"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"fig, ax = plt.subplots(nrows=1, ncols=1, figsize=(9, 4))\n",
"ax.plot(x, label=f\"HR: {60*y:0.0f} BPM\")\n",
"ax.set_title(\"ECG Frame\")\n",
"ax.legend()\n",
"fig.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Register dataloaders to factory\n",
"\n",
"We will then create a simple DataloaderFactory to ease the creation of dataloaders based on dataset names."
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"DataloaderFactory = nse.utils.create_factory(factory=\"BYOT.DataloaderFactory\", type=hk.HKDataloader)\n",
"DataloaderFactory.register(\"ptbxl\", PtbxlDataloader)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2. Create Data Pipeline\n",
"\n",
"We will create a data pipeline that will be used to train and evaluate the model. For each dataset, we will:\n",
"1. Load the dataset via `hk.DatasetFactory`\n",
"1. Split the dataset patients into training and validation sets\n",
"1. Load the corresponding dataloader via `hk.DataloaderFactory` and create a `tf.data.Dataset` for training and validation\n",
"\n",
"Once each dataset has a pair of training and validation datasets, we will combine them into a single training and validation dataset. At this point we will then extend the pipeline by adding the following:\n",
"1. Shuffle the dataset (if training)\n",
"1. Batch the dataset\n",
"1. Apply augmentations/preprocessing (if any)\n",
"1. Prefetch the dataset\n",
"\n",
"Lastly, for the validation set will cache which will (1) speed up the evaluation process and (2) ensure that the same validation set is used for each epoch with fixed size.\n"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"def create_data_pipeline(\n",
" ds: tf.data.Dataset,\n",
" sampling_rate: int,\n",
" batch_size: int,\n",
" buffer_size: int | None = None,\n",
" augmentations: list[hk.NamedParams] | None = None,\n",
") -> tf.data.Dataset:\n",
" \"\"\"Transforms a dataset into a pipeline with augmentations.\n",
"\n",
" Args:\n",
" ds(tf.data.Dataset): Input dataset.\n",
" sampling_rate(int): Sampling rate of the dataset.\n",
" batch_size(int): Batch size.\n",
" buffer_size(int | None): Buffer size for shuffling.\n",
" augmentations(list[hk.NamedParams] | None): List of augmentations to apply.\n",
"\n",
" Returns:\n",
" tf.data.Dataset: Augmented dataset\n",
" \"\"\"\n",
" if buffer_size:\n",
" ds = ds.shuffle(\n",
" buffer_size=buffer_size,\n",
" reshuffle_each_iteration=True,\n",
" )\n",
" if batch_size:\n",
" ds = ds.batch(\n",
" batch_size=batch_size,\n",
" drop_remainder=True,\n",
" num_parallel_calls=tf.data.AUTOTUNE,\n",
" )\n",
" augmenter = hk.datasets.create_augmentation_pipeline(\n",
" augmentations,\n",
" sampling_rate=sampling_rate\n",
" )\n",
"\n",
" ds = (\n",
" ds.map(\n",
" lambda data, labels: {\n",
" \"data\": tf.cast(data, \"float32\"),\n",
" \"labels\": tf.cast(labels, \"float32\"),\n",
" },\n",
" num_parallel_calls=tf.data.AUTOTUNE,\n",
" )\n",
" .map(\n",
" augmenter,\n",
" num_parallel_calls=tf.data.AUTOTUNE,\n",
" )\n",
" .map(\n",
" lambda data: (data[\"data\"], data[\"labels\"]),\n",
" num_parallel_calls=tf.data.AUTOTUNE,\n",
" )\n",
" )\n",
" return ds.prefetch(tf.data.AUTOTUNE)\n",
"\n",
"def load_train_datasets(\n",
" datasets: list[hk.HKDataset],\n",
" dataloaderFactory: nse.utils.ItemFactory[hk.HKDataloader],\n",
" params: hk.HKTaskParams,\n",
") -> tuple[tf.data.Dataset, tf.data.Dataset]:\n",
" \"\"\"Loads training and validation datasets.\n",
"\n",
" Args:\n",
" datasets(list[hk.HKDataset]): List of datasets to load.\n",
" dataloaderFactory(nse.utils.ItemFactory[hk.HKDataloader]): Factory to create dataloaders.\n",
" params(hk.HKTaskParams): Task parameters.\n",
"\n",
" Returns:\n",
" tuple[tf.data.Dataset, tf.data.Dataset]: Training and validation datasets.\n",
" \"\"\"\n",
"\n",
" # This will load each dataset/dataloader, split subjects, and merge into single tf.data.Dataset\n",
" train_ds, val_ds = hk.tasks.utils.load_train_dataloader_split(datasets, params, factory=DataloaderFactory)\n",
"\n",
" # Create training and validation pipelines\n",
" train_ds = create_data_pipeline(\n",
" ds=train_ds,\n",
" sampling_rate=params.sampling_rate,\n",
" batch_size=params.batch_size,\n",
" buffer_size=params.buffer_size,\n",
" augmentations=params.augmentations + params.preprocesses,\n",
" )\n",
"\n",
" val_ds = create_data_pipeline(\n",
" ds=val_ds,\n",
" sampling_rate=params.sampling_rate,\n",
" batch_size=params.batch_size,\n",
" augmentations=params.preprocesses,\n",
" )\n",
"\n",
" # Cache validation dataset\n",
" val_steps_per_epoch = params.val_size // params.batch_size if params.val_size else params.val_steps_per_epoch\n",
" val_steps_per_epoch = val_steps_per_epoch or 50\n",
" val_ds = val_ds.take(val_steps_per_epoch).cache()\n",
"\n",
" return train_ds, val_ds\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3. Create task routines\n",
"\n",
"We will create a task that will predict heart rate from raw ECG signal. The task will have the following modes:\n",
"1. __train__: Train the model\n",
"1. __evaluate__: Evaluate the model\n"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"def train(params: hk.HKTaskParams):\n",
" \"\"\"Train model\n",
"\n",
" Args:\n",
" params (hk.HKTaskParams): Training parameters\n",
" \"\"\"\n",
" os.makedirs(params.job_dir, exist_ok=True)\n",
"\n",
" logger = nse.utils.setup_logger(__name__, level=params.verbose, file_path=params.job_dir / \"train.log\")\n",
" logger.debug(f\"Creating working directory in {params.job_dir}\")\n",
"\n",
" params.seed = nse.utils.set_random_seed(params.seed)\n",
" logger.debug(f\"Random seed {params.seed}\")\n",
"\n",
" with open(params.job_dir / \"train_config.json\", \"w\", encoding=\"utf-8\") as fp:\n",
" fp.write(params.model_dump_json(indent=2))\n",
"\n",
" params.num_classes = 1 # Regression\n",
" feat_shape = (params.frame_size, 1)\n",
"\n",
" datasets = [hk.DatasetFactory.get(ds.name)(**ds.params) for ds in params.datasets]\n",
"\n",
" train_ds, val_ds = load_train_datasets(\n",
" datasets=datasets,\n",
" dataloaderFactory=DataloaderFactory,\n",
" params=params\n",
" )\n",
"\n",
" y_true = np.concatenate([y for _, y in val_ds.as_numpy_iterator()])\n",
" y_true = np.argmax(y_true, axis=-1).flatten()\n",
"\n",
" inputs = keras.Input(shape=feat_shape, name=\"input\", dtype=\"float32\")\n",
"\n",
" # Load existing model\n",
" if params.resume and params.model_file:\n",
" logger.debug(f\"Loading model from file {params.model_file}\")\n",
" model = nse.models.load_model(params.model_file)\n",
" params.model_file = None\n",
" else:\n",
" logger.debug(\"Creating model from scratch\")\n",
" if params.architecture is None:\n",
" raise ValueError(\"Model architecture must be specified\")\n",
" model = hk.ModelFactory.get(params.architecture.name)(\n",
" inputs=inputs,\n",
" params=params.architecture.params,\n",
" num_classes=params.num_classes,\n",
" )\n",
" # END IF\n",
"\n",
" flops = nse.metrics.flops.get_flops(model, batch_size=1, fpath=params.job_dir / \"model_flops.log\")\n",
"\n",
" t_mul = 1\n",
" first_steps = (params.steps_per_epoch * params.epochs) / (np.power(params.lr_cycles, t_mul) - t_mul + 1)\n",
" scheduler = keras.optimizers.schedules.CosineDecayRestarts(\n",
" initial_learning_rate=params.lr_rate,\n",
" first_decay_steps=np.ceil(first_steps),\n",
" t_mul=t_mul,\n",
" m_mul=0.5,\n",
" )\n",
"\n",
" optimizer = keras.optimizers.Adam(scheduler)\n",
" loss = keras.losses.MeanSquaredError()\n",
" metrics = [\n",
" keras.metrics.MeanAbsoluteError(name=\"mae\"),\n",
" keras.metrics.MeanSquaredError(name=\"mse\"),\n",
" keras.metrics.R2Score(name=\"rsq\"),\n",
" ]\n",
"\n",
" if params.model_file is None:\n",
" params.model_file = params.job_dir / \"model.keras\"\n",
"\n",
" model.compile(optimizer=optimizer, loss=loss, metrics=metrics)\n",
" logger.debug(f\"Model requires {flops/1e6:0.2f} MFLOPS\")\n",
"\n",
" model_callbacks = [\n",
" keras.callbacks.EarlyStopping(\n",
" monitor=f\"val_{params.val_metric}\",\n",
" patience=max(int(0.25 * params.epochs), 1),\n",
" mode=\"max\" if params.val_metric == \"f1\" else \"auto\",\n",
" restore_best_weights=True,\n",
" verbose=min(params.verbose - 1, 1),\n",
" ),\n",
" keras.callbacks.ModelCheckpoint(\n",
" filepath=str(params.model_file),\n",
" monitor=f\"val_{params.val_metric}\",\n",
" save_best_only=True,\n",
" mode=\"max\" if params.val_metric == \"f1\" else \"auto\",\n",
" verbose=min(params.verbose - 1, 1),\n",
" ),\n",
" keras.callbacks.CSVLogger(params.job_dir / \"history.csv\"),\n",
" ]\n",
"\n",
" history = model.fit(\n",
" train_ds,\n",
" steps_per_epoch=params.steps_per_epoch,\n",
" verbose=params.verbose,\n",
" epochs=params.epochs,\n",
" validation_data=val_ds,\n",
" callbacks=model_callbacks,\n",
" )\n",
" logger.debug(f\"Model saved to {params.model_file}\")\n",
"\n",
" nse.plotting.plot_history_metrics(\n",
" history.history,\n",
" metrics=[\"loss\", metrics[0].name],\n",
" save_path=params.job_dir / \"history.png\",\n",
" title=\"Training History\",\n",
" stack=True,\n",
" figsize=(9, 5),\n",
" )\n",
"\n",
" # Summarize results\n",
" rst = model.evaluate(val_ds, return_dict=True)\n",
" logger.info(f\"[VAL SET] \" + \", \".join(f\"{k.upper()}={v:.4f}\" for k, v in rst.items()))\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"def evaluate(params:hk.HKTaskParams):\n",
" \"\"\"Evaluate model\n",
"\n",
" Args:\n",
" params (HKTaskParams): Evaluation parameters\n",
" \"\"\"\n",
" os.makedirs(params.job_dir, exist_ok=True)\n",
" logger = nse.utils.setup_logger(__name__, level=params.verbose, file_path=params.job_dir / \"test.log\")\n",
" logger.debug(f\"Creating working directory in {params.job_dir}\")\n",
"\n",
" params.seed = nse.utils.set_random_seed(params.seed)\n",
" logger.debug(f\"Random seed {params.seed}\")\n",
"\n",
" datasets = [hk.DatasetFactory.get(ds.name)(**ds.params) for ds in params.datasets]\n",
"\n",
" _, test_ds = load_train_datasets(\n",
" datasets=datasets,\n",
" dataloaderFactory=DataloaderFactory,\n",
" params=params\n",
" )\n",
" test_x = np.concatenate([x for x, _ in test_ds.as_numpy_iterator()])\n",
" test_y = np.concatenate([y for _, y in test_ds.as_numpy_iterator()])\n",
"\n",
" logger.debug(\"Loading model\")\n",
" model = nse.models.load_model(params.model_file)\n",
"\n",
" logger.debug(\"Performing inference\")\n",
" rst = model.evaluate(test_ds, verbose=params.verbose, return_dict=True)\n",
" logger.info(\"[TEST SET] \" + \", \".join([f\"{k.upper()}={v:.2%}\" for k, v in rst.items()]))\n",
"\n",
" y_pred = model.predict(test_x)\n",
"\n",
" fig, ax = plt.subplots(nrows=1, ncols=1, figsize=(9, 4))\n",
" ax.scatter(y_pred*60, test_y*60)\n",
" ax.set_title(\"Predicted vs True BPM\")\n",
" ax.set_xlabel(\"Predicted BPM\")\n",
" ax.set_ylabel(\"True BPM\")\n",
" ax.annotate(f\"R2={rst['rsq']:.2f}\", xy=(0.05, 0.95), xycoords='axes fraction')\n",
"\n",
" fig.tight_layout()\n",
" fig.show()\n",
" fig.savefig(params.job_dir / \"bpm_plot.png\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Create HeartRateTask class and register it to the factory"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"class HeartRateTask(hk.HKTask):\n",
" @staticmethod\n",
" def train(params: hk.HKTaskParams):\n",
" train(params)\n",
"\n",
" @staticmethod\n",
" def evaluate(params: hk.HKTaskParams):\n",
" evaluate(params)\n",
"\n",
" @staticmethod\n",
" def export(params: hk.HKTaskParams) -> None:\n",
" raise NotImplementedError(\"Export not implemented\")\n",
"\n",
" @staticmethod\n",
" def demo(params: hk.HKTaskParams) -> None:\n",
" raise NotImplementedError(\"Demo not implemented\")\n"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"hk.TaskFactory.register(\"heartrate\", HeartRateTask)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"rhythm\n",
"beat\n",
"segmentation\n",
"diagnostic\n",
"denoise\n",
"foundation\n",
"translate\n",
"heartrate\n"
]
}
],
"source": [
"for task_name in hk.TaskFactory.list():\n",
" print(task_name)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 4. Let's test out the new task!\n",
"\n",
"First we will create a task configuration with the following features:\n",
"* Frame Size: 8 seconds\n",
"* Dataset: PTB-XL\n",
"* Model: `EfficientNetV2` with 4 MBConv blocks each depth 1\n",
"* Batch Size: 256\n",
"* Buffer Size: 20,000\n",
"* Learning Rate: 1e-3\n",
"* Preprocess: Z-score normalization\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"params = hk.HKTaskParams(\n",
" name=\"BYOT-HR\",\n",
" job_dir=Path(tempfile.gettempdir()) / \"hk-byot-hr\",\n",
" verbose=1,\n",
" datasets=[\n",
" hk.NamedParams(\n",
" name=\"ptbxl\",\n",
" params=dict(\n",
" path=Path(os.environ[\"HK_DATASET_PATH\"]) / \"ptbxl\",\n",
" ),\n",
" ),\n",
" ],\n",
" frame_size=4000, # 8 seconds\n",
" sampling_rate=500, # 500Hz\n",
" samples_per_patient=5,\n",
" val_samples_per_patient=5,\n",
" val_patients=0.2,\n",
" val_size=10000,\n",
" batch_size=256,\n",
" buffer_size=20000,\n",
" epochs=100,\n",
" steps_per_epoch=50,\n",
" lr_rate=1e-3,\n",
" lr_cycles=1,\n",
" val_metric=\"loss\",\n",
" preprocesses=[\n",
" hk.NamedParams(\n",
" name=\"layer_norm\",\n",
" params=dict(\n",
" epsilon=0.01,\n",
" name=\"znorm\"\n",
" ),\n",
" ),\n",
" ],\n",
" augmentations=[],\n",
" architecture=hk.NamedParams(\n",
" name=\"efficientnetv2\",\n",
" params=dict(\n",
" input_filters=8,\n",
" input_kernel_size=[1, 9],\n",
" input_strides=[1, 2],\n",
" blocks=[\n",
" {\"filters\": 16, \"depth\": 1, \"kernel_size\": [1, 9], \"strides\": [1, 2], \"ex_ratio\": 1, \"se_ratio\": 2},\n",
" {\"filters\": 24, \"depth\": 1, \"kernel_size\": [1, 9], \"strides\": [1, 2], \"ex_ratio\": 1, \"se_ratio\": 2},\n",
" {\"filters\": 32, \"depth\": 1, \"kernel_size\": [1, 9], \"strides\": [1, 2], \"ex_ratio\": 1, \"se_ratio\": 2},\n",
" {\"filters\": 40, \"depth\": 1, \"kernel_size\": [1, 9], \"strides\": [1, 2], \"ex_ratio\": 1, \"se_ratio\": 2}\n",
" ],\n",
" output_filters=0,\n",
" include_top=True,\n",
" use_logits=True\n",
" ),\n",
" ),\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"task = hk.TaskFactory.get(\"heartrate\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Train the model\n"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
"I0000 00:00:1723822309.458226 626139 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"I0000 00:00:1723822309.478233 626139 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"I0000 00:00:1723822309.478319 626139 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"I0000 00:00:1723822309.479299 626139 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"I0000 00:00:1723822309.479375 626139 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"I0000 00:00:1723822309.479420 626139 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"I0000 00:00:1723822309.529037 626139 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"I0000 00:00:1723822309.529123 626139 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n",
"I0000 00:00:1723822309.529179 626139 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/100\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
"I0000 00:00:1723822323.031206 626304 service.cc:146] XLA service 0x7471ec02c0b0 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:\n",
"I0000 00:00:1723822323.031237 626304 service.cc:154] StreamExecutor device (0): NVIDIA GeForce RTX 4090, Compute Capability 8.9\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m 5/50\u001b[0m \u001b[32m━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1s\u001b[0m 34ms/step - loss: 1.8535 - mae: 1.2239 - mse: 1.8535 - rsq: -20.3693"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"I0000 00:00:1723822328.955479 626304 device_compiler.h:188] Compiled cluster using XLA! This line is logged at most once for the lifetime of the process.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m17s\u001b[0m 55ms/step - loss: 1.4214 - mae: 1.1194 - mse: 1.4214 - rsq: -16.4093 - val_loss: 0.7500 - val_mae: 0.8469 - val_mse: 0.7500 - val_rsq: -8.4336\n",
"Epoch 2/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 37ms/step - loss: 0.4457 - mae: 0.6133 - mse: 0.4457 - rsq: -4.2974 - val_loss: 0.0573 - val_mae: 0.1936 - val_mse: 0.0573 - val_rsq: 0.2792\n",
"Epoch 3/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 87ms/step - loss: 0.0722 - mae: 0.2064 - mse: 0.0722 - rsq: 0.0739 - val_loss: 0.0206 - val_mae: 0.0998 - val_mse: 0.0206 - val_rsq: 0.7403\n",
"Epoch 4/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 92ms/step - loss: 0.0411 - mae: 0.1526 - mse: 0.0411 - rsq: 0.4376 - val_loss: 0.0178 - val_mae: 0.0924 - val_mse: 0.0178 - val_rsq: 0.7758\n",
"Epoch 5/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 46ms/step - loss: 0.0388 - mae: 0.1436 - mse: 0.0388 - rsq: 0.5175 - val_loss: 0.0161 - val_mae: 0.0889 - val_mse: 0.0161 - val_rsq: 0.7972\n",
"Epoch 6/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0316 - mae: 0.1323 - mse: 0.0316 - rsq: 0.5965 - val_loss: 0.0173 - val_mae: 0.0953 - val_mse: 0.0173 - val_rsq: 0.7820\n",
"Epoch 7/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 36ms/step - loss: 0.0287 - mae: 0.1265 - mse: 0.0287 - rsq: 0.6291 - val_loss: 0.0152 - val_mae: 0.0857 - val_mse: 0.0152 - val_rsq: 0.8089\n",
"Epoch 8/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0266 - mae: 0.1204 - mse: 0.0266 - rsq: 0.6571 - val_loss: 0.0115 - val_mae: 0.0709 - val_mse: 0.0115 - val_rsq: 0.8550\n",
"Epoch 9/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0251 - mae: 0.1161 - mse: 0.0251 - rsq: 0.6806 - val_loss: 0.0116 - val_mae: 0.0734 - val_mse: 0.0116 - val_rsq: 0.8537\n",
"Epoch 10/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0225 - mae: 0.1125 - mse: 0.0225 - rsq: 0.7156 - val_loss: 0.0104 - val_mae: 0.0672 - val_mse: 0.0104 - val_rsq: 0.8689\n",
"Epoch 11/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0235 - mae: 0.1115 - mse: 0.0235 - rsq: 0.7163 - val_loss: 0.0094 - val_mae: 0.0626 - val_mse: 0.0094 - val_rsq: 0.8821\n",
"Epoch 12/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0206 - mae: 0.1054 - mse: 0.0206 - rsq: 0.7445 - val_loss: 0.0088 - val_mae: 0.0573 - val_mse: 0.0088 - val_rsq: 0.8890\n",
"Epoch 13/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0209 - mae: 0.1055 - mse: 0.0209 - rsq: 0.7386 - val_loss: 0.0083 - val_mae: 0.0559 - val_mse: 0.0083 - val_rsq: 0.8951\n",
"Epoch 14/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0194 - mae: 0.1026 - mse: 0.0194 - rsq: 0.7589 - val_loss: 0.0095 - val_mae: 0.0653 - val_mse: 0.0095 - val_rsq: 0.8807\n",
"Epoch 15/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0201 - mae: 0.1032 - mse: 0.0201 - rsq: 0.7443 - val_loss: 0.0079 - val_mae: 0.0561 - val_mse: 0.0079 - val_rsq: 0.9010\n",
"Epoch 16/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0179 - mae: 0.0993 - mse: 0.0179 - rsq: 0.7775 - val_loss: 0.0071 - val_mae: 0.0524 - val_mse: 0.0071 - val_rsq: 0.9104\n",
"Epoch 17/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0176 - mae: 0.0985 - mse: 0.0176 - rsq: 0.7787 - val_loss: 0.0070 - val_mae: 0.0508 - val_mse: 0.0070 - val_rsq: 0.9126\n",
"Epoch 18/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0169 - mae: 0.0968 - mse: 0.0169 - rsq: 0.7807 - val_loss: 0.0092 - val_mae: 0.0673 - val_mse: 0.0092 - val_rsq: 0.8847\n",
"Epoch 19/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0167 - mae: 0.0959 - mse: 0.0167 - rsq: 0.7843 - val_loss: 0.0067 - val_mae: 0.0495 - val_mse: 0.0067 - val_rsq: 0.9155\n",
"Epoch 20/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0169 - mae: 0.0953 - mse: 0.0169 - rsq: 0.7864 - val_loss: 0.0066 - val_mae: 0.0505 - val_mse: 0.0066 - val_rsq: 0.9164\n",
"Epoch 21/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0164 - mae: 0.0944 - mse: 0.0164 - rsq: 0.7958 - val_loss: 0.0065 - val_mae: 0.0487 - val_mse: 0.0065 - val_rsq: 0.9185\n",
"Epoch 22/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0173 - mae: 0.0963 - mse: 0.0173 - rsq: 0.7887 - val_loss: 0.0064 - val_mae: 0.0497 - val_mse: 0.0064 - val_rsq: 0.9197\n",
"Epoch 23/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0158 - mae: 0.0935 - mse: 0.0158 - rsq: 0.7930 - val_loss: 0.0063 - val_mae: 0.0507 - val_mse: 0.0063 - val_rsq: 0.9203\n",
"Epoch 24/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 36ms/step - loss: 0.0150 - mae: 0.0926 - mse: 0.0150 - rsq: 0.8087 - val_loss: 0.0056 - val_mae: 0.0440 - val_mse: 0.0056 - val_rsq: 0.9297\n",
"Epoch 25/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0151 - mae: 0.0919 - mse: 0.0151 - rsq: 0.8020 - val_loss: 0.0057 - val_mae: 0.0452 - val_mse: 0.0057 - val_rsq: 0.9282\n",
"Epoch 26/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0153 - mae: 0.0909 - mse: 0.0153 - rsq: 0.8012 - val_loss: 0.0054 - val_mae: 0.0424 - val_mse: 0.0054 - val_rsq: 0.9324\n",
"Epoch 27/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0171 - mae: 0.0913 - mse: 0.0171 - rsq: 0.7825 - val_loss: 0.0056 - val_mae: 0.0461 - val_mse: 0.0056 - val_rsq: 0.9291\n",
"Epoch 28/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0148 - mae: 0.0891 - mse: 0.0148 - rsq: 0.8121 - val_loss: 0.0084 - val_mae: 0.0690 - val_mse: 0.0084 - val_rsq: 0.8945\n",
"Epoch 29/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0152 - mae: 0.0902 - mse: 0.0152 - rsq: 0.8177 - val_loss: 0.0057 - val_mae: 0.0487 - val_mse: 0.0057 - val_rsq: 0.9284\n",
"Epoch 30/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0142 - mae: 0.0892 - mse: 0.0142 - rsq: 0.8188 - val_loss: 0.0054 - val_mae: 0.0467 - val_mse: 0.0054 - val_rsq: 0.9321\n",
"Epoch 31/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0139 - mae: 0.0886 - mse: 0.0139 - rsq: 0.8321 - val_loss: 0.0047 - val_mae: 0.0407 - val_mse: 0.0047 - val_rsq: 0.9409\n",
"Epoch 32/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 36ms/step - loss: 0.0133 - mae: 0.0868 - mse: 0.0133 - rsq: 0.8310 - val_loss: 0.0045 - val_mae: 0.0397 - val_mse: 0.0045 - val_rsq: 0.9435\n",
"Epoch 33/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0138 - mae: 0.0869 - mse: 0.0138 - rsq: 0.8214 - val_loss: 0.0052 - val_mae: 0.0449 - val_mse: 0.0052 - val_rsq: 0.9352\n",
"Epoch 34/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0140 - mae: 0.0856 - mse: 0.0140 - rsq: 0.8197 - val_loss: 0.0047 - val_mae: 0.0414 - val_mse: 0.0047 - val_rsq: 0.9404\n",
"Epoch 35/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0150 - mae: 0.0859 - mse: 0.0150 - rsq: 0.7989 - val_loss: 0.0046 - val_mae: 0.0390 - val_mse: 0.0046 - val_rsq: 0.9425\n",
"Epoch 36/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0136 - mae: 0.0861 - mse: 0.0136 - rsq: 0.8291 - val_loss: 0.0052 - val_mae: 0.0453 - val_mse: 0.0052 - val_rsq: 0.9344\n",
"Epoch 37/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0141 - mae: 0.0872 - mse: 0.0141 - rsq: 0.8245 - val_loss: 0.0057 - val_mae: 0.0532 - val_mse: 0.0057 - val_rsq: 0.9280\n",
"Epoch 38/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0138 - mae: 0.0863 - mse: 0.0138 - rsq: 0.8309 - val_loss: 0.0047 - val_mae: 0.0418 - val_mse: 0.0047 - val_rsq: 0.9413\n",
"Epoch 39/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0131 - mae: 0.0856 - mse: 0.0131 - rsq: 0.8344 - val_loss: 0.0052 - val_mae: 0.0488 - val_mse: 0.0052 - val_rsq: 0.9344\n",
"Epoch 40/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0123 - mae: 0.0835 - mse: 0.0123 - rsq: 0.8416 - val_loss: 0.0040 - val_mae: 0.0377 - val_mse: 0.0040 - val_rsq: 0.9494\n",
"Epoch 41/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0123 - mae: 0.0828 - mse: 0.0123 - rsq: 0.8364 - val_loss: 0.0042 - val_mae: 0.0390 - val_mse: 0.0042 - val_rsq: 0.9469\n",
"Epoch 42/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0120 - mae: 0.0822 - mse: 0.0120 - rsq: 0.8379 - val_loss: 0.0044 - val_mae: 0.0401 - val_mse: 0.0044 - val_rsq: 0.9446\n",
"Epoch 43/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0126 - mae: 0.0813 - mse: 0.0126 - rsq: 0.8329 - val_loss: 0.0042 - val_mae: 0.0394 - val_mse: 0.0042 - val_rsq: 0.9477\n",
"Epoch 44/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0127 - mae: 0.0849 - mse: 0.0127 - rsq: 0.8375 - val_loss: 0.0047 - val_mae: 0.0458 - val_mse: 0.0047 - val_rsq: 0.9415\n",
"Epoch 45/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0123 - mae: 0.0829 - mse: 0.0123 - rsq: 0.8482 - val_loss: 0.0041 - val_mae: 0.0402 - val_mse: 0.0041 - val_rsq: 0.9484\n",
"Epoch 46/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0127 - mae: 0.0831 - mse: 0.0127 - rsq: 0.8387 - val_loss: 0.0041 - val_mae: 0.0414 - val_mse: 0.0041 - val_rsq: 0.9480\n",
"Epoch 47/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0121 - mae: 0.0817 - mse: 0.0121 - rsq: 0.8436 - val_loss: 0.0047 - val_mae: 0.0465 - val_mse: 0.0047 - val_rsq: 0.9405\n",
"Epoch 48/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0117 - mae: 0.0819 - mse: 0.0117 - rsq: 0.8480 - val_loss: 0.0051 - val_mae: 0.0508 - val_mse: 0.0051 - val_rsq: 0.9359\n",
"Epoch 49/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0127 - mae: 0.0821 - mse: 0.0127 - rsq: 0.8452 - val_loss: 0.0037 - val_mae: 0.0354 - val_mse: 0.0037 - val_rsq: 0.9539\n",
"Epoch 50/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 36ms/step - loss: 0.0139 - mae: 0.0821 - mse: 0.0139 - rsq: 0.8199 - val_loss: 0.0036 - val_mae: 0.0349 - val_mse: 0.0036 - val_rsq: 0.9547\n",
"Epoch 51/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 36ms/step - loss: 0.0113 - mae: 0.0807 - mse: 0.0113 - rsq: 0.8632 - val_loss: 0.0034 - val_mae: 0.0334 - val_mse: 0.0034 - val_rsq: 0.9566\n",
"Epoch 52/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0116 - mae: 0.0798 - mse: 0.0116 - rsq: 0.8522 - val_loss: 0.0036 - val_mae: 0.0352 - val_mse: 0.0036 - val_rsq: 0.9543\n",
"Epoch 53/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0115 - mae: 0.0808 - mse: 0.0115 - rsq: 0.8621 - val_loss: 0.0034 - val_mae: 0.0338 - val_mse: 0.0034 - val_rsq: 0.9567\n",
"Epoch 54/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0144 - mae: 0.0808 - mse: 0.0144 - rsq: 0.8201 - val_loss: 0.0036 - val_mae: 0.0342 - val_mse: 0.0036 - val_rsq: 0.9553\n",
"Epoch 55/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0121 - mae: 0.0789 - mse: 0.0121 - rsq: 0.8478 - val_loss: 0.0034 - val_mae: 0.0340 - val_mse: 0.0034 - val_rsq: 0.9566\n",
"Epoch 56/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 36ms/step - loss: 0.0116 - mae: 0.0790 - mse: 0.0116 - rsq: 0.8607 - val_loss: 0.0034 - val_mae: 0.0339 - val_mse: 0.0034 - val_rsq: 0.9570\n",
"Epoch 57/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0113 - mae: 0.0799 - mse: 0.0113 - rsq: 0.8525 - val_loss: 0.0039 - val_mae: 0.0380 - val_mse: 0.0039 - val_rsq: 0.9514\n",
"Epoch 58/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0117 - mae: 0.0798 - mse: 0.0117 - rsq: 0.8543 - val_loss: 0.0034 - val_mae: 0.0332 - val_mse: 0.0034 - val_rsq: 0.9575\n",
"Epoch 59/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0125 - mae: 0.0825 - mse: 0.0125 - rsq: 0.8491 - val_loss: 0.0044 - val_mae: 0.0450 - val_mse: 0.0044 - val_rsq: 0.9451\n",
"Epoch 60/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0104 - mae: 0.0764 - mse: 0.0104 - rsq: 0.8624 - val_loss: 0.0037 - val_mae: 0.0366 - val_mse: 0.0037 - val_rsq: 0.9534\n",
"Epoch 61/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 37ms/step - loss: 0.0113 - mae: 0.0776 - mse: 0.0113 - rsq: 0.8535 - val_loss: 0.0034 - val_mae: 0.0329 - val_mse: 0.0034 - val_rsq: 0.9578\n",
"Epoch 62/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0113 - mae: 0.0774 - mse: 0.0113 - rsq: 0.8519 - val_loss: 0.0052 - val_mae: 0.0522 - val_mse: 0.0052 - val_rsq: 0.9342\n",
"Epoch 63/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 36ms/step - loss: 0.0110 - mae: 0.0786 - mse: 0.0110 - rsq: 0.8620 - val_loss: 0.0033 - val_mae: 0.0335 - val_mse: 0.0033 - val_rsq: 0.9579\n",
"Epoch 64/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0111 - mae: 0.0791 - mse: 0.0111 - rsq: 0.8581 - val_loss: 0.0034 - val_mae: 0.0338 - val_mse: 0.0034 - val_rsq: 0.9577\n",
"Epoch 65/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0116 - mae: 0.0799 - mse: 0.0116 - rsq: 0.8651 - val_loss: 0.0032 - val_mae: 0.0318 - val_mse: 0.0032 - val_rsq: 0.9595\n",
"Epoch 66/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0132 - mae: 0.0790 - mse: 0.0132 - rsq: 0.8365 - val_loss: 0.0046 - val_mae: 0.0461 - val_mse: 0.0046 - val_rsq: 0.9423\n",
"Epoch 67/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0116 - mae: 0.0802 - mse: 0.0116 - rsq: 0.8559 - val_loss: 0.0034 - val_mae: 0.0332 - val_mse: 0.0034 - val_rsq: 0.9571\n",
"Epoch 68/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0107 - mae: 0.0766 - mse: 0.0107 - rsq: 0.8577 - val_loss: 0.0033 - val_mae: 0.0323 - val_mse: 0.0033 - val_rsq: 0.9584\n",
"Epoch 69/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0107 - mae: 0.0775 - mse: 0.0107 - rsq: 0.8635 - val_loss: 0.0035 - val_mae: 0.0358 - val_mse: 0.0035 - val_rsq: 0.9559\n",
"Epoch 70/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0105 - mae: 0.0762 - mse: 0.0105 - rsq: 0.8693 - val_loss: 0.0039 - val_mae: 0.0406 - val_mse: 0.0039 - val_rsq: 0.9505\n",
"Epoch 71/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0106 - mae: 0.0766 - mse: 0.0106 - rsq: 0.8634 - val_loss: 0.0031 - val_mae: 0.0316 - val_mse: 0.0031 - val_rsq: 0.9605\n",
"Epoch 72/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0113 - mae: 0.0782 - mse: 0.0113 - rsq: 0.8529 - val_loss: 0.0032 - val_mae: 0.0320 - val_mse: 0.0032 - val_rsq: 0.9597\n",
"Epoch 73/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0109 - mae: 0.0779 - mse: 0.0109 - rsq: 0.8620 - val_loss: 0.0031 - val_mae: 0.0311 - val_mse: 0.0031 - val_rsq: 0.9610\n",
"Epoch 74/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0111 - mae: 0.0769 - mse: 0.0111 - rsq: 0.8636 - val_loss: 0.0031 - val_mae: 0.0310 - val_mse: 0.0031 - val_rsq: 0.9607\n",
"Epoch 75/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0102 - mae: 0.0758 - mse: 0.0102 - rsq: 0.8729 - val_loss: 0.0032 - val_mae: 0.0322 - val_mse: 0.0032 - val_rsq: 0.9595\n",
"Epoch 76/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 36ms/step - loss: 0.0107 - mae: 0.0772 - mse: 0.0107 - rsq: 0.8609 - val_loss: 0.0031 - val_mae: 0.0311 - val_mse: 0.0031 - val_rsq: 0.9613\n",
"Epoch 77/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0110 - mae: 0.0774 - mse: 0.0110 - rsq: 0.8658 - val_loss: 0.0031 - val_mae: 0.0316 - val_mse: 0.0031 - val_rsq: 0.9608\n",
"Epoch 78/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0105 - mae: 0.0768 - mse: 0.0105 - rsq: 0.8665 - val_loss: 0.0033 - val_mae: 0.0339 - val_mse: 0.0033 - val_rsq: 0.9589\n",
"Epoch 79/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0104 - mae: 0.0767 - mse: 0.0104 - rsq: 0.8677 - val_loss: 0.0030 - val_mae: 0.0307 - val_mse: 0.0030 - val_rsq: 0.9617\n",
"Epoch 80/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0112 - mae: 0.0775 - mse: 0.0112 - rsq: 0.8662 - val_loss: 0.0031 - val_mae: 0.0307 - val_mse: 0.0031 - val_rsq: 0.9608\n",
"Epoch 81/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0105 - mae: 0.0752 - mse: 0.0105 - rsq: 0.8626 - val_loss: 0.0031 - val_mae: 0.0310 - val_mse: 0.0031 - val_rsq: 0.9605\n",
"Epoch 82/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0111 - mae: 0.0774 - mse: 0.0111 - rsq: 0.8591 - val_loss: 0.0031 - val_mae: 0.0311 - val_mse: 0.0031 - val_rsq: 0.9606\n",
"Epoch 83/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0107 - mae: 0.0766 - mse: 0.0107 - rsq: 0.8632 - val_loss: 0.0034 - val_mae: 0.0348 - val_mse: 0.0034 - val_rsq: 0.9570\n",
"Epoch 84/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0098 - mae: 0.0748 - mse: 0.0098 - rsq: 0.8718 - val_loss: 0.0030 - val_mae: 0.0304 - val_mse: 0.0030 - val_rsq: 0.9619\n",
"Epoch 85/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0107 - mae: 0.0774 - mse: 0.0107 - rsq: 0.8723 - val_loss: 0.0030 - val_mae: 0.0306 - val_mse: 0.0030 - val_rsq: 0.9618\n",
"Epoch 86/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0103 - mae: 0.0771 - mse: 0.0103 - rsq: 0.8624 - val_loss: 0.0030 - val_mae: 0.0305 - val_mse: 0.0030 - val_rsq: 0.9621\n",
"Epoch 87/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0107 - mae: 0.0774 - mse: 0.0107 - rsq: 0.8680 - val_loss: 0.0030 - val_mae: 0.0305 - val_mse: 0.0030 - val_rsq: 0.9620\n",
"Epoch 88/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0118 - mae: 0.0769 - mse: 0.0118 - rsq: 0.8507 - val_loss: 0.0031 - val_mae: 0.0307 - val_mse: 0.0031 - val_rsq: 0.9615\n",
"Epoch 89/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0108 - mae: 0.0756 - mse: 0.0108 - rsq: 0.8602 - val_loss: 0.0031 - val_mae: 0.0315 - val_mse: 0.0031 - val_rsq: 0.9607\n",
"Epoch 90/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0099 - mae: 0.0748 - mse: 0.0099 - rsq: 0.8767 - val_loss: 0.0030 - val_mae: 0.0304 - val_mse: 0.0030 - val_rsq: 0.9620\n",
"Epoch 91/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0108 - mae: 0.0751 - mse: 0.0108 - rsq: 0.8638 - val_loss: 0.0031 - val_mae: 0.0312 - val_mse: 0.0031 - val_rsq: 0.9614\n",
"Epoch 92/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0101 - mae: 0.0752 - mse: 0.0101 - rsq: 0.8703 - val_loss: 0.0031 - val_mae: 0.0307 - val_mse: 0.0031 - val_rsq: 0.9615\n",
"Epoch 93/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0099 - mae: 0.0752 - mse: 0.0099 - rsq: 0.8730 - val_loss: 0.0031 - val_mae: 0.0309 - val_mse: 0.0031 - val_rsq: 0.9614\n",
"Epoch 94/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0105 - mae: 0.0759 - mse: 0.0105 - rsq: 0.8643 - val_loss: 0.0031 - val_mae: 0.0317 - val_mse: 0.0031 - val_rsq: 0.9605\n",
"Epoch 95/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0107 - mae: 0.0755 - mse: 0.0107 - rsq: 0.8700 - val_loss: 0.0030 - val_mae: 0.0306 - val_mse: 0.0030 - val_rsq: 0.9618\n",
"Epoch 96/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0110 - mae: 0.0761 - mse: 0.0110 - rsq: 0.8575 - val_loss: 0.0030 - val_mae: 0.0306 - val_mse: 0.0030 - val_rsq: 0.9617\n",
"Epoch 97/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0100 - mae: 0.0753 - mse: 0.0100 - rsq: 0.8757 - val_loss: 0.0033 - val_mae: 0.0330 - val_mse: 0.0033 - val_rsq: 0.9590\n",
"Epoch 98/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0113 - mae: 0.0770 - mse: 0.0113 - rsq: 0.8597 - val_loss: 0.0032 - val_mae: 0.0326 - val_mse: 0.0032 - val_rsq: 0.9595\n",
"Epoch 99/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 35ms/step - loss: 0.0112 - mae: 0.0760 - mse: 0.0112 - rsq: 0.8565 - val_loss: 0.0031 - val_mae: 0.0310 - val_mse: 0.0031 - val_rsq: 0.9612\n",
"Epoch 100/100\n",
"\u001b[1m50/50\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 34ms/step - loss: 0.0122 - mae: 0.0779 - mse: 0.0122 - rsq: 0.8481 - val_loss: 0.0030 - val_mae: 0.0305 - val_mse: 0.0030 - val_rsq: 0.9618\n",
"\u001b[1m39/39\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 1ms/step - loss: 0.0030 - mae: 0.0307 - mse: 0.0030 - rsq: 0.9639\n"
]
},
{
"data": {
"text/html": [
"INFO [VAL SET] LOSS=0.0030, MAE=0.0305, MSE=0.0030, RSQ=0.9621 3247659150.py:114\n",
"\n"
],
"text/plain": [
"\u001b[34mINFO \u001b[0m \u001b[1m[\u001b[0mVAL SET\u001b[1m]\u001b[0m \u001b[33mLOSS\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.0030\u001b[0m, \u001b[33mMAE\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.0305\u001b[0m, \u001b[33mMSE\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.0030\u001b[0m, \u001b[33mRSQ\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.9621\u001b[0m \u001b]8;id=187434;file:///tmp/ipykernel_626139/3247659150.py\u001b\\\u001b[2m3247659150.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=786914;file:///tmp/ipykernel_626139/3247659150.py#114\u001b\\\u001b[2m114\u001b[0m\u001b]8;;\u001b\\\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"image/png": "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",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"task.train(params)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Finally we will evaluate the model"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m39/39\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 3ms/step - loss: 0.0030 - mae: 0.0307 - mse: 0.0030 - rsq: 0.9639\n"
]
},
{
"data": {
"text/html": [
"INFO [TEST SET] LOSS=0.30%, MAE=3.05%, MSE=0.30%, RSQ=96.21% 3848634147.py:29\n",
"\n"
],
"text/plain": [
"\u001b[34mINFO \u001b[0m \u001b[1m[\u001b[0mTEST SET\u001b[1m]\u001b[0m \u001b[33mLOSS\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.30\u001b[0m%, \u001b[33mMAE\u001b[0m=\u001b[1;36m3\u001b[0m\u001b[1;36m.05\u001b[0m%, \u001b[33mMSE\u001b[0m=\u001b[1;36m0\u001b[0m\u001b[1;36m.30\u001b[0m%, \u001b[33mRSQ\u001b[0m=\u001b[1;36m96\u001b[0m\u001b[1;36m.21\u001b[0m% \u001b]8;id=872574;file:///tmp/ipykernel_626139/3848634147.py\u001b\\\u001b[2m3848634147.py\u001b[0m\u001b]8;;\u001b\\\u001b[2m:\u001b[0m\u001b]8;id=819072;file:///tmp/ipykernel_626139/3848634147.py#29\u001b\\\u001b[2m29\u001b[0m\u001b]8;;\u001b\\\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m312/312\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 1ms/step\n"
]
},
{
"data": {
"image/png": "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",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"task.evaluate(params)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.12.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}