{"id":3412,"date":"2026-06-19T13:17:55","date_gmt":"2026-06-19T11:17:55","guid":{"rendered":"https:\/\/neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/"},"modified":"2026-08-25T13:45:22","modified_gmt":"2026-08-25T11:45:22","slug":"precision-comparison-tensorflow-pytorch-neural-designer","status":"publish","type":"blog","link":"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/","title":{"rendered":"Precision of TensorFlow, PyTorch, and Neural Designer"},"content":{"rendered":"<style>.ndb{width:100vw;margin-left:calc(50% - 50vw);background:#eeeeee;padding:22px 24px 14px;font-family:\"Outfit\",\"Roboto\",Arial,sans-serif;color:#1b2635}.ndb *{box-sizing:border-box}.ndb a{text-decoration:none}.ndb-wrap{width:min(100%,1200px);margin:0 auto}.ndb-lead{font-size:18px;line-height:1.6;color:#3a4a5a;font-weight:300;margin:0 0 22px}.ndb-lead a{color:#2d799f;font-weight:600}.ndb-highlight{margin:0 0 36px;padding:28px 34px;border-radius:18px;background:linear-gradient(135deg,#56a1c8 0%,#245e80 100%);color:#fff;box-shadow:0 16px 34px rgba(30,83,116,.22)}.ndb-highlight p{margin:0;color:#fff;font-size:20px;line-height:1.5;font-weight:400}.ndb-highlight b{font-weight:800}.ndb-toc{list-style:none;display:flex;flex-wrap:wrap;gap:10px;justify-content:center;margin:0 0 42px;padding:0}.ndb-toc a{padding:10px 18px;background:#f2f2f2;border-radius:22px;color:#12354b!important;font-size:14px;font-weight:600;box-shadow:-6px -6px 12px rgba(255,255,255,.9),6px 6px 12px rgba(30,83,116,.10)}.ndb-toc a:hover{color:#2d799f!important}.ndb-card{margin:0 0 42px;padding:0;background:transparent;border-radius:0;box-shadow:none;scroll-margin-top:90px}.ndb-card h2{margin:0 0 20px;padding-bottom:12px;color:#001233;font-size:24px;font-weight:700;position:relative;border-bottom:1px solid #dbe5ec}.ndb-card h2:after{content:\"\";position:absolute;left:0;bottom:-1px;width:62px;height:3px;background:#56a1c8;border-radius:2px}.ndb-card p{margin:0 0 14px;font-size:16.5px;line-height:1.62;color:#33424f}.ndb-card a{color:#2d799f;font-weight:500}.ndb-card ul{margin:0 0 14px;padding-left:22px}.ndb-card li{margin:5px 0;font-size:16px;line-height:1.5;color:#33424f}.ndb-card img:not([src$=\".svg\"]):not([data-src$=\".svg\"]){display:block;width:auto;max-width:min(560px,100%);height:auto;margin:22px auto;border-radius:12px;box-shadow:0 12px 28px rgba(0,18,51,.12)}.ndb-card th img[src$=\".svg\"],.ndb-card th img[data-src$=\".svg\"],.ndb-card img[src$=\".svg\"],.ndb-card img[data-src$=\".svg\"]{display:inline-block;max-width:24px;height:auto;margin:0 6px -4px 0;box-shadow:none}.ndb-card table{border-collapse:separate;border-spacing:0;width:100%;max-width:100%;margin:22px 0;font-size:15px;background:#fbfcfd;border-radius:12px;overflow:hidden;box-shadow:0 10px 24px rgba(0,18,51,.08)}.ndb-card th,.ndb-card td{padding:11px 16px;border-bottom:1px solid #e6ecf0;text-align:left;vertical-align:top}.ndb-card thead th{background:#12354b;color:#fff;font-weight:600;text-align:center}.ndb-card tbody th{background:#e9f1f6;color:#12354b;font-weight:600}.ndb-card td{color:#33424f}.ndb-card table ul{margin:0;padding-left:18px}.ndb-card table li{font-size:14px}.ndb-card pre{margin:22px 0;padding:22px 24px;background:#0b1830!important;color:#e6eef5!important;border-radius:14px;overflow-x:auto;font-family:Consolas,Menlo,monospace;font-size:12.5px;line-height:1.5;white-space:pre}.ndb-card--accent{background:transparent}@media(max-width:820px){.ndb-card{padding:0}.ndb-card h2{font-size:21px}.ndb-toc{gap:8px}}@media(max-width:640px){.ndb{padding:12px 14px}}<\/style><div class=\"ndb\"><div class=\"ndb-wrap\"><div class=\"ndb-lead\"><p><a href=\"https:\/\/tensorflow.org\/\">TensorFlow<\/a>, <a href=\"https:\/\/pytorch.org\/\">PyTorch<\/a> and <a href=\"https:\/\/www.neuraldesigner.com\/\">Neural Designer<\/a>\u00a0are three popular machine learning platforms developed by\u00a0<a href=\"https:\/\/research.google\/teams\/brain\/\">Google<\/a>,\u00a0<a href=\"https:\/\/ai.facebook.com\/research\/\">Facebook<\/a> and\u00a0<a href=\"https:\/\/www.artelnics.com\/\">Artelnics<\/a>, respectively.<\/p>\n<p>Although all those frameworks implement neural networks, they present some important differences in functionality, usability, performance, etc.<\/p>\n<p>Moreover, Neural Designer trains this neural network <b>x5.71<\/b> times faster than TensorFlow and <b>x8.21<\/b> times faster than PyTorch.<\/p>\n<p data-start=\"50\" data-end=\"154\">In this article, we outline all the steps required to reproduce the results using Neural Designer (<a href=\"https:\/\/www.neuraldesigner.com\/downloads\/\">download<\/a>)<\/p>\n<\/div><div class=\"ndb-highlight\"><p>As we will see, the training accuracy of Neural Designer using the Levenberg-Marquardt algorithm is <b>x1.91<\/b> higher than that of TensorFlow and <b>x1.21<\/b> times higher than that of PyTorch using Adam.<\/p>\n<\/div><ul class=\"ndb-toc\"><li><a href=\"#Introduction\">Introduction<\/a><\/li><li><a href=\"#BenchmarkApplication\">Benchmark application<\/a><\/li><li><a href=\"#ReferenceComputer\">Reference computer<\/a><\/li><li><a href=\"#Results\">Results<\/a><\/li><li><a href=\"#Conclusions\">Conclusions<\/a><\/li><\/ul><div class=\"ndb-card\" id=\"Introduction\"><h2>Introduction<\/h2><p>One of the most critical factors in machine learning platforms is their training accuracy.<\/p>\n<p><img decoding=\"async\" style=\"width: 600px;\" src=\"https:\/\/www.neuraldesigner.com\/images\/precision-test.svg\"  alt=\"Precision Test\"\/><\/p>\n<p>This article aims to measure the training accuracies of TensorFlow, PyTorch, and Neural Designer for a benchmark application and compare the speeds obtained by those platforms.<\/p>\n<p>The most important factor for training accuracy is the optimization algorithm used.<\/p>\n<p>The above table shows that TensorFlow and PyTorch are programmed in C++ and Python, while Neural Designer is entirely programmed in C++.<\/p>\n<p>Next, we measure the training accuracy for a benchmark problem on a reference computer using TensorFlow, PyTorch, and Neural Designer. We then compare the results produced by that platforms.<\/p>\n<\/div><div class=\"ndb-card\" id=\"BenchmarkApplication\"><h2>Benchmark application<\/h2><p>The first step is to choose a benchmark application that is general enough to conclude the performance of the machine learning platforms. As previously stated, we will train a neural network that approximates a set of input-target samples.<\/p>\n<p>In this regard, an approximation application comprises a data set, a neural network, and an associated training strategy.<br \/>The next table uniquely defines these three components.<\/p>\n<table>\n<tbody>\n<tr>\n<th>Data set<br \/><img decoding=\"async\" src=\"https:\/\/www.neuraldesigner.com\/images\/data_set.svg\"  alt=\"Data Set\"\/><\/th>\n<td>\n<ul>\n<li>Benchmark: Rosenbrock<\/li>\n<li>Inputs number: 10<\/li>\n<li>Targets number: 1<\/li>\n<li>Samples number: 10000<\/li>\n<li>File size: 2.38 MB<\/li>\n<\/ul>\n<\/td>\n<\/tr>\n<tr>\n<th>Neural network<br \/><img decoding=\"async\" src=\"https:\/\/www.neuraldesigner.com\/images\/neural_network.svg\"  alt=\"Neural Network\"\/><\/th>\n<td>\n<ul>\n<li>Layers number: 2<\/li>\n<li>Layer 1:\n<ul style=\"list-style-type: none;\">\n<li>-Type: Perceptron (Dense)<\/li>\n<li>-Inputs number: 10<\/li>\n<li>-Neurons number: 10<\/li>\n<li>-Activation function: Hyperbolic tangent (tanh)<\/li>\n<\/ul>\n<\/li>\n<li>Layer 2:\n<ul style=\"list-style-type: none;\">\n<li>-Type: Perceptron (Dense)<\/li>\n<li>-Inputs number: 10<\/li>\n<li>-Neurons number: 1<\/li>\n<li>-Activation function: Linear<\/li>\n<\/ul>\n<\/li>\n<li>Initialization: Random uniform [-1,1]<\/li>\n<\/ul>\n<\/td>\n<\/tr>\n<tr>\n<th>Training strategy<br \/><img decoding=\"async\" src=\"https:\/\/www.neuraldesigner.com\/images\/training_strategy.svg\"  alt=\"Training Strategy\"\/><\/th>\n<td>\n<ul>\n<li>Loss index:\n<ul style=\"list-style-type: none;\">\n<li>-Error: Mean Squared Error (MSE)<\/li>\n<li>-Regularization: None<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<ul>\n<li>Optimization algorithm (TensorFlow and PyTorch):\n<ul style=\"list-style-type: none;\">\n<li>-Algorithm: Adaptive Moment Estimation (Adam)<\/li>\n<li>-Batch size: 1000<\/li>\n<li>-Maximum epochs: 10000<\/li>\n<\/ul>\n<\/li>\n<li>Optimization algorithm (Neural Designer):\n<ul style=\"list-style-type: none;\">\n<li>-Algorithm: Levenberg-Marquardt (LM)<\/li>\n<li>-Maximum epochs: 1000<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>Once we have created the TensorFlow, PyTorch, and Neural Designer applications, we need to run them.<\/p>\n<\/div><div class=\"ndb-card\" id=\"ReferenceComputer\"><h2>Reference computer<\/h2><p>The next step is to choose the computer to train the neural networks with TensorFlow, PyTorch, and Neural Designer.<\/p>\n<table>\n<tbody>\n<tr>\n<th>Operating system:<\/th>\n<td>Windows 10 Enterprise<\/td>\n<\/tr>\n<tr>\n<th>Processor:<\/th>\n<td>CPU Intel(R) Xeon(R) Platinum 8259CL CPU @ 2.50GHz<\/td>\n<\/tr>\n<tr>\n<th>Physical RAM:<\/th>\n<td>16.0 GB<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>Once the computer has been chosen, we install TensorFlow (2.1.0), PyTorch (1.7.0), and Neural Designer (5.9.0) on it.<\/p>\n<\/p>\n<pre style=\"margin: 0; line-height: 125%;\">#TENSORFLOW CODE\n                import tensorflow as tf\n                import pandas as pd\n                import time\n                import numpy as np\n                #read data float32\n\tstart_time = time.time() \n\tfilename = \"C:\/R_new.csv\"\n\tdf_test = pd.read_csv(filename, nrows=100)\n\tfloat_cols = [c for c in df_test if df_test[c].dtype == \"float64\"]\n\tfloat32_cols = {c: np.float32 for c in float_cols}\n\tdata = pd.read_csv(filename, engine='c', dtype=float32_cols)\n                print(\"Loading time: \", round(time.time() - start_time), \" seconds\")\n\tx = data.iloc[:,:-1].values\n\ty = data.iloc[:,[-1]].values\n\tinitializer = tf.keras.initializers.RandomUniform(minval=-1., maxval=1.)\n                #build model\n\tmodel = tf.keras.models.Sequential([tf.keras.layers.Dense(1000, \n\t\t\t\t\t\t\t\t\t    activation = 'tanh', \n\t\t\t\t\t\t\t\t\t    kernel_initializer = initializer, \n\t\t\t\t\t\t\t\t\t    bias_initializer=initializer),\n\t\t\t\t\t\t\ttf.keras.layers.Dense(1, \n\t\t\t\t\t\t\t\t\t    activation = 'linear', \n\t\t\t\t\t\t\t\t\t    kernel_initializer = initializer, \n\t\t\t\t\t\t\t\t\t    bias_initializer=initializer)])\n                #compile model\n\tmodel.compile(optimizer='adam', loss = 'mean_squared_error')\n                #train model\n\tstart_time = time.time()\n\thistory = model.fit(x, y, batch_size = 1000, epochs = 1000)\n                print(\"Training time: \", round(time.time() - start_time), \" seconds\")\n            <\/pre>\n<p>Building this application with PyTorch also requires some Python scripting. This code is listed below. Also, you can download <a href=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2025\/07\/Final_pytorch-cpu.py_.zip\">here.<\/a><\/p>\n<pre style=\"margin: 0; line-height: 125%;\">#PYTORCH CODE\t\n            import pandas as pd\n            import time\n            import torch\n            import numpy as np\n            import statistics\n            def init_weights(m):\n            if type(m) == torch.nn.Linear:\t\t\n\t\t\ttorch.nn.init.uniform_(m.weight, a=-1.0, b=1.0)\n\t\t\ttorch.nn.init.uniform_(m.bias.data, a=-1.0, b=1.0)\n\tepoch = 1000\n\ttotal_samples, batch_size, input_variables, hidden_neurons, output_variables = 1000000, 1000, 1000, 1000, 1\n\tdevice = torch.device(\"cuda:0\") \n            # read data float32\n\tstart_time = time.time()\n\tfilename = \"C:\/R_new.csv\"\n\tdf_test = pd.read_csv(filename, nrows=100)\n\tfloat_cols = [c for c in df_test if df_test[c].dtype == \"float64\"]\n\tfloat32_cols = {c: np.float32 for c in float_cols}\n\tdataset = pd.read_csv(filename, engine='c', dtype=float32_cols)\n            print(\"Loading time: \", round(time.time() - start_time), \" seconds\")\n\tx = torch.tensor(dataset.iloc[:,:-1].values, dtype = torch.float32)\n\ty = torch.tensor(dataset.iloc[:,[-1]].values, dtype = torch.float32)\n            # build model\n\tmodel = torch.nn.Sequential(torch.nn.Linear(input_variables, hidden_neurons),\n\t\t\t\t\t\t\t\ttorch.nn.Tanh(),\n\t\t\t\t\t\t\t\ttorch.nn.Linear(hidden_neurons, output_variables)).cuda()\n            # initialize weights\n\tmodel.apply(init_weights)\n            # compile model\n\tlearning_rate = 0.001\n\tloss_fn = torch.nn.MSELoss(reduction = 'mean')\n\toptimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)\n\tindices = np.arange(0,total_samples)\n\tstart = time.time()\n            for j in range(epoch):\n\t\tmse=[]\n\t\tt0 = time.time()\n            for i in range(0, total_samples, batch_size):\n\t\t\tbatch_indices = indices[i:i+batch_size]\n\t\t\tbatch_x, batch_y = x[batch_indices], y[batch_indices]\n\t\t\tbatch_x = batch_x.cuda()\n\t\t\tbatch_y = batch_y.cuda()\n\t\t\toutputs = model.forward(batch_x)\n\t\t\tloss = loss_fn(outputs, batch_y)\n\t\t\tmodel.zero_grad()\n\t\t\tloss.backward()\n\t\t\toptimizer.step()\n\t\t\tmse.append(loss.item())\n            print(\"Epoch:\", j+1,\"\/1000\", \"[================================] - \",\"loss: \", statistics.mean(mse))\n\t\tt1 = time.time() - t0\n            print(\"Elapsed time: \", int(round(t1 )), \"sec\")\n\tend = time.time()\n\telapsed = end - start\n            print(\"Training time: \",int(round(elapsed )), \"seconds\")\n        <\/pre>\n<p>Once the TensorFlow, PyTorch, and Neural Designer applications have been created, we need to run them.<\/p>\n<\/div><div class=\"ndb-card\" id=\"Results\"><h2>Results<\/h2><p>The last step is to run the benchmark application on the selected machine with TensorFlow, PyTorch, and Neural Designer and compare those platforms&#8217; training times.<\/p>\n<p>The next figure shows the training results with <b>TensorFlow<\/b>.<\/p>\n<table>\n<thead>\n<tr>\n<th>Run<\/th>\n<th>Time<\/th>\n<th>MSE<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>1<\/td>\n<td>00:47<\/td>\n<td>0.0587<\/td>\n<\/tr>\n<tr>\n<td>2<\/td>\n<td>00:48<\/td>\n<td>0.0582<\/td>\n<\/tr>\n<tr>\n<td>3<\/td>\n<td>00:48<\/td>\n<td>0.0988<\/td>\n<\/tr>\n<tr>\n<td>4<\/td>\n<td>00:47<\/td>\n<td>0.1012<\/td>\n<\/tr>\n<tr>\n<td>5<\/td>\n<td>00:47<\/td>\n<td>0.0508<\/td>\n<\/tr>\n<tr>\n<td>6<\/td>\n<td>00:48<\/td>\n<td>0.1008<\/td>\n<\/tr>\n<tr>\n<td>7<\/td>\n<td>00:51<\/td>\n<td><b>0.0333<\/b><\/td>\n<\/tr>\n<tr>\n<td>8<\/td>\n<td>00:52<\/td>\n<td>0.0998<\/td>\n<\/tr>\n<tr>\n<td>9<\/td>\n<td>00:50<\/td>\n<td>0.0582<\/td>\n<\/tr>\n<tr>\n<td>10<\/td>\n<td>00:48<\/td>\n<td>0.0454<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>As we can see, the minimum mean squared error by TensorFlow is 0.0333, and the average mean squared error over the ten runs is 0.0705. The average training time is 48.6 seconds.<\/p>\n<p>Similarly, the following figure is a screenshot of <b>PyTorch<\/b> at the end of the process.<\/p>\n<table>\n<thead>\n<tr>\n<th>Run<\/th>\n<th>Time<\/th>\n<th>MSE<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>1<\/td>\n<td>01:15<\/td>\n<td>0.0294<\/td>\n<\/tr>\n<tr>\n<td>2<\/td>\n<td>01:09<\/td>\n<td>0.0474<\/td>\n<\/tr>\n<tr>\n<td>3<\/td>\n<td>01:10<\/td>\n<td>0.0332<\/td>\n<\/tr>\n<tr>\n<td>4<\/td>\n<td>01:08<\/td>\n<td>0.0586<\/td>\n<\/tr>\n<tr>\n<td>5<\/td>\n<td>01:10<\/td>\n<td><b>0.0221<\/b><\/td>\n<\/tr>\n<tr>\n<td>6<\/td>\n<td>01:09<\/td>\n<td>0.0480<\/td>\n<\/tr>\n<tr>\n<td>7<\/td>\n<td>01:12<\/td>\n<td>0.1006<\/td>\n<\/tr>\n<tr>\n<td>8<\/td>\n<td>01:10<\/td>\n<td>0.0332<\/td>\n<\/tr>\n<tr>\n<td>9<\/td>\n<td>01:09<\/td>\n<td>0.0582<\/td>\n<\/tr>\n<tr>\n<td>10<\/td>\n<td>01:06<\/td>\n<td>0.0988<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>In this case, the minimum mean squared error by PyTorch over the ten runs is 0.0221.<br \/>The average mean squared error is 0.0529. The average training time is 69.8 seconds.<\/p>\n<p>Finally, the following figure shows the training results with <b>Neural Designer<\/b>.<\/p>\n<table>\n<thead>\n<tr>\n<th>Run<\/th>\n<th>Time<\/th>\n<th>MSE<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td>1<\/td>\n<td>00:08<\/td>\n<td>0.0196<\/td>\n<\/tr>\n<tr>\n<td>2<\/td>\n<td>00:09<\/td>\n<td>0.0263<\/td>\n<\/tr>\n<tr>\n<td>3<\/td>\n<td>00:08<\/td>\n<td>0.0254<\/td>\n<\/tr>\n<tr>\n<td>4<\/td>\n<td>00:09<\/td>\n<td>0.0191<\/td>\n<\/tr>\n<tr>\n<td>5<\/td>\n<td>00:09<\/td>\n<td>0.0413<\/td>\n<\/tr>\n<tr>\n<td>6<\/td>\n<td>00:09<\/td>\n<td>0.0263<\/td>\n<\/tr>\n<tr>\n<td>7<\/td>\n<td>00:08<\/td>\n<td>0.0397<\/td>\n<\/tr>\n<tr>\n<td>8<\/td>\n<td>00:08<\/td>\n<td><b>0.0174<\/b><\/td>\n<\/tr>\n<tr>\n<td>9<\/td>\n<td>00:08<\/td>\n<td>0.0527<\/td>\n<\/tr>\n<tr>\n<td>10<\/td>\n<td>00:09<\/td>\n<td>0.0521<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>The minimum mean squared error by Neural Designer is 0.0174. The average mean squared error over the ten runs is 0.0320.<br \/>With Neural Designer, the average training time is 8.5 seconds.<\/p>\n<p>The following table summarizes the metrics yield by the three machine learning platforms.<\/p>\n<table>\n<thead>\n<tr>\n<th>\u00a0<\/th>\n<th>TensorFlow<\/th>\n<th>PyTorch<\/th>\n<th>Neural Designer<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<th>Minimum MSE<\/th>\n<td style=\"text-align: right;\">0.0333<\/td>\n<td style=\"text-align: right;\">0.0221<\/td>\n<td style=\"text-align: right;\"><b>0.0174<\/b><\/td>\n<\/tr>\n<tr>\n<th>Average MSE<\/th>\n<td style=\"text-align: right;\">0.0705<\/td>\n<td style=\"text-align: right;\">0.0529<\/td>\n<td style=\"text-align: right;\"><b>0.0320<\/b><\/td>\n<\/tr>\n<tr>\n<th>Average training time<\/th>\n<td style=\"text-align: right;\">48.6 seconds<\/td>\n<td style=\"text-align: right;\">69.8 seconds<\/td>\n<td style=\"text-align: right;\"><b>8.5 seconds<\/b><\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>Finally, the following chart depicts the training accuracies of TensorFlow, PyTorch, and Neural Designer for this case graphically.<\/p>\n<p><img decoding=\"async\" style=\"width: 800px;\" src=\"https:\/\/www.neuraldesigner.com\/images\/precision-comparison.svg\"  alt=\"Precision Comparison\"\/><\/p>\n<p>As we can see, both the minimum and the average mean squared error of Neural Designer using the LM algorithm is smaller than that of TensorFlow and PyTorch using Adam.<\/p>\n<p>Using these metrics, we can say that the precision of Neural Designer for this benchmark is x1.91 times bigger than that of TensorFlow and 1.27 times higher than that of PyTorch.<\/p>\n<p>Regarding the training time, in this benchmark, Neural Designer is about x5.72 times faster than TensorFlow and x8.21 times faster than PyTorch.<\/p>\n<\/div><div class=\"ndb-card ndb-card--accent\" id=\"Conclusions\"><h2>Conclusions<\/h2><p>Neural Designer implements second-order optimizers, such as the quasi-Newton method and the Levenberg-Marquardt algorithm. These algorithms have better convergence properties for small and medium-sized datasets than first-order optimizers, such as Adam.<\/p>\n<p>This results in that, for the benchmark described in this post, the precision of Neural Designer is <b>x1.91<\/b> times faster than that of TensorFlow and <b>x1.27<\/b> times faster than that of PyTorch.<\/p>\n<p>To reproduce these results, <a href=\"https:\/\/www.neuraldesigner.com\/downloads\/\">download\u00a0<\/a>Neural Designer and follow the steps described in this article.<\/p>\n<\/div><\/div><\/div>","protected":false},"author":13,"featured_media":1679,"template":"","categories":[],"tags":[37],"class_list":["post-3412","blog","type-blog","status-publish","has-post-thumbnail","hentry","tag-platforms"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.4 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Precision of TensorFlow, PyTorch, and Neural Designer<\/title>\n<meta name=\"description\" content=\"Compare the training precision of three popular machine learning platforms: TensorFlow, PyTorch, and Neural Designer.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Precision of TensorFlow, PyTorch, and Neural Designer\" \/>\n<meta property=\"og:description\" content=\"Compare the training precision of three popular machine learning platforms: TensorFlow, PyTorch, and Neural Designer.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/\" \/>\n<meta property=\"og:site_name\" content=\"Neural Designer\" \/>\n<meta property=\"article:modified_time\" content=\"2026-08-25T11:45:22+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/precision-comparison.webp\" \/>\n\t<meta property=\"og:image:width\" content=\"1200\" \/>\n\t<meta property=\"og:image:height\" content=\"627\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/webp\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:site\" content=\"@NeuralDesigner\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"6 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/\",\"url\":\"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/\",\"name\":\"Precision of TensorFlow, PyTorch, and Neural Designer\",\"isPartOf\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/precision-comparison.webp\",\"datePublished\":\"2026-06-19T11:17:55+00:00\",\"dateModified\":\"2026-08-25T11:45:22+00:00\",\"description\":\"Compare the training precision of three popular machine learning platforms: TensorFlow, PyTorch, and Neural Designer.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/#primaryimage\",\"url\":\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/precision-comparison.webp\",\"contentUrl\":\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/precision-comparison.webp\",\"width\":1200,\"height\":627,\"caption\":\"Precision comparison chart\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.neuraldesigner.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Blog\",\"item\":\"https:\/\/www.neuraldesigner.com\/blog\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Precision of TensorFlow, PyTorch, and Neural Designer\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.neuraldesigner.com\/#website\",\"url\":\"https:\/\/www.neuraldesigner.com\/\",\"name\":\"Neural Designer\",\"description\":\"Explainable AI Platform\",\"publisher\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.neuraldesigner.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.neuraldesigner.com\/#organization\",\"name\":\"Neural Designer\",\"url\":\"https:\/\/www.neuraldesigner.com\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.neuraldesigner.com\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/05\/logo-neural-1.png\",\"contentUrl\":\"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/05\/logo-neural-1.png\",\"width\":1024,\"height\":223,\"caption\":\"Neural Designer\"},\"image\":{\"@id\":\"https:\/\/www.neuraldesigner.com\/#\/schema\/logo\/image\/\"},\"sameAs\":[\"https:\/\/x.com\/NeuralDesigner\",\"https:\/\/es.linkedin.com\/showcase\/neuraldesigner\/\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Precision of TensorFlow, PyTorch, and Neural Designer","description":"Compare the training precision of three popular machine learning platforms: TensorFlow, PyTorch, and Neural Designer.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/","og_locale":"en_US","og_type":"article","og_title":"Precision of TensorFlow, PyTorch, and Neural Designer","og_description":"Compare the training precision of three popular machine learning platforms: TensorFlow, PyTorch, and Neural Designer.","og_url":"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/","og_site_name":"Neural Designer","article_modified_time":"2026-08-25T11:45:22+00:00","og_image":[{"width":1200,"height":627,"url":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/precision-comparison.webp","type":"image\/webp"}],"twitter_card":"summary_large_image","twitter_site":"@NeuralDesigner","twitter_misc":{"Est. reading time":"6 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/","url":"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/","name":"Precision of TensorFlow, PyTorch, and Neural Designer","isPartOf":{"@id":"https:\/\/www.neuraldesigner.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/#primaryimage"},"image":{"@id":"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/#primaryimage"},"thumbnailUrl":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/precision-comparison.webp","datePublished":"2026-06-19T11:17:55+00:00","dateModified":"2026-08-25T11:45:22+00:00","description":"Compare the training precision of three popular machine learning platforms: TensorFlow, PyTorch, and Neural Designer.","breadcrumb":{"@id":"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/#primaryimage","url":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/precision-comparison.webp","contentUrl":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/06\/precision-comparison.webp","width":1200,"height":627,"caption":"Precision comparison chart"},{"@type":"BreadcrumbList","@id":"https:\/\/www.neuraldesigner.com\/blog\/precision-comparison-tensorflow-pytorch-neural-designer\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.neuraldesigner.com\/"},{"@type":"ListItem","position":2,"name":"Blog","item":"https:\/\/www.neuraldesigner.com\/blog\/"},{"@type":"ListItem","position":3,"name":"Precision of TensorFlow, PyTorch, and Neural Designer"}]},{"@type":"WebSite","@id":"https:\/\/www.neuraldesigner.com\/#website","url":"https:\/\/www.neuraldesigner.com\/","name":"Neural Designer","description":"Explainable AI Platform","publisher":{"@id":"https:\/\/www.neuraldesigner.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.neuraldesigner.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.neuraldesigner.com\/#organization","name":"Neural Designer","url":"https:\/\/www.neuraldesigner.com\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.neuraldesigner.com\/#\/schema\/logo\/image\/","url":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/05\/logo-neural-1.png","contentUrl":"https:\/\/www.neuraldesigner.com\/wp-content\/uploads\/2023\/05\/logo-neural-1.png","width":1024,"height":223,"caption":"Neural Designer"},"image":{"@id":"https:\/\/www.neuraldesigner.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/NeuralDesigner","https:\/\/es.linkedin.com\/showcase\/neuraldesigner\/"]}]}},"_links":{"self":[{"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/blog\/3412","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/blog"}],"about":[{"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/types\/blog"}],"author":[{"embeddable":true,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/users\/13"}],"version-history":[{"count":8,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/blog\/3412\/revisions"}],"predecessor-version":[{"id":23541,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/blog\/3412\/revisions\/23541"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/media\/1679"}],"wp:attachment":[{"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/media?parent=3412"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/categories?post=3412"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.neuraldesigner.com\/api\/wp\/v2\/tags?post=3412"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}