From 5b5e3cc7cf3b7108173b47130a8c9901ac079022 Mon Sep 17 00:00:00 2001 From: oskar Date: Tue, 4 Nov 2025 23:26:22 +0100 Subject: [PATCH] fixes, my version --- work-sc.ipynb | 422 ++++++++++++++++++++++++++++++++------------------ 1 file changed, 273 insertions(+), 149 deletions(-) diff --git a/work-sc.ipynb b/work-sc.ipynb index f67362f..5ac0d80 100644 --- a/work-sc.ipynb +++ b/work-sc.ipynb @@ -5,19 +5,19 @@ "id": "initial_id", "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:00.816816Z", - "start_time": "2025-11-04T22:00:00.813630Z" + "end_time": "2025-11-04T22:20:01.935976Z", + "start_time": "2025-11-04T22:20:01.932910Z" } }, "source": "import numpy as np", "outputs": [], - "execution_count": 84 + "execution_count": 49 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:00.830847Z", - "start_time": "2025-11-04T22:00:00.829329Z" + "end_time": "2025-11-04T22:20:01.948882Z", + "start_time": "2025-11-04T22:20:01.944370Z" } }, "cell_type": "code", @@ -32,13 +32,13 @@ ], "id": "48cafaf4b64967bb", "outputs": [], - "execution_count": 85 + "execution_count": 50 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:00.885348Z", - "start_time": "2025-11-04T22:00:00.880961Z" + "end_time": "2025-11-04T22:20:02.002162Z", + "start_time": "2025-11-04T22:20:01.996198Z" } }, "cell_type": "code", @@ -62,13 +62,13 @@ ], "id": "d13137630b41b756", "outputs": [], - "execution_count": 86 + "execution_count": 51 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:00.944688Z", - "start_time": "2025-11-04T22:00:00.939752Z" + "end_time": "2025-11-04T22:20:02.054626Z", + "start_time": "2025-11-04T22:20:02.050524Z" } }, "cell_type": "code", @@ -78,13 +78,13 @@ ], "id": "31f205147667dea6", "outputs": [], - "execution_count": 87 + "execution_count": 52 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:00.994063Z", - "start_time": "2025-11-04T22:00:00.990969Z" + "end_time": "2025-11-04T22:20:02.109755Z", + "start_time": "2025-11-04T22:20:02.102747Z" } }, "cell_type": "code", @@ -106,13 +106,13 @@ ], "id": "c1b960e7dcf09d91", "outputs": [], - "execution_count": 88 + "execution_count": 53 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:01.051837Z", - "start_time": "2025-11-04T22:00:01.046197Z" + "end_time": "2025-11-04T22:20:02.164149Z", + "start_time": "2025-11-04T22:20:02.158664Z" } }, "cell_type": "code", @@ -131,13 +131,13 @@ ], "id": "efae2e184daf2fce", "outputs": [], - "execution_count": 89 + "execution_count": 54 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:01.101365Z", - "start_time": "2025-11-04T22:00:01.097608Z" + "end_time": "2025-11-04T22:20:02.218489Z", + "start_time": "2025-11-04T22:20:02.212053Z" } }, "cell_type": "code", @@ -162,13 +162,13 @@ ], "id": "c3cd9e8f51dbe967", "outputs": [], - "execution_count": 90 + "execution_count": 55 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:01.147862Z", - "start_time": "2025-11-04T22:00:01.146127Z" + "end_time": "2025-11-04T22:20:02.265846Z", + "start_time": "2025-11-04T22:20:02.262056Z" } }, "cell_type": "code", @@ -191,13 +191,13 @@ ], "id": "121416e7bbab57bb", "outputs": [], - "execution_count": 91 + "execution_count": 56 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:01.200653Z", - "start_time": "2025-11-04T22:00:01.198951Z" + "end_time": "2025-11-04T22:20:02.319756Z", + "start_time": "2025-11-04T22:20:02.314518Z" } }, "cell_type": "code", @@ -221,13 +221,13 @@ ], "id": "92e4b87664f18a63", "outputs": [], - "execution_count": 92 + "execution_count": 57 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:01.259385Z", - "start_time": "2025-11-04T22:00:01.253050Z" + "end_time": "2025-11-04T22:20:02.375728Z", + "start_time": "2025-11-04T22:20:02.368707Z" } }, "cell_type": "code", @@ -260,13 +260,13 @@ ], "id": "2c8e4eed1846f003", "outputs": [], - "execution_count": 93 + "execution_count": 58 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:01.319868Z", - "start_time": "2025-11-04T22:00:01.312729Z" + "end_time": "2025-11-04T22:20:02.429757Z", + "start_time": "2025-11-04T22:20:02.424922Z" } }, "cell_type": "code", @@ -281,13 +281,13 @@ ], "id": "16320b953a183511", "outputs": [], - "execution_count": 94 + "execution_count": 59 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:01.380430Z", - "start_time": "2025-11-04T22:00:01.373966Z" + "end_time": "2025-11-04T22:20:02.487991Z", + "start_time": "2025-11-04T22:20:02.480828Z" } }, "cell_type": "code", @@ -316,7 +316,7 @@ " # updating model state\n", " params_values = update(params_values, grads_values, nn_architecture, learning_rate)\n", "\n", - " if(i % 50 == 0):\n", + " if(i % 1000 == 0):\n", " if(verbose):\n", " print(\"Iteration: {:05} - cost: {:.5f} - accuracy: {:.5f}\".format(i, cost, accuracy))\n", " if(callback is not None):\n", @@ -326,13 +326,13 @@ ], "id": "fce33f70bba3898", "outputs": [], - "execution_count": 95 + "execution_count": 60 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:01.444163Z", - "start_time": "2025-11-04T22:00:01.436199Z" + "end_time": "2025-11-04T22:20:02.541893Z", + "start_time": "2025-11-04T22:20:02.536342Z" } }, "cell_type": "code", @@ -359,13 +359,13 @@ ], "id": "cccd73b5018799d4", "outputs": [], - "execution_count": 96 + "execution_count": 61 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:01.500700Z", - "start_time": "2025-11-04T22:00:01.497537Z" + "end_time": "2025-11-04T22:20:02.595656Z", + "start_time": "2025-11-04T22:20:02.591558Z" } }, "cell_type": "code", @@ -377,13 +377,13 @@ ], "id": "4f66ffa878f01c02", "outputs": [], - "execution_count": 97 + "execution_count": 62 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:01.560294Z", - "start_time": "2025-11-04T22:00:01.553505Z" + "end_time": "2025-11-04T22:21:10.863339Z", + "start_time": "2025-11-04T22:21:10.858278Z" } }, "cell_type": "code", @@ -393,29 +393,136 @@ ], "id": "bebe0ed00a2d514", "outputs": [], - "execution_count": 98 + "execution_count": 65 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:04.165839Z", - "start_time": "2025-11-04T22:00:01.614181Z" + "end_time": "2025-11-04T22:21:50.510912Z", + "start_time": "2025-11-04T22:21:38.081823Z" } }, "cell_type": "code", "source": [ - "params_values = train(np.transpose(X_train), np.transpose(y_train.reshape((y_train.shape[0], 1))), nn_architecture, 20000, 0.01)\n", + "params_values = train(np.transpose(X_train), np.transpose(y_train.reshape((y_train.shape[0], 1))), nn_architecture, 100000, 0.001, verbose=True)\n", "# params_values\n" ], "id": "ce04892d496c5147", - "outputs": [], - "execution_count": 99 + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Iteration: 00000 - cost: 0.69407 - accuracy: 0.49556\n", + "Iteration: 01000 - cost: 0.69369 - accuracy: 0.49556\n", + "Iteration: 02000 - cost: 0.69346 - accuracy: 0.49556\n", + "Iteration: 03000 - cost: 0.69332 - accuracy: 0.49556\n", + "Iteration: 04000 - cost: 0.69324 - accuracy: 0.49556\n", + "Iteration: 05000 - cost: 0.69319 - accuracy: 0.49556\n", + "Iteration: 06000 - cost: 0.69316 - accuracy: 0.49556\n", + "Iteration: 07000 - cost: 0.69314 - accuracy: 0.50444\n", + "Iteration: 08000 - cost: 0.69313 - accuracy: 0.50444\n", + "Iteration: 09000 - cost: 0.69312 - accuracy: 0.50444\n", + "Iteration: 10000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 11000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 12000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 13000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 14000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 15000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 16000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 17000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 18000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 19000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 20000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 21000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 22000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 23000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 24000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 25000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 26000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 27000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 28000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 29000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 30000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 31000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 32000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 33000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 34000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 35000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 36000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 37000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 38000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 39000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 40000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 41000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 42000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 43000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 44000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 45000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 46000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 47000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 48000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 49000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 50000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 51000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 52000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 53000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 54000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 55000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 56000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 57000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 58000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 59000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 60000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 61000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 62000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 63000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 64000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 65000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 66000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 67000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 68000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 69000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 70000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 71000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 72000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 73000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 74000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 75000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 76000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 77000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 78000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 79000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 80000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 81000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 82000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 83000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 84000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 85000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 86000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 87000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 88000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 89000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 90000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 91000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 92000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 93000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 94000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 95000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 96000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 97000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 98000 - cost: 0.69311 - accuracy: 0.50444\n", + "Iteration: 99000 - cost: 0.69311 - accuracy: 0.50444\n" + ] + } + ], + "execution_count": 66 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:11.428146Z", - "start_time": "2025-11-04T22:00:11.422370Z" + "end_time": "2025-11-04T22:20:02.749879571Z", + "start_time": "2025-11-04T22:18:29.064616Z" } }, "cell_type": "code", @@ -435,75 +542,13 @@ ] } ], - "execution_count": 105 + "execution_count": 47 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:00:29.176357Z", - "start_time": "2025-11-04T22:00:23.282276Z" - } - }, - "cell_type": "code", - "source": [ - "model = Sequential()\n", - "model.add(Dense(25, input_dim=2,activation='relu'))\n", - "model.add(Dense(50, activation='relu'))\n", - "model.add(Dense(50, activation='relu'))\n", - "model.add(Dense(25, activation='relu'))\n", - "model.add(Dense(1, activation='sigmoid'))\n", - "\n", - "model.compile(loss='binary_crossentropy', optimizer=\"sgd\", metrics=['accuracy'])\n", - "\n", - "# Training\n", - "history = model.fit(X_train, y_train, epochs=200, verbose=0)" - ], - "id": "f05ff40ed26e45c2", - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/home/oskar/projects/nn-from-scratch/.venv/lib/python3.13/site-packages/keras/src/layers/core/dense.py:95: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", - " super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n" - ] - } - ], - "execution_count": 106 - }, - { - "metadata": { - "ExecuteTime": { - "end_time": "2025-11-04T22:00:33.380478Z", - "start_time": "2025-11-04T22:00:33.309269Z" - } - }, - "cell_type": "code", - "source": [ - "Y_test_prob = model.predict(X_test)\n", - "Y_test_hat = (Y_test_prob > 0.5).astype(int).ravel()\n", - "acc_test = accuracy_score(y_test, Y_test_hat)\n", - "print(\"Test set accuracy: {:.2f} - Goliath\".format(acc_test))" - ], - "id": "ef52bee9c93081d3", - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "WARNING:tensorflow:6 out of the last 10 calls to .one_step_on_data_distributed at 0x7e21f476c900> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details.\n", - "\u001B[1m4/4\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 8ms/step \n", - "Test set accuracy: 0.99 - Goliath\n" - ] - } - ], - "execution_count": 107 - }, - { - "metadata": { - "ExecuteTime": { - "end_time": "2025-11-04T22:03:33.972219Z", - "start_time": "2025-11-04T22:03:33.966407Z" + "end_time": "2025-11-04T22:25:47.659577Z", + "start_time": "2025-11-04T22:25:47.652275Z" } }, "cell_type": "code", @@ -527,15 +572,99 @@ " plt.savefig(file_name)\n", " plt.close()" ], - "id": "9535365d1da72395", + "id": "553e08ddc23ab78c", "outputs": [], - "execution_count": 109 + "execution_count": 70 + }, + { + "metadata": {}, + "cell_type": "code", + "outputs": [], + "execution_count": null, + "source": [ + "def callback_numpy_plot(index, params):\n", + " plot_title = \"NumPy Model - It: {:05}\".format(index)\n", + " file_name = \"numpy_model_{:05}.png\".format(index // 50)\n", + " file_path = os.path.join(OUTPUT_DIR, file_name)\n", + " prediction_probs, _ = full_forward_propagation(np.transpose(grid_2d), params, nn_architecture)\n", + " prediction_probs = prediction_probs.reshape(prediction_probs.shape[1], 1)\n", + " make_plot(X_test, y_test, plot_title, file_name=file_path, XX=XX, YY=YY, preds=prediction_probs, dark=True)\n", + "\n", + "\n", + "# Training\n", + "params_values = train(np.transpose(X_train), np.transpose(y_train.reshape((y_train.shape[0], 1))), nn_architecture,\n", + " 10000, 0.01, False, callback_numpy_plot)\n", + "prediction_probs_numpy, _ = full_forward_propagation(np.transpose(grid_2d), params_values, nn_architecture)\n", + "prediction_probs_numpy = prediction_probs_numpy.reshape(prediction_probs_numpy.shape[1], 1)\n", + "make_plot(X_test, y_test, \"NumPy Model\", file_name=None, XX=XX, YY=YY, preds=prediction_probs_numpy)" + ], + "id": "b6a4d6a1a1fb289" + }, + { + "metadata": {}, + "cell_type": "code", + "outputs": [], + "execution_count": null, + "source": "", + "id": "dc0b9266ae37298a" }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:02:51.938430Z", - "start_time": "2025-11-04T22:02:51.934316Z" + "end_time": "2025-11-04T22:20:02.760128452Z", + "start_time": "2025-11-04T22:17:38.579795Z" + } + }, + "cell_type": "code", + "source": [ + "model = Sequential()\n", + "model.add(Dense(25, input_dim=2,activation='relu'))\n", + "model.add(Dense(50, activation='relu'))\n", + "model.add(Dense(50, activation='relu'))\n", + "model.add(Dense(25, activation='relu'))\n", + "model.add(Dense(1, activation='sigmoid'))\n", + "\n", + "model.compile(loss='binary_crossentropy', optimizer=\"sgd\", metrics=['accuracy'])\n", + "\n", + "# Training\n", + "history = model.fit(X_train, y_train, epochs=200, verbose=0)" + ], + "id": "f05ff40ed26e45c2", + "outputs": [], + "execution_count": 42 + }, + { + "metadata": { + "ExecuteTime": { + "end_time": "2025-11-04T22:20:02.761214479Z", + "start_time": "2025-11-04T22:17:44.410525Z" + } + }, + "cell_type": "code", + "source": [ + "Y_test_prob = model.predict(X_test)\n", + "Y_test_hat = (Y_test_prob > 0.5).astype(int).ravel()\n", + "acc_test = accuracy_score(y_test, Y_test_hat)\n", + "print(\"Test set accuracy: {:.2f} - Goliath\".format(acc_test))" + ], + "id": "ef52bee9c93081d3", + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "\u001B[1m4/4\u001B[0m \u001B[32m━━━━━━━━━━━━━━━━━━━━\u001B[0m\u001B[37m\u001B[0m \u001B[1m0s\u001B[0m 7ms/step \n", + "Test set accuracy: 1.00 - Goliath\n" + ] + } + ], + "execution_count": 43 + }, + { + "metadata": { + "ExecuteTime": { + "end_time": "2025-11-04T22:22:16.887963Z", + "start_time": "2025-11-04T22:22:16.881924Z" } }, "cell_type": "code", @@ -547,20 +676,21 @@ "GRID_Y_END = 2\n", "# output directory (the folder must be created on the drive)\n", "OUTPUT_DIR = \"./binary_classification_vizualizations/\"\n", + "os.makedirs(OUTPUT_DIR, exist_ok=True)\n", "### Definition of grid boundaries\n", - "grid = np.mgrid[GRID_X_START:GRID_X_END:100j, GRID_X_START:GRID_Y_END:100j]\n", + "grid = np.mgrid[GRID_X_START:GRID_X_END:100j, GRID_Y_START:GRID_Y_END:100j]\n", "grid_2d = grid.reshape(2, -1).T\n", "XX, YY = grid" ], "id": "b070f03d55981894", "outputs": [], - "execution_count": 108 + "execution_count": 68 }, { "metadata": { "ExecuteTime": { - "end_time": "2025-11-04T22:05:02.290039Z", - "start_time": "2025-11-04T22:05:02.042691Z" + "end_time": "2025-11-04T22:23:06.066935Z", + "start_time": "2025-11-04T22:22:22.111811Z" } }, "cell_type": "code", @@ -569,7 +699,8 @@ " plot_title = \"Keras Model - It: {:05}\".format(epoch)\n", " file_name = \"keras_model_{:05}.png\".format(epoch)\n", " file_path = os.path.join(OUTPUT_DIR, file_name)\n", - " prediction_probs = model.predict_proba(grid_2d, batch_size=32, verbose=0)\n", + " prediction_probs = model.predict(grid_2d, batch_size=32, verbose=0)\n", + " prediction_probs = prediction_probs.reshape(-1)\n", " make_plot(X_test, y_test, plot_title, file_name=file_path, XX=XX, YY=YY, preds=prediction_probs)\n", "\n", "\n", @@ -588,34 +719,27 @@ "\n", "# Training\n", "history = model.fit(X_train, y_train, epochs=200, verbose=0, callbacks=[testmodelcb])\n", - "rediction_probs = model.predict_proba(grid_2d, batch_size=32, verbose=0)\n", - "make_plot(X_test, y_test, \"Keras Model\", file_name=None, XX=XX, YY=YY, preds=prediction_probs)" + "prediction_probs = model.predict(grid_2d, batch_size=32, verbose=0)\n", + "prediction_probs = prediction_probs.reshape(-1)\n", + "make_plot(X_test, y_test, \"Keras Model\", file_name=None, XX=XX, YY=YY, preds=prediction_probs)\n" ], "id": "6feab7da06e7a828", "outputs": [ { - "name": "stderr", - "output_type": "stream", - "text": [ - "/home/oskar/projects/nn-from-scratch/.venv/lib/python3.13/site-packages/keras/src/layers/core/dense.py:95: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", - " super().__init__(activity_regularizer=activity_regularizer, **kwargs)\n" - ] - }, - { - "ename": "AttributeError", - "evalue": "'Sequential' object has no attribute 'predict_proba'", - "output_type": "error", - "traceback": [ - "\u001B[31m---------------------------------------------------------------------------\u001B[39m", - "\u001B[31mAttributeError\u001B[39m Traceback (most recent call last)", - "\u001B[36mCell\u001B[39m\u001B[36m \u001B[39m\u001B[32mIn[110]\u001B[39m\u001B[32m, line 23\u001B[39m\n\u001B[32m 20\u001B[39m model.compile(loss=\u001B[33m'\u001B[39m\u001B[33mbinary_crossentropy\u001B[39m\u001B[33m'\u001B[39m, optimizer=\u001B[33m\"\u001B[39m\u001B[33msgd\u001B[39m\u001B[33m\"\u001B[39m, metrics=[\u001B[33m'\u001B[39m\u001B[33maccuracy\u001B[39m\u001B[33m'\u001B[39m])\n\u001B[32m 22\u001B[39m \u001B[38;5;66;03m# Training\u001B[39;00m\n\u001B[32m---> \u001B[39m\u001B[32m23\u001B[39m history = \u001B[43mmodel\u001B[49m\u001B[43m.\u001B[49m\u001B[43mfit\u001B[49m\u001B[43m(\u001B[49m\u001B[43mX_train\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43my_train\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mepochs\u001B[49m\u001B[43m=\u001B[49m\u001B[32;43m200\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mverbose\u001B[49m\u001B[43m=\u001B[49m\u001B[32;43m0\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcallbacks\u001B[49m\u001B[43m=\u001B[49m\u001B[43m[\u001B[49m\u001B[43mtestmodelcb\u001B[49m\u001B[43m]\u001B[49m\u001B[43m)\u001B[49m\n\u001B[32m 24\u001B[39m rediction_probs = model.predict_proba(grid_2d, batch_size=\u001B[32m32\u001B[39m, verbose=\u001B[32m0\u001B[39m)\n\u001B[32m 25\u001B[39m make_plot(X_test, y_test, \u001B[33m\"\u001B[39m\u001B[33mKeras Model\u001B[39m\u001B[33m\"\u001B[39m, file_name=\u001B[38;5;28;01mNone\u001B[39;00m, XX=XX, YY=YY, preds=prediction_probs)\n", - "\u001B[36mFile \u001B[39m\u001B[32m~/projects/nn-from-scratch/.venv/lib/python3.13/site-packages/keras/src/utils/traceback_utils.py:122\u001B[39m, in \u001B[36mfilter_traceback..error_handler\u001B[39m\u001B[34m(*args, **kwargs)\u001B[39m\n\u001B[32m 119\u001B[39m filtered_tb = _process_traceback_frames(e.__traceback__)\n\u001B[32m 120\u001B[39m \u001B[38;5;66;03m# To get the full stack trace, call:\u001B[39;00m\n\u001B[32m 121\u001B[39m \u001B[38;5;66;03m# `keras.config.disable_traceback_filtering()`\u001B[39;00m\n\u001B[32m--> \u001B[39m\u001B[32m122\u001B[39m \u001B[38;5;28;01mraise\u001B[39;00m e.with_traceback(filtered_tb) \u001B[38;5;28;01mfrom\u001B[39;00m\u001B[38;5;250m \u001B[39m\u001B[38;5;28;01mNone\u001B[39;00m\n\u001B[32m 123\u001B[39m \u001B[38;5;28;01mfinally\u001B[39;00m:\n\u001B[32m 124\u001B[39m \u001B[38;5;28;01mdel\u001B[39;00m filtered_tb\n", - "\u001B[36mCell\u001B[39m\u001B[36m \u001B[39m\u001B[32mIn[110]\u001B[39m\u001B[32m, line 5\u001B[39m, in \u001B[36mcallback_keras_plot\u001B[39m\u001B[34m(epoch, logs)\u001B[39m\n\u001B[32m 3\u001B[39m file_name = \u001B[33m\"\u001B[39m\u001B[33mkeras_model_\u001B[39m\u001B[38;5;132;01m{:05}\u001B[39;00m\u001B[33m.png\u001B[39m\u001B[33m\"\u001B[39m.format(epoch)\n\u001B[32m 4\u001B[39m file_path = os.path.join(OUTPUT_DIR, file_name)\n\u001B[32m----> \u001B[39m\u001B[32m5\u001B[39m prediction_probs = \u001B[43mmodel\u001B[49m\u001B[43m.\u001B[49m\u001B[43mpredict_proba\u001B[49m(grid_2d, batch_size=\u001B[32m32\u001B[39m, verbose=\u001B[32m0\u001B[39m)\n\u001B[32m 6\u001B[39m make_plot(X_test, y_test, plot_title, file_name=file_path, XX=XX, YY=YY, preds=prediction_probs)\n", - "\u001B[31mAttributeError\u001B[39m: 'Sequential' object has no attribute 'predict_proba'" - ] + "data": { + "text/plain": [ + "
" + ], + "image/png": "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" + }, + "metadata": {}, + "output_type": "display_data", + "jetTransient": { + "display_id": null + } } ], - "execution_count": 110 + "execution_count": 69 } ], "metadata": {