0706-2157

diffusion.ipynb

@@ -74,9 +74,24 @@
    "cell_type": "code",
    "execution_count": 2,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9d207dc0a7a24bccb2f419954b64ddc0",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
-    "# notebook_login()"
+    "notebook_login()"
    ]
   },
   {
@@ -259,7 +274,7 @@
     "    dim = 3\n",
     "    stride = (2,2) if dim == 2 else (2,2,2)\n",
     "    num_image = 2000#32000#20000#15000#7000#25600#3000#10000#1000#10000#5000#2560#800#2560\n",
-    "    batch_size = 1#2#50#20#2#100 # 10\n",
+    "    batch_size = 2#2#50#20#2#100 # 10\n",
     "    n_epoch = 10#50#20#20#2#5#25 # 120\n",
     "    HII_DIM = 64\n",
     "    num_redshift = 128#64#512#256#256#64#512#128\n",
@@ -565,15 +580,16 @@
      "output_type": "stream",
      "text": [
       "Number of parameters for nn_model: 306285057\n",
-      "----------------- num_image = 50 -----------------\n",
-      "run_name = 0706-2119\n",
+      "---------------- num_image = 1000 ----------------\n",
+      "run_name = 0706-2157\n",
       "Launching training on one GPU.\n",
       "dataset content: <KeysViewHDF5 ['brightness_temp', 'density', 'kwargs', 'params', 'redshifts_distances', 'seeds', 'xH_box']>\n",
       "51200 images can be loaded\n",
       "field.shape = (64, 64, 514)\n",
       "params keys = [b'ION_Tvir_MIN', b'HII_EFF_FACTOR']\n",
-      "loading 50 images randomly\n",
-      "images loaded: (50, 1, 64, 64, 128)\n"
+      "loading 1000 images randomly\n",
+      "images loaded: (1000, 1, 64, 64, 128)\n",
+      "params loaded: (1000, 2)\n"
      ]
     },
     {
@@ -587,20 +603,19 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "params loaded: (50, 2)\n",
-      "images rescaled to [-1.0, 1.1198105812072754]\n",
-      "params rescaled to [0.0031794774029485495, 0.9969930182712254]\n"
+      "images rescaled to [-1.0, 1.2339041233062744]\n",
+      "params rescaled to [0.0006788479393025145, 0.9997530171043563]\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "3d6033db849844caa518578cd47e47f1",
+       "model_id": "1d069efc366d480ba2515135ccb18f6c",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "  0%|          | 0/50 [00:00<?, ?it/s]"
+       "  0%|          | 0/500 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -609,12 +624,12 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d5df662ea2a242f48099eff4ee120160",
+       "model_id": "93abe7efc5044d3796f67a0d243058b2",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "  0%|          | 0/50 [00:00<?, ?it/s]"
+       "  0%|          | 0/500 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -623,12 +638,12 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ed794eb171ce45be8bc333b21f71adad",
+       "model_id": "75e22a8998244becb916714cf4b8053e",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "  0%|          | 0/50 [00:00<?, ?it/s]"
+       "  0%|          | 0/500 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -637,12 +652,12 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f917cec5bd9e46358337a66fd4f7b364",
+       "model_id": "7364f0924d2246e49fa02a596e0afde8",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "  0%|          | 0/50 [00:00<?, ?it/s]"
+       "  0%|          | 0/500 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -651,12 +666,12 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "7790690aaee44f4cb601b954fc5cf714",
+       "model_id": "a5c57b0059154c2695e7fc0d426bb0d9",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "  0%|          | 0/50 [00:00<?, ?it/s]"
+       "  0%|          | 0/500 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -665,12 +680,12 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "57d0579828ae47ed92afbf52716acee3",
+       "model_id": "b0c9ee9c876144eab582e196e71ed83c",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "  0%|          | 0/50 [00:00<?, ?it/s]"
+       "  0%|          | 0/500 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -679,12 +694,12 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "b9d490d81736432ba7a3ec38137cbb6e",
+       "model_id": "d2956adb8f4c45938f2d8f93baca2998",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "  0%|          | 0/50 [00:00<?, ?it/s]"
+       "  0%|          | 0/500 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -693,12 +708,12 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "7fac169a311e466095ded759464bd864",
+       "model_id": "1f3031b4cd1040829ce3b457ee30e464",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "  0%|          | 0/50 [00:00<?, ?it/s]"
+       "  0%|          | 0/500 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -707,12 +722,12 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "36bcd1e04d3d4d95aa5d9a078233e2c9",
+       "model_id": "b4dcf375da4c4c4492d308e4bdc19358",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "  0%|          | 0/50 [00:00<?, ?it/s]"
+       "  0%|          | 0/500 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -721,12 +736,12 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "e017f171453b4f8eb91d09de38e3fb05",
+       "model_id": "50c6936f333a451394d6761fa9a085be",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "  0%|          | 0/50 [00:00<?, ?it/s]"
+       "  0%|          | 0/500 [00:00<?, ?it/s]"
       ]
      },
      "metadata": {},
@@ -734,7 +749,7 @@
     }
    ],
    "source": [
-    "num_image_list = [50]#[200]#[1600,3200,6400,12800,25600]\n",
+    "num_image_list = [1000]#[200]#[1600,3200,6400,12800,25600]\n",
     "if __name__ == \"__main__\":\n",
     "    # torch.multiprocessing.set_start_method(\"spawn\")\n",
     "    # args = (config, nn_model, ddpm, optimizer, dataloader, lr_scheduler)\n",
@@ -747,15 +762,6 @@
     "        notebook_launcher(ddpm21cm.train, num_processes=1, mixed_precision='fp16')"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# ll -lth outputs"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -764,10 +770,10 @@
    "source": [
     "if __name__ == \"__main__\":\n",
     "    # num_image_list = [1600,3200,6400,12800,25600]\n",
-    "    num_image_list = [20]\n",
+    "    num_image_list = [1000]\n",
     "    # num_image_list = [3200,6400,12800,25600]\n",
     "    # args = (config, nn_model, ddpm, optimizer, dataloader, lr_scheduler)\n",
-    "    repeat = 6\n",
+    "    repeat = 2\n",
     "    config = TrainConfig()\n",
     "    for i, num_image in enumerate(num_image_list):\n",
     "        config.num_image = num_image\n",
@@ -799,10 +805,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "def plot_grid(samples, c=None, row=2, col=3):\n",
+    "def plot_grid(samples, c=None, row=1, col=2):\n",
     "    print(\"samples.shape =\", samples.shape)\n",
     "    for j in range(samples.shape[2]):\n",
-    "        plt.figure(figsize = (9,6), dpi=400)\n",
+    "        plt.figure(figsize = (12,6), dpi=400)\n",
     "        for i in range(len(samples)):\n",
     "            plt.subplot(row,col,i+1)\n",
     "            plt.imshow(samples[i,0,:,:,j], cmap='gray')#, vmin=-1, vmax=1)\n",
@@ -817,7 +823,7 @@
     "        plt.close()\n",
     "        # plt.show()\n",
     "    \n",
-    "data = np.load(\"outputs/Tvir4.400000095367432-zeta131.34100341796875-N20.npy\")\n",
+    "data = np.load(\"outputs/Tvir4.400000095367432-zeta131.34100341796875-N1000.npy\")\n",
     "# print(data.shape)\n",
     "plot_grid(data)\n",
     "# plt.imshow(data)"