unet.ja.json

{
 "<h1>U-Net model for <a href=\"index.html\">Denoising Diffusion Probabilistic Models (DDPM)</a></h1>\n<p>This is a <a href=\"../../unet/index.html\">U-Net</a> based model to predict noise <span translate=no>_^_0_^_</span>.</p>\n<p>U-Net is a gets it&#x27;s name from the U shape in the model diagram. It processes a given image by progressively lowering (halving) the feature map resolution and then increasing the resolution. There are pass-through connection at each resolution.</p>\n<p><span translate=no>_^_1_^_</span></p>\n<p>This implementation contains a bunch of modifications to original U-Net (residual blocks, multi-head attention)  and also adds time-step embeddings <span translate=no>_^_2_^_</span>.</p>\n": "<h1><a href=\"index.html\">\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb (DDPM</a>) \u7528\u306e U-Net \u30e2\u30c7\u30eb</h1>\n<p>\u3053\u308c\u306f <a href=\"../../unet/index.html\">U-Net</a> <span translate=no>_^_0_^_</span> \u30d9\u30fc\u30b9\u306e\u30ce\u30a4\u30ba\u4e88\u6e2c\u30e2\u30c7\u30eb\u3067\u3059\u3002</p>\n<p>U-Net\u306f\u3001\u30e2\u30c7\u30eb\u56f3\u306eU\u5b57\u5f62\u306b\u3061\u306a\u3093\u3067\u540d\u4ed8\u3051\u3089\u308c\u307e\u3057\u305f\u3002\u7279\u5fb4\u30de\u30c3\u30d7\u306e\u89e3\u50cf\u5ea6\u3092\u6bb5\u968e\u7684\u306b\u4f4e\u304f (\u534a\u5206\u306b)\u3001\u6b21\u306b\u89e3\u50cf\u5ea6\u3092\u4e0a\u3052\u308b\u3053\u3068\u306b\u3088\u3063\u3066\u3001\u7279\u5b9a\u306e\u753b\u50cf\u3092\u51e6\u7406\u3057\u307e\u3059\u3002\u5404\u89e3\u50cf\u5ea6\u306b\u306f\u30d1\u30b9\u30b9\u30eb\u30fc\u63a5\u7d9a\u304c\u3042\u308a\u307e\u3059</p>\u3002\n<p><span translate=no>_^_1_^_</span></p>\n<p>\u3053\u306e\u5b9f\u88c5\u306b\u306f\u3001\u30aa\u30ea\u30b8\u30ca\u30eb\u306e U-Net \u306b\u591a\u6570\u306e\u5909\u66f4\uff08\u6b8b\u7559\u30d6\u30ed\u30c3\u30af\u3001\u30de\u30eb\u30c1\u30d8\u30c3\u30c9\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\uff09\u304c\u542b\u307e\u308c\u3066\u304a\u308a\u3001\u30bf\u30a4\u30e0\u30b9\u30c6\u30c3\u30d7\u306e\u57cb\u3081\u8fbc\u307f\u3082\u8ffd\u52a0\u3055\u308c\u3066\u3044\u307e\u3059\u3002<span translate=no>_^_2_^_</span></p>\n",
 "<h2>U-Net</h2>\n": "<h2>\u30e6\u30fc\u30cd\u30c3\u30c8</h2>\n",
 "<h3>Attention block</h3>\n<p>This is similar to <a href=\"../../transformers/mha.html\">transformer multi-head attention</a>.</p>\n": "<h3>\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\u30d6\u30ed\u30c3\u30af</h3>\n<p><a href=\"../../transformers/mha.html\">\u3053\u308c\u306f\u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30de\u30fc\u306e\u30de\u30eb\u30c1\u30d8\u30c3\u30c9\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\u306b\u4f3c\u3066\u3044\u307e\u3059</a>\u3002</p>\n",
 "<h3>Down block</h3>\n<p>This combines <span translate=no>_^_0_^_</span> and <span translate=no>_^_1_^_</span>. These are used in the first half of U-Net at each resolution.</p>\n": "<h3>\u30c0\u30a6\u30f3\u30d6\u30ed\u30c3\u30af</h3>\n<p><span translate=no>_^_0_^_</span>\u3053\u308c\u306f\u3068\u3092\u7d44\u307f\u5408\u308f\u305b\u305f\u3082\u306e\u3067\u3059<span translate=no>_^_1_^_</span>\u3002\u3053\u308c\u3089\u306fU-Net\u306e\u524d\u534a\u3067\u305d\u308c\u305e\u308c\u306e\u89e3\u50cf\u5ea6\u3067\u4f7f\u308f\u308c\u3066\u3044\u307e\u3059</p>\u3002\n",
 "<h3>Embeddings for <span translate=no>_^_0_^_</span></h3>\n": "<h3>\u306e\u57cb\u3081\u8fbc\u307f <span translate=no>_^_0_^_</span></h3>\n",
 "<h3>Middle block</h3>\n<p>It combines a <span translate=no>_^_0_^_</span>, <span translate=no>_^_1_^_</span>, followed by another <span translate=no>_^_2_^_</span>. This block is applied at the lowest resolution of the U-Net.</p>\n": "<h3>\u30df\u30c9\u30eb\u30d6\u30ed\u30c3\u30af</h3>\n<p>a \u3068<span translate=no>_^_0_^_</span><span translate=no>_^_1_^_</span>\u3001<span translate=no>_^_2_^_</span>\u306e\u5f8c\u306b\u7d9a\u304f\u5225\u306e\u3082\u306e\u3092\u7d44\u307f\u5408\u308f\u305b\u307e\u3059\u3002\u3053\u306e\u30d6\u30ed\u30c3\u30af\u306f U-Net \u306e\u6700\u4f4e\u89e3\u50cf\u5ea6\u3067\u9069\u7528\u3055\u308c\u307e\u3059</p>\u3002\n",
 "<h3>Residual block</h3>\n<p>A residual block has two convolution layers with group normalization. Each resolution is processed with two residual blocks.</p>\n": "<h3>\u6b8b\u7559\u30d6\u30ed\u30c3\u30af</h3>\n<p>\u6b8b\u5dee\u30d6\u30ed\u30c3\u30af\u306b\u306f\u3001\u30b0\u30eb\u30fc\u30d7\u6b63\u898f\u5316\u3055\u308c\u305f 2 \u3064\u306e\u7573\u307f\u8fbc\u307f\u5c64\u304c\u3042\u308a\u307e\u3059\u3002\u5404\u89e3\u50cf\u5ea6\u306f 2 \u3064\u306e\u6b8b\u5dee\u30d6\u30ed\u30c3\u30af\u3067\u51e6\u7406\u3055\u308c\u307e\u3059</p>\u3002\n",
 "<h3>Scale down the feature map by <span translate=no>_^_0_^_</span></h3>\n": "<h3>\u30d5\u30a3\u30fc\u30c1\u30e3\u30de\u30c3\u30d7\u3092\u6b21\u306e\u65b9\u6cd5\u3067\u30b9\u30b1\u30fc\u30eb\u30c0\u30a6\u30f3\u3057\u307e\u3059\u3002<span translate=no>_^_0_^_</span></h3>\n",
 "<h3>Scale up the feature map by <span translate=no>_^_0_^_</span></h3>\n": "<h3>\u6b21\u306e\u65b9\u6cd5\u3067\u30d5\u30a3\u30fc\u30c1\u30e3\u30de\u30c3\u30d7\u3092\u30b9\u30b1\u30fc\u30eb\u30a2\u30c3\u30d7\u3057\u307e\u3059\u3002<span translate=no>_^_0_^_</span></h3>\n",
 "<h3>Swish actiavation function</h3>\n<p><span translate=no>_^_0_^_</span></p>\n": "<h3>\u30b9\u30a4\u30c3\u30c1\u30a2\u30af\u30c6\u30a3\u30d9\u30fc\u30b7\u30e7\u30f3\u6a5f\u80fd</h3>\n<p><span translate=no>_^_0_^_</span></p>\n",
 "<h3>Up block</h3>\n<p>This combines <span translate=no>_^_0_^_</span> and <span translate=no>_^_1_^_</span>. These are used in the second half of U-Net at each resolution.</p>\n": "<h3>\u30a2\u30c3\u30d7\u30d6\u30ed\u30c3\u30af</h3>\n<p><span translate=no>_^_0_^_</span>\u3053\u308c\u306f\u3068\u3092\u7d44\u307f\u5408\u308f\u305b\u305f\u3082\u306e\u3067\u3059<span translate=no>_^_1_^_</span>\u3002\u3053\u308c\u3089\u306fU-Net\u306e\u5f8c\u534a\u3067\u305d\u308c\u305e\u308c\u306e\u89e3\u50cf\u5ea6\u3067\u4f7f\u308f\u308c\u3066\u3044\u307e\u3059</p>\u3002\n",
 "<h4>First half of U-Net - decreasing resolution</h4>\n": "<h4>U-Net\u306e\u524d\u534a-\u89e3\u50cf\u5ea6\u306e\u4f4e\u4e0b</h4>\n",
 "<h4>Second half of U-Net - increasing resolution</h4>\n": "<h4>U-Net\u306e\u5f8c\u534a-\u89e3\u50cf\u5ea6\u306e\u5411\u4e0a</h4>\n",
 "<p> </p>\n": "<p></p>\n",
 "<p><span translate=no>_^_0_^_</span> at the same resolution </p>\n": "<p><span translate=no>_^_0_^_</span>\u540c\u3058\u89e3\u50cf\u5ea6\u3067</p>\n",
 "<p><span translate=no>_^_0_^_</span> is not used, but it&#x27;s kept in the arguments because for the attention layer function signature to match with <span translate=no>_^_1_^_</span>. </p>\n": "<p><span translate=no>_^_0_^_</span>\u306f\u4f7f\u308f\u308c\u3066\u3044\u307e\u305b\u3093\u304c\u3001<span translate=no>_^_1_^_</span>\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\u30ec\u30a4\u30e4\u30fc\u306e\u95a2\u6570\u30b7\u30b0\u30cd\u30c1\u30e3\u3068\u306e\u30de\u30c3\u30c1\u30f3\u30b0\u306e\u305f\u3081\u5f15\u6570\u306b\u306f\u6b8b\u3055\u308c\u3066\u3044\u307e\u3059\u3002</p>\n",
 "<p><span translate=no>_^_0_^_</span> will store outputs at each resolution for skip connection </p>\n": "<p><span translate=no>_^_0_^_</span>\u63a5\u7d9a\u3092\u30b9\u30ad\u30c3\u30d7\u3067\u304d\u308b\u3088\u3046\u306b\u3001\u51fa\u529b\u3092\u5404\u89e3\u50cf\u5ea6\u3067\u4fdd\u5b58\u3057\u307e\u3059</p>\n",
 "<p>Activation </p>\n": "<p>\u30a2\u30af\u30c6\u30a3\u30d9\u30fc\u30b7\u30e7\u30f3</p>\n",
 "<p>Add <span translate=no>_^_0_^_</span> </p>\n": "<p>[\u8ffd\u52a0] <span translate=no>_^_0_^_</span></p>\n",
 "<p>Add skip connection </p>\n": "<p>\u30b9\u30ad\u30c3\u30d7\u63a5\u7d9a\u3092\u8ffd\u52a0</p>\n",
 "<p>Add the shortcut connection and return </p>\n": "<p>\u30b7\u30e7\u30fc\u30c8\u30ab\u30c3\u30c8\u63a5\u7d9a\u3092\u8ffd\u52a0\u3057\u3066\u623b\u308b</p>\n",
 "<p>Add time embeddings </p>\n": "<p>\u6642\u9593\u57cb\u3081\u8fbc\u307f\u3092\u8ffd\u52a0</p>\n",
 "<p>Calculate scaled dot-product <span translate=no>_^_0_^_</span> </p>\n": "<p>\u30b9\u30b1\u30fc\u30ea\u30f3\u30b0\u3055\u308c\u305f\u30c9\u30c3\u30c8\u30d7\u30ed\u30c0\u30af\u30c8\u306e\u8a08\u7b97 <span translate=no>_^_0_^_</span></p>\n",
 "<p>Change <span translate=no>_^_0_^_</span> to shape <span translate=no>_^_1_^_</span> </p>\n": "<p><span translate=no>_^_0_^_</span>\u5f62\u72b6\u306b\u5909\u66f4 <span translate=no>_^_1_^_</span></p>\n",
 "<p>Change to shape <span translate=no>_^_0_^_</span> </p>\n": "<p>\u5f62\u72b6\u306b\u5909\u66f4 <span translate=no>_^_0_^_</span></p>\n",
 "<p>Combine the set of modules </p>\n": "<p>\u30e2\u30b8\u30e5\u30fc\u30eb\u30bb\u30c3\u30c8\u3092\u7d44\u307f\u5408\u308f\u305b\u308b</p>\n",
 "<p>Create sinusoidal position embeddings <a href=\"../../transformers/positional_encoding.html\">same as those from the transformer</a></p>\n<span translate=no>_^_0_^_</span><p>where <span translate=no>_^_1_^_</span> is <span translate=no>_^_2_^_</span> </p>\n": "<p><a href=\"../../transformers/positional_encoding.html\">\u5909\u5727\u5668\u3068\u540c\u3058\u6b63\u5f26\u6ce2\u4f4d\u7f6e\u57cb\u3081\u8fbc\u307f\u3092\u4f5c\u6210</a></p>\n<span translate=no>_^_0_^_</span><p><span translate=no>_^_1_^_</span>\u3069\u3053 <span translate=no>_^_2_^_</span></p>\n",
 "<p>Default <span translate=no>_^_0_^_</span> </p>\n": "<p>\u30c7\u30d5\u30a9\u30eb\u30c8 <span translate=no>_^_0_^_</span></p>\n",
 "<p>Down sample at all resolutions except the last </p>\n": "<p>\u6700\u5f8c\u306e\u89e3\u50cf\u5ea6\u3092\u9664\u304f\u3059\u3079\u3066\u306e\u89e3\u50cf\u5ea6\u306e\u30c0\u30a6\u30f3\u30b5\u30f3\u30d7\u30eb</p>\n",
 "<p>Final block to reduce the number of channels </p>\n": "<p>\u30c1\u30e3\u30f3\u30cd\u30eb\u6570\u3092\u6e1b\u3089\u3059\u305f\u3081\u306e\u6700\u5f8c\u306e\u30d6\u30ed\u30c3\u30af</p>\n",
 "<p>Final normalization and convolution </p>\n": "<p>\u6700\u7d42\u7684\u306a\u6b63\u898f\u5316\u3068\u7573\u307f\u8fbc\u307f</p>\n",
 "<p>Final normalization and convolution layer </p>\n": "<p>\u6700\u7d42\u6b63\u898f\u5316\u3068\u7573\u307f\u8fbc\u307f\u5c64</p>\n",
 "<p>First convolution layer </p>\n": "<p>\u6700\u521d\u306e\u7573\u307f\u8fbc\u307f\u5c64</p>\n",
 "<p>First half of U-Net </p>\n": "<p>\u30e6\u30fc\u30cd\u30c3\u30c8\u524d\u534a</p>\n",
 "<p>First linear layer </p>\n": "<p>\u7b2c 1 \u7dda\u5f62\u30ec\u30a4\u30e4\u30fc</p>\n",
 "<p>For each resolution </p>\n": "<p>\u5404\u89e3\u50cf\u5ea6\u306b\u3064\u3044\u3066</p>\n",
 "<p>Get image projection </p>\n": "<p>\u30a4\u30e1\u30fc\u30b8\u30d7\u30ed\u30b8\u30a7\u30af\u30b7\u30e7\u30f3\u3092\u53d6\u5f97</p>\n",
 "<p>Get query, key, and values (concatenated) and shape it to <span translate=no>_^_0_^_</span> </p>\n": "<p>\u30af\u30a8\u30ea\u3001\u30ad\u30fc\u3001\u5024 (\u9023\u7d50) \u3092\u53d6\u5f97\u3057\u3001\u4ee5\u4e0b\u306e\u3088\u3046\u306b\u5f62\u3092\u6574\u3048\u307e\u3059 <span translate=no>_^_0_^_</span></p>\n",
 "<p>Get shape </p>\n": "<p>\u30b7\u30a7\u30a4\u30d7\u3092\u53d6\u5f97</p>\n",
 "<p>Get the skip connection from first half of U-Net and concatenate </p>\n": "<p>U-Net\u306e\u524d\u534a\u304b\u3089\u30b9\u30ad\u30c3\u30d7\u63a5\u7d9a\u3092\u53d6\u5f97\u3057\u3066\u9023\u7d50\u3059\u308b</p>\n",
 "<p>Get time-step embeddings </p>\n": "<p>\u30bf\u30a4\u30e0\u30b9\u30c6\u30c3\u30d7\u306e\u57cb\u3081\u8fbc\u307f\u3092\u5165\u624b</p>\n",
 "<p>Group normalization and the first convolution layer </p>\n": "<p>\u30b0\u30eb\u30fc\u30d7\u6b63\u898f\u5316\u3068\u6700\u521d\u306e\u7573\u307f\u8fbc\u307f\u5c64</p>\n",
 "<p>Group normalization and the second convolution layer </p>\n": "<p>\u30b0\u30eb\u30fc\u30d7\u6b63\u898f\u5316\u3068 2 \u756a\u76ee\u306e\u7573\u307f\u8fbc\u307f\u5c64</p>\n",
 "<p>If the number of input channels is not equal to the number of output channels we have to project the shortcut connection </p>\n": "<p>\u5165\u529b\u30c1\u30e3\u30f3\u30cd\u30eb\u306e\u6570\u304c\u51fa\u529b\u30c1\u30e3\u30f3\u30cd\u30eb\u306e\u6570\u3068\u7b49\u3057\u304f\u306a\u3044\u5834\u5408\u306f\u3001\u30b7\u30e7\u30fc\u30c8\u30ab\u30c3\u30c8\u63a5\u7d9a\u3092\u6295\u5f71\u3059\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002</p>\n",
 "<p>Linear layer for final transformation </p>\n": "<p>\u6700\u7d42\u5909\u63db\u7528\u306e\u7dda\u5f62\u30ec\u30a4\u30e4\u30fc</p>\n",
 "<p>Linear layer for time embeddings </p>\n": "<p>\u6642\u9593\u57cb\u3081\u8fbc\u307f\u7528\u306e\u7dda\u5f62\u30ec\u30a4\u30e4\u30fc</p>\n",
 "<p>Middle (bottom) </p>\n": "<p>\u4e2d\u592e (\u4e0b\u90e8)</p>\n",
 "<p>Middle block </p>\n": "<p>\u30df\u30c9\u30eb\u30d6\u30ed\u30c3\u30af</p>\n",
 "<p>Multiply by values </p>\n": "<p>\u5024\u306b\u3088\u308b\u4e57\u7b97</p>\n",
 "<p>Normalization layer </p>\n": "<p>\u6b63\u898f\u5316\u30ec\u30a4\u30e4\u30fc</p>\n",
 "<p>Number of channels </p>\n": "<p>\u30c1\u30e3\u30f3\u30cd\u30eb\u6570</p>\n",
 "<p>Number of output channels at this resolution </p>\n": "<p>\u3053\u306e\u89e3\u50cf\u5ea6\u3067\u306e\u51fa\u529b\u30c1\u30e3\u30f3\u30cd\u30eb\u6570</p>\n",
 "<p>Number of resolutions </p>\n": "<p>\u89e3\u50cf\u5ea6\u306e\u6570</p>\n",
 "<p>Project image into feature map </p>\n": "<p>\u753b\u50cf\u3092\u30d5\u30a3\u30fc\u30c1\u30e3\u30de\u30c3\u30d7\u306b\u6295\u5f71</p>\n",
 "<p>Projections for query, key and values </p>\n": "<p>\u30af\u30a8\u30ea\u3001\u30ad\u30fc\u3001\u5024\u306e\u6295\u5f71</p>\n",
 "<p>Reshape to <span translate=no>_^_0_^_</span> </p>\n": "<p>\u5f62\u72b6\u3092\u6b21\u306e\u5f62\u5f0f\u306b\u5909\u66f4 <span translate=no>_^_0_^_</span></p>\n",
 "<p>Scale for dot-product attention </p>\n": "<p>\u30c9\u30c3\u30c8\u30d7\u30ed\u30c0\u30af\u30c8\u30fb\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\u30fb\u30b9\u30b1\u30fc\u30eb</p>\n",
 "<p>Second convolution layer </p>\n": "<p>2 \u756a\u76ee\u306e\u7573\u307f\u8fbc\u307f\u5c64</p>\n",
 "<p>Second half of U-Net </p>\n": "<p>\u30e6\u30fc\u30cd\u30c3\u30c8\u5f8c\u534a</p>\n",
 "<p>Second linear layer </p>\n": "<p>2 \u756a\u76ee\u306e\u7dda\u5f62\u30ec\u30a4\u30e4\u30fc</p>\n",
 "<p>Softmax along the sequence dimension <span translate=no>_^_0_^_</span> </p>\n": "<p>\u30b7\u30fc\u30b1\u30f3\u30b9\u6b21\u5143\u306b\u6cbf\u3063\u305f\u30bd\u30d5\u30c8\u30de\u30c3\u30af\u30b9 <span translate=no>_^_0_^_</span></p>\n",
 "<p>Split query, key, and values. Each of them will have shape <span translate=no>_^_0_^_</span> </p>\n": "<p>\u30af\u30a8\u30ea\u3001\u30ad\u30fc\u3001\u5024\u3092\u5206\u5272\u3057\u307e\u3059\u3002\u305d\u308c\u305e\u308c\u306b\u5f62\u304c\u3042\u308a\u307e\u3059 <span translate=no>_^_0_^_</span></p>\n",
 "<p>The input has <span translate=no>_^_0_^_</span> because we concatenate the output of the same resolution from the first half of the U-Net </p>\n": "<p>\u5165\u529b\u306f\u3001<span translate=no>_^_0_^_</span> U-Net\u306e\u524d\u534a\u304b\u3089\u540c\u3058\u89e3\u50cf\u5ea6\u306e\u51fa\u529b\u3092\u9023\u7d50\u3057\u3066\u3044\u308b\u305f\u3081\u3067\u3059\u3002</p>\n",
 "<p>Time embedding layer. Time embedding has <span translate=no>_^_0_^_</span> channels </p>\n": "<p>\u6642\u9593\u57cb\u3081\u8fbc\u307f\u30ec\u30a4\u30e4\u30fc\u3002\u6642\u9593\u57cb\u3081\u8fbc\u307f\u306b\u306f\u30c1\u30e3\u30f3\u30cd\u30eb\u304c\u3042\u308a\u307e\u3059 <span translate=no>_^_0_^_</span></p>\n",
 "<p>Transform to <span translate=no>_^_0_^_</span> </p>\n": "<p>\u306b\u5909\u63db <span translate=no>_^_0_^_</span></p>\n",
 "<p>Transform with the MLP </p>\n": "<p>MLP \u306b\u3088\u308b\u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30e1\u30fc\u30b7\u30e7\u30f3</p>\n",
 "<p>Up sample at all resolutions except last </p>\n": "<p>\u524d\u56de\u3092\u9664\u304f\u3059\u3079\u3066\u306e\u89e3\u50cf\u5ea6\u3067\u30b5\u30f3\u30d7\u30eb\u3092\u30a2\u30c3\u30d7</p>\n",
 "<ul><li><span translate=no>_^_0_^_</span> has shape <span translate=no>_^_1_^_</span> </li>\n<li><span translate=no>_^_2_^_</span> has shape <span translate=no>_^_3_^_</span></li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u5f62\u304c\u3042\u308b <span translate=no>_^_1_^_</span></li>\n<li><span translate=no>_^_2_^_</span>\u5f62\u304c\u3042\u308b <span translate=no>_^_3_^_</span></li></ul>\n",
 "<ul><li><span translate=no>_^_0_^_</span> is the number of channels in the image. <span translate=no>_^_1_^_</span> for RGB. </li>\n<li><span translate=no>_^_2_^_</span> is number of channels in the initial feature map that we transform the image into </li>\n<li><span translate=no>_^_3_^_</span> is the list of channel numbers at each resolution. The number of channels is <span translate=no>_^_4_^_</span> </li>\n<li><span translate=no>_^_5_^_</span> is a list of booleans that indicate whether to use attention at each resolution </li>\n<li><span translate=no>_^_6_^_</span> is the number of <span translate=no>_^_7_^_</span> at each resolution</li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u753b\u50cf\u5185\u306e\u30c1\u30e3\u30f3\u30cd\u30eb\u6570\u3067\u3059\u3002<span translate=no>_^_1_^_</span>RGB \u7528\u3067\u3059\u3002</li>\n<li><span translate=no>_^_2_^_</span>\u753b\u50cf\u3092\u5909\u63db\u3059\u308b\u6700\u521d\u306e\u7279\u5fb4\u30de\u30c3\u30d7\u306e\u30c1\u30e3\u30f3\u30cd\u30eb\u6570\u3067\u3059</li>\n<li><span translate=no>_^_3_^_</span>\u306f\u3001\u5404\u89e3\u50cf\u5ea6\u306e\u30c1\u30e3\u30f3\u30cd\u30eb\u756a\u53f7\u306e\u30ea\u30b9\u30c8\u3067\u3059\u3002\u30c1\u30e3\u30f3\u30cd\u30eb\u6570\u306f <span translate=no>_^_4_^_</span></li>\n<li><span translate=no>_^_5_^_</span>\u305d\u308c\u305e\u308c\u306e\u89e3\u50cf\u5ea6\u3067\u6ce8\u610f\u3092\u5411\u3051\u308b\u3079\u304d\u304b\u3069\u3046\u304b\u3092\u793a\u3059\u30d6\u30fc\u30ea\u30a2\u30f3\u306e\u30ea\u30b9\u30c8\u3067\u3059</li>\n<li><span translate=no>_^_6_^_</span><span translate=no>_^_7_^_</span>\u306f\u5404\u89e3\u50cf\u5ea6\u3067\u306e\u306e\u6570\u3067\u3059</li></ul>\n",
 "<ul><li><span translate=no>_^_0_^_</span> is the number of channels in the input </li>\n<li><span translate=no>_^_1_^_</span> is the number of heads in multi-head attention </li>\n<li><span translate=no>_^_2_^_</span> is the number of dimensions in each head </li>\n<li><span translate=no>_^_3_^_</span> is the number of groups for <a href=\"../../normalization/group_norm/index.html\">group normalization</a></li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u306f\u5165\u529b\u306e\u30c1\u30e3\u30f3\u30cd\u30eb\u6570</li>\n<li><span translate=no>_^_1_^_</span>\u30de\u30eb\u30c1\u30d8\u30c3\u30c9\u30fb\u30a2\u30c6\u30f3\u30b7\u30e7\u30f3\u306e\u30d8\u30c3\u30c9\u6570\u3067\u3059</li>\n<li><span translate=no>_^_2_^_</span>\u306f\u5404\u30d8\u30c3\u30c9\u306e\u6b21\u5143\u6570\u3067\u3059</li>\n<li><span translate=no>_^_3_^_</span><a href=\"../../normalization/group_norm/index.html\">\u306f\u30b0\u30eb\u30fc\u30d7\u6b63\u898f\u5316\u306e\u5bfe\u8c61\u3068\u306a\u308b\u30b0\u30eb\u30fc\u30d7\u306e\u6570\u3067\u3059</a></li></ul>\n",
 "<ul><li><span translate=no>_^_0_^_</span> is the number of dimensions in the embedding</li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u306f\u57cb\u3081\u8fbc\u307f\u306e\u6b21\u5143\u6570\u3067\u3059</li></ul>\n",
 "<ul><li><span translate=no>_^_0_^_</span> is the number of input channels </li>\n<li><span translate=no>_^_1_^_</span> is the number of input channels </li>\n<li><span translate=no>_^_2_^_</span> is the number channels in the time step (<span translate=no>_^_3_^_</span>) embeddings </li>\n<li><span translate=no>_^_4_^_</span> is the number of groups for <a href=\"../../normalization/group_norm/index.html\">group normalization</a> </li>\n<li><span translate=no>_^_5_^_</span> is the dropout rate</li></ul>\n": "<ul><li><span translate=no>_^_0_^_</span>\u306f\u5165\u529b\u30c1\u30e3\u30f3\u30cd\u30eb\u6570</li>\n<li><span translate=no>_^_1_^_</span>\u306f\u5165\u529b\u30c1\u30e3\u30f3\u30cd\u30eb\u6570</li>\n<li><span translate=no>_^_2_^_</span>\u306f\u30bf\u30a4\u30e0\u30b9\u30c6\u30c3\u30d7 (<span translate=no>_^_3_^_</span>) \u57cb\u3081\u8fbc\u307f\u306e\u6570\u30c1\u30e3\u30f3\u30cd\u30eb\u3067\u3059</li>\n<li><span translate=no>_^_4_^_</span><a href=\"../../normalization/group_norm/index.html\">\u306f\u30b0\u30eb\u30fc\u30d7\u6b63\u898f\u5316\u306e\u5bfe\u8c61\u3068\u306a\u308b\u30b0\u30eb\u30fc\u30d7\u306e\u6570\u3067\u3059</a></li>\n<li><span translate=no>_^_5_^_</span>\u8131\u843d\u7387\u3067\u3059</li></ul>\n",
 "U-Net model for Denoising Diffusion Probabilistic Models (DDPM)": "\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb (DDPM) \u7528\u306e U-Net \u30e2\u30c7\u30eb",
 "UNet model for Denoising Diffusion Probabilistic Models (DDPM)": "\u30ce\u30a4\u30ba\u9664\u53bb\u62e1\u6563\u78ba\u7387\u30e2\u30c7\u30eb (DDPM) \u7528\u306e UNet \u30e2\u30c7\u30eb"
}