diff --git a/mlguess/keras/models.py b/mlguess/keras/models.py index d63ad0b..2e4c0eb 100644 --- a/mlguess/keras/models.py +++ b/mlguess/keras/models.py @@ -233,8 +233,6 @@ def fit( validation_data=validation_data, initial_epoch=initial_epoch, steps_per_epoch=steps_per_epoch, - workers=workers, - use_multiprocessing=use_multiprocessing, shuffle=shuffle, **kwargs, ) diff --git a/notebooks/regression_example.ipynb b/notebooks/regression_example.ipynb index f67f649..4422a6c 100644 --- a/notebooks/regression_example.ipynb +++ b/notebooks/regression_example.ipynb @@ -42,9 +42,23 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], + "execution_count": 1, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "2024-02-29 13:12:04.704730: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n", + "2024-02-29 13:12:04.746479: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n", + "2024-02-29 13:12:04.746517: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n", + "2024-02-29 13:12:04.748194: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n", + "2024-02-29 13:12:04.756471: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n", + "To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n", + "2024-02-29 13:12:06.687230: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n" + ] + } + ], "source": [ "import os, tqdm, yaml\n", "import numpy as np\n", @@ -93,7 +107,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ @@ -114,18 +128,18 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, "outputs": [], "source": [ - "# TODO: Why do we need two seeds?\n", + "# TODO: Where do we need two seeds?\n", "data_seed = 0\n", "flat_seed = 1000" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": {}, "outputs": [], "source": [ @@ -151,7 +165,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "metadata": {}, "outputs": [], "source": [ @@ -162,7 +176,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "metadata": {}, "outputs": [], "source": [ @@ -187,7 +201,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "metadata": {}, "outputs": [], "source": [ @@ -198,9 +212,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "2024-02-29 13:12:11.656601: E external/local_xla/xla/stream_executor/cuda/cuda_driver.cc:274] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected\n" + ] + } + ], "source": [ "model = RegressorDNN(**conf[\"model\"])\n", "model.build_neural_network(x_train.shape[-1], y_train.shape[-1])" @@ -208,9 +230,116 @@ }, { "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], + "execution_count": 10, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
Model: \"functional_1\"\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1mModel: \"functional_1\"\u001b[0m\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
+       "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
+       "│ input (InputLayer)              │ (None, 4)              │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_00 (Dense)                │ (None, 500)            │         2,500 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dropout_h_00 (Dropout)          │ (None, 500)            │             0 │\n",
+       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
+       "│ dense_last (Dense)              │ (None, 1)              │           501 │\n",
+       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
+       "
\n" + ], + "text/plain": [ + "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n", + "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n", + "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n", + "│ input (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dense_00 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m500\u001b[0m) │ \u001b[38;5;34m2,500\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dropout_h_00 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m500\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", + "│ dense_last (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m) │ \u001b[38;5;34m501\u001b[0m │\n", + "└─────────────────────────────────┴────────────────────────┴───────────────┘\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Total params: 3,001 (11.72 KB)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m3,001\u001b[0m (11.72 KB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Trainable params: 3,001 (11.72 KB)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m3,001\u001b[0m (11.72 KB)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "data": { + "text/html": [ + "
 Non-trainable params: 0 (0.00 B)\n",
+       "
\n" + ], + "text/plain": [ + "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" + ] + }, + "metadata": {}, + "output_type": "display_data" + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001b[1m17/20\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━━━\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - loss: 0.0951 - mae: 0.2246" + ] + }, + { + "ename": "ValueError", + "evalue": "The following argument(s) are not supported: ['options']", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", + "Cell \u001b[0;32mIn[10], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx_train\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 2\u001b[0m \u001b[43m \u001b[49m\u001b[43my_train\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3\u001b[0m \u001b[43m \u001b[49m\u001b[43mvalidation_data\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mx_valid\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_valid\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 4\u001b[0m \u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mget_callbacks\u001b[49m\u001b[43m(\u001b[49m\u001b[43mconf\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n", + "File \u001b[0;32m/glade/work/ggantos/miles-guess/mlguess/keras/models.py:226\u001b[0m, in \u001b[0;36mBaseRegressor.fit\u001b[0;34m(self, x, y, validation_data, callbacks, initial_epoch, steps_per_epoch, workers, use_multiprocessing, shuffle, **kwargs)\u001b[0m\n\u001b[1;32m 224\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmodel\u001b[38;5;241m.\u001b[39msummary()\n\u001b[1;32m 225\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtraining_var \u001b[38;5;241m=\u001b[39m [np\u001b[38;5;241m.\u001b[39mvar(y[:, i]) \u001b[38;5;28;01mfor\u001b[39;00m i \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mrange\u001b[39m(y\u001b[38;5;241m.\u001b[39mshape[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m])]\n\u001b[0;32m--> 226\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhistory \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 227\u001b[0m \u001b[43m \u001b[49m\u001b[43mx\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 228\u001b[0m \u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 229\u001b[0m \u001b[43m \u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbatch_size\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 230\u001b[0m \u001b[43m \u001b[49m\u001b[43mepochs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mepochs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 231\u001b[0m \u001b[43m \u001b[49m\u001b[43mverbose\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mverbose\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 232\u001b[0m \u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 233\u001b[0m \u001b[43m \u001b[49m\u001b[43mvalidation_data\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mvalidation_data\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 234\u001b[0m \u001b[43m \u001b[49m\u001b[43minitial_epoch\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minitial_epoch\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 235\u001b[0m \u001b[43m \u001b[49m\u001b[43msteps_per_epoch\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msteps_per_epoch\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 236\u001b[0m \u001b[43m \u001b[49m\u001b[43mshuffle\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mshuffle\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 237\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 238\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n", + "File \u001b[0;32m/glade/work/ggantos/conda-envs/guess/lib/python3.10/site-packages/keras/src/utils/traceback_utils.py:123\u001b[0m, in \u001b[0;36mfilter_traceback..error_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 120\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n\u001b[1;32m 121\u001b[0m \u001b[38;5;66;03m# To get the full stack trace, call:\u001b[39;00m\n\u001b[1;32m 122\u001b[0m \u001b[38;5;66;03m# `keras.config.disable_traceback_filtering()`\u001b[39;00m\n\u001b[0;32m--> 123\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\u001b[38;5;241m.\u001b[39mwith_traceback(filtered_tb) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 124\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[1;32m 125\u001b[0m \u001b[38;5;28;01mdel\u001b[39;00m filtered_tb\n", + "File \u001b[0;32m/glade/work/ggantos/conda-envs/guess/lib/python3.10/site-packages/keras/src/saving/saving_api.py:73\u001b[0m, in \u001b[0;36msave_model\u001b[0;34m(model, filepath, overwrite, **kwargs)\u001b[0m\n\u001b[1;32m 66\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 67\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThe `save_format` argument is deprecated in Keras 3. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 68\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mPlease remove this argument and pass a file path with \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 69\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124meither `.keras` or `.h5` extension.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 70\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mReceived: save_format=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00msave_format\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 71\u001b[0m )\n\u001b[1;32m 72\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m kwargs:\n\u001b[0;32m---> 73\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 74\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThe following argument(s) are not supported: \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 75\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mlist\u001b[39m(kwargs\u001b[38;5;241m.\u001b[39mkeys())\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 76\u001b[0m )\n\u001b[1;32m 78\u001b[0m \u001b[38;5;66;03m# Deprecation warnings\u001b[39;00m\n\u001b[1;32m 79\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mstr\u001b[39m(filepath)\u001b[38;5;241m.\u001b[39mendswith((\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.h5\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.hdf5\u001b[39m\u001b[38;5;124m\"\u001b[39m)):\n", + "\u001b[0;31mValueError\u001b[0m: The following argument(s) are not supported: ['options']" + ] + } + ], "source": [ "model.fit(x_train,\n", " y_train,\n", @@ -222,7 +351,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "##### Predict with the model" + "#### Predict with the model" ] }, { @@ -240,7 +369,7 @@ "metadata": {}, "outputs": [], "source": [ - "mae = np.mean(np.abs(y_pred[:, 0]-test_data[output_cols[0]]))\n", + "mae = np.mean(np.abs(y_pred[:, 0] - test_data[output_cols[0]]))\n", "mae" ] }, @@ -248,16 +377,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "##### Create a Monte Carlo ensemble" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "monte_carlo_steps = 10" + "#### Create a Monte Carlo ensemble" ] }, { @@ -266,7 +386,9 @@ "metadata": {}, "outputs": [], "source": [ - "results = model.predict_monte_carlo(x_test, monte_carlo_steps, y_scaler)" + "results = model.predict_monte_carlo(x_test,\n", + " conf[\"monte_carlo_passes\"],\n", + " y_scaler)" ] }, {