0521-1939

diffusion.ipynb

@@ -121,14 +121,14 @@
     "        self.images = torch.from_numpy(self.images)\n",
     "        print(f\"images rescaled to [{self.images.min()}, {self.images.max()}]\")\n",
     "\n",
-    "        cond_filter = torch.bernoulli(torch.ones(self.params.shape[0],1)-self.drop_prob).repeat(1,self.params.shape[1]).numpy()\n",
+    "        cond_filter = torch.bernoulli(torch.ones(len(self.params),1)-self.drop_prob).repeat(1,self.params.shape[1]).numpy()\n",
     "        self.params = torch.from_numpy(self.params*cond_filter)\n",
     "        print(f\"params rescaled to [{self.params.min()}, {self.params.max()}]\")\n",
     "\n",
     "    def load_h5(self):\n",
     "        with h5py.File(self.dir_name, 'r') as f:\n",
     "            print(f\"dataset content: {f.keys()}\")\n",
-    "            max_num_image = f['brightness_temp'].shape[0]\n",
+    "            max_num_image = len(f['brightness_temp'])#.shape[0]\n",
     "            print(f\"{max_num_image} images can be loaded\")\n",
     "            field_shape = f['brightness_temp'].shape[1:]\n",
     "            print(f\"field.shape = {field_shape}\")\n",
@@ -275,8 +275,8 @@
     "        return noisy_images, noise, ts\n",
     "\n",
     "    def sample(self, nn_model, params, device, guide_w = 0):\n",
-    "        n_sample = params.shape[0]\n",
-    "        print(\"params.shape[0], len(params)\", params.shape[0], len(params))\n",
+    "        n_sample = len(params) #params.shape[0]\n",
+    "        # print(\"params.shape[0], len(params)\", params.shape[0], len(params))\n",
     "        x_i = torch.randn(n_sample, *self.shape[1:]).to(device)\n",
     "        # print(\"x_i.shape =\", x_i.shape)\n",
     "        if guide_w != -1:\n",
@@ -945,7 +945,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 103,
+   "execution_count": 123,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -966,6 +966,8 @@
     "    num_image = 20 # 2400\n",
     "    HII_DIM = 64\n",
     "    num_redshift = 512#256#256#64#512#128\n",
+    "    img_shape = (HII_DIM, num_redshift) if dim == 2 else (HII_DIM, HII_DIM, num_redshift)\n",
+    "\n",
     "    n_epoch = 10#2#5#25 # 120\n",
     "    num_timesteps = 1000#1000 # 1000, 500; DDPM time steps\n",
     "    train_batch_size = 10#10#20#2#100 # 10\n",
@@ -1008,7 +1010,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 104,
+   "execution_count": 124,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1018,7 +1020,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 105,
+   "execution_count": 125,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1027,7 +1029,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 106,
+   "execution_count": 126,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1051,7 +1053,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 107,
+   "execution_count": 127,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1249,7 +1251,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 117,
+   "execution_count": 128,
    "metadata": {},
    "outputs": [
     {
@@ -1263,8 +1265,8 @@
       "loading 20 images randomly\n",
       "images loaded: (20, 1, 64, 512)\n",
       "params loaded: (20, 2)\n",
-      "images rescaled to [-1.0, 0.8818775415420532]\n",
-      "params rescaled to [0.0, 0.9965706900954632]\n",
+      "images rescaled to [-1.0, 1.038496732711792]\n",
+      "params rescaled to [0.0, 0.9816321951033768]\n",
       "resumed nn_model from model_state.pth\n",
       "Number of parameters for nn_model: 111048705\n"
      ]
@@ -1424,7 +1426,6 @@
     "\n",
     "    def sample(self, file, params=torch.tensor((0.2,0.8)), ema=False, entire=False):\n",
     "        # n_sample = params.shape[0]\n",
-    "        shape = (self.config.HII, self.config.num_redshift) if self.config.dim == 2 else (self.config.HII, self.config.HII, self.config.num_redshift)\n",
     "        model = self.ema_model if ema else self.nn_model\n",
     "        # params = torch.tile(params, (n_sample,1)).to(device)\n",
     "\n",
@@ -1441,13 +1442,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 110,
+   "execution_count": 129,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "7b26c7444a1144728f0299db5d5683b1",
+       "model_id": "067df92056c8456aa796e3416bac122a",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1461,7 +1462,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "e3b8c1a18460443d986282f284bf0b42",
+       "model_id": "8e77d9787ee049e5896b1be75d34bf05",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1475,7 +1476,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "84d558fcea2f4b998f311da7452a2c93",
+       "model_id": "8211e85e22354d7da06f66786ff33d4a",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1489,7 +1490,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "364208bd1fa04859baf233ed30451638",
+       "model_id": "31d068ad21c642468bb2a90c7af57c83",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1503,7 +1504,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "e8aa693ca9b444d7b6adb77531f8b718",
+       "model_id": "2ca6304e757f4c8696bacfc36692e791",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1517,7 +1518,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "aab44a74df8c4a7a8baf975b8ec50b8b",
+       "model_id": "7cc536030a784596995ec5130b7638c5",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1531,7 +1532,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "461da88dafc8437a858b6eed2042c709",
+       "model_id": "b415a15a942046f08e3e2c92404c14ad",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1545,7 +1546,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a85d41b905884ec6947eb1fb94f2f934",
+       "model_id": "2de1a814b7d34998b63eec43c1d43c12",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1559,7 +1560,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f9677e0a3b6049d1a9877eec1689f506",
+       "model_id": "2ae161b79b0d4e688b12432455a6c065",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1573,7 +1574,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "5bd75ea4440b4acbb54b55c14fec272b",
+       "model_id": "7497a93eb57a40e281141126947f78ae",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1583,13 +1584,6 @@
      },
      "metadata": {},
      "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "saved model at ./outputs/model_state_09.pth\n"
-     ]
     }
    ],
    "source": [