (int i = 0; i < inp_size; ++i) {
image.push_back(std::vector<float>(inp_size * 3, 0.0f));
}
float cx = inp_size / 2.0f;
float cy = inp_size / 2.0f;
float max_dist = std::sqrt(cx * cx + cy * cy);
for (int y = 0; y < inp_size; ++y) {
for (int x = 0; x < inp_size; ++x) {
float dx = x - cx;
float dy = y - cy;
float hue = std::atan2(dy, dx) / (2.0f * 3.14159265f);
if (hue < 0) hue += 1.0f;
float sat = std::sqrt(dx * dx + dy * dy) / max_dist;
if (sat > 1.0f) sat = 1.0f;
float h6 = hue * 6.0f;
int i6 = (int)h6;
float f = h6 - i6;
float p = 1.0f - sat;
float q = 1.0f - sat * f;
float t = 1.0f - sat * (1.0f - f);
float r, g, b;
switch (i6 % 6) {
case 0: r=1; g=t; b=p; break;
case 1: r=q; g=1; b=p; break;
case 2: r=p; g=1; b=t; break;
case 3: r=p; g=q; b=1; break;
case 4: r=t; g=p; b=1; break;
default: r=1; g=p; b=q; break;
}
image[y][x * 3 + 0] = r;
image[y][x * 3 + 1] = g;
image[y][x * 3 + 2] = b;
}
}
} else if (input == "one") {
samples = std::vector<float>(inp_size, 1.0f);
} else if (input == "zero") {
samples = std::vector<float>(inp_size, 0.0f);
} else if (input == "half") {
samples = std::vector<float>(inp_size, 0.5f);
} else if (input == "1010") {
samples.resize(inp_size);
for (int i = 0; i < inp_size; ++i) {
samples[i] = (i % 2) ? 0.0f : 1.0f;
}
} else {
LOG_ERR("ERR: Invalid input specified with --image/--audio\n");
show_additional_info(argc, argv);
return 1;
}
// run encode pass
LOG_INF("Running encode pass for input type: %s\n", input.c_str());
if (samples.size() > 0) {
LOG_INF("Input audio with %zu samples, type: %s\n", samples.size(), input.c_str());
mtmd_debug_encode_audio(ctx_mtmd.get(), samples);
} else {
LOG_INF("Input image with dimensions %d x %d, type: %s\n", inp_size, inp_size, input.c_str());
mtmd_debug_encode_image(ctx_mtmd.get(), image);
}
} else if (params.prompt == "preproc") {
std::vector<uint8_t> rgb_values;
std::vector<float> pcm_samples;
if (input == "black") {
rgb_values = std::vector<uint8_t>(inp_size * inp_size * 3, 0);
} else if (input == "white") {
rgb_values = std::vector<uint8_t>(inp_size * inp_size * 3, 255);
} else if (input == "gray") {
rgb_values = std::vector<uint8_t>(inp_size * inp_size * 3, 128);
} else if (input == "cb") {
rgb_values.resize(inp_size * inp_size * 3);
for (int y = 0; y < inp_size; ++y) {
for (int x = 0; x < inp_size; ++x) {
uint8_t v = ((x + y) % 2) ? 0 : 255;
rgb_values[(y * inp_size + x) * 3 + 0] = v;
rgb_values[(y * inp_size + x) * 3 + 1] = v;
rgb_values[(y * inp_size + x) * 3 + 2] = v;
}
}
} else if (input == "one") {
pcm_samples = std::vector<float>(inp_size, 1.0f);
} else if (input == "zero") {
pcm_samples = std::vector<float>(inp_size, 0.0f);
} else if (input == "half") {
pcm_samples = std::vector<float>(inp_size, 0.5f);
} else if (input == "440") {
pcm_samples.resize(inp_size);
float freq = 440.0f;
float sample_rate = mtmd_get_audio_sample_rate(ctx_mtmd.get());
float pi = 3.14159265f;
for (int i = 0; i < inp_size; ++i) {
pcm_samples[i] = sinf(2 * pi * freq * i / sample_rate);
}
} else {
LOG_ERR("ERR: Invalid input specified with --image/--audio\n");
show_additional_info(argc, argv);
return 1;
}
// run preprocessing pass
LOG_INF("Running preprocessing pass for input type: %s\n", input.c_str());
if (pcm_samples.size() > 0) {
LOG_INF("Input audio with %zu samples, type: %s\n", pcm_samples.size(), input.c_str());
mtmd_debug_preprocess_audio(ctx_mtmd.get(), pcm_samples);
} else {
LOG_INF("Input image with dimensions %d x %d, type: %s\n", inp_size, inp_size, input.c_str());
mtmd_debug_preprocess_image(ctx_mtmd.get(), rgb_values, inp_size, inp_size);
}
} else {
LOG_ERR("ERR: Invalid mode specified with -p\n");
show_additional_info(argc, argv);
return 1;
}
return 0;
}
|