Daniel Voigt Godoy - Deep Learning with PyTorch Step-by-Step A Beginner’s Guide-leanpub
Figure 3.13 - Using a low thresholdYou can see in the figure above that lowering the threshold (moving it to the lefton the probability line) turned one false negative into a true positive (blue pointclose to 0.4), but it also turned one true negative into a false positive (red pointclose to 0.4).Let’s double-check it with Scikit-Learn’s confusion matrix:confusion_matrix(y_val, (probabilities_val >= 0.3))Outputarray([[ 6, 3],[ 0, 11]])OK, now let’s plot the corresponding metrics one more time:Figure 3.14 - Trade-offs for two different thresholdsStill not a curve, I know, but we can already learn something from these two points.Classification Threshold | 251
Lowering the threshold moves you to the right along bothcurves.Let’s move to the other side now.High ThresholdWhat about 70%? If the predicted probability is greater than or equal to 70%, weclassify the data point as positive, and as negative otherwise. That’s a very strictthreshold since we require the model to be very confident to consider a data pointto be positive. What can we expect from it? Fewer false positives, more falsenegatives.Figure 3.15 - Using a high thresholdYou can see in the figure above that raising the threshold (moving it to the right onthe probability line) turned two false positives into true negatives (red pointsclose to 0.6), but it also turned one true positive into a false negative (blue pointclose to 0.6).Let’s double-check it with Scikit-Learn’s confusion matrix:confusion_matrix(y_val, (probabilities_val >= 0.7))Outputarray([[9, 0],[2, 9]])OK, now let’s plot the corresponding metrics again:252 | Chapter 3: A Simple Classification Problem
- Page 226 and 227: OutputOrderedDict([('0.weight', ten
- Page 228 and 229: Run - Data Preparation V21 # %load
- Page 230 and 231: • defining our StepByStep class
- Page 232 and 233: import numpy as npimport torchimpor
- Page 234 and 235: Next, we’ll standardize the featu
- Page 236 and 237: Equation 3.1 - A linear regression
- Page 238 and 239: The odds ratio is given by the rati
- Page 240 and 241: As expected, probabilities that add
- Page 242 and 243: Sigmoid Functiondef sigmoid(z):retu
- Page 244 and 245: A picture is worth a thousand words
- Page 246 and 247: OutputOrderedDict([('linear.weight'
- Page 248 and 249: The first summation adds up the err
- Page 250 and 251: IMPORTANT: Make sure to pass the pr
- Page 252 and 253: To make it clear: In this chapter,
- Page 254 and 255: argument of nn.BCEWithLogitsLoss().
- Page 256 and 257: It is not that hard, to be honest.
- Page 258 and 259: Figure 3.6 - Training and validatio
- Page 260 and 261: Outputarray([[0.5504593 ],[0.949995
- Page 262 and 263: decision boundary.Look at the expre
- Page 264 and 265: Are my data points separable?That
- Page 266 and 267: model = nn.Sequential()model.add_mo
- Page 268 and 269: It looks like this:Figure 3.10 - Sp
- Page 270 and 271: True and False Positives and Negati
- Page 272 and 273: tpr_fpr(cm_thresh50)Output(0.909090
- Page 274 and 275: The trade-off between precision and
- Page 278 and 279: Figure 3.16 - Trade-offs for two di
- Page 280 and 281: thresholds do not necessarily inclu
- Page 282 and 283: actual data, it is as bad as it can
- Page 284 and 285: If you want to learn more about bot
- Page 286 and 287: Model Training1 n_epochs = 10023 sb
- Page 288 and 289: step in your journey! What’s next
- Page 290 and 291: Chapter 4Classifying ImagesSpoilers
- Page 292 and 293: Data GenerationOur images are quite
- Page 294 and 295: Images and ChannelsIn case you’re
- Page 296 and 297: image_rgb = np.stack([image_r, imag
- Page 298 and 299: That’s fairly straightforward; we
- Page 300 and 301: • Transformations based on Tensor
- Page 302 and 303: position of an object in a picture
- Page 304 and 305: Outputtensor([[[0., 0., 0., 1., 0.]
- Page 306 and 307: Outputtensor([[[-1., -1., -1., 1.,
- Page 308 and 309: We can convert the former into the
- Page 310 and 311: composer = Compose([RandomHorizonta
- Page 312 and 313: Output<torch.utils.data.dataset.Sub
- Page 314 and 315: train_composer = Compose([RandomHor
- Page 316 and 317: The minority class should have the
- Page 318 and 319: train_loader = DataLoader(dataset=t
- Page 320 and 321: implemented in Chapter 2.1? Let’s
- Page 322 and 323: Let’s take one mini-batch of imag
- Page 324 and 325: What does our model look like? Visu
Figure 3.13 - Using a low threshold
You can see in the figure above that lowering the threshold (moving it to the left
on the probability line) turned one false negative into a true positive (blue point
close to 0.4), but it also turned one true negative into a false positive (red point
close to 0.4).
Let’s double-check it with Scikit-Learn’s confusion matrix:
confusion_matrix(y_val, (probabilities_val >= 0.3))
Output
array([[ 6, 3],
[ 0, 11]])
OK, now let’s plot the corresponding metrics one more time:
Figure 3.14 - Trade-offs for two different thresholds
Still not a curve, I know, but we can already learn something from these two points.
Classification Threshold | 251