1 00:00:00,890 --> 00:00:08,520 ‫Our next step is to create architecture for our model, we will be using almost the same architecture. 2 00:00:09,120 --> 00:00:11,890 ‫We will be using sequential keras api. 3 00:00:12,360 --> 00:00:15,630 ‫And we will be adding four con layer. 4 00:00:15,930 --> 00:00:17,980 ‫We will start with 32 filters. 5 00:00:18,240 --> 00:00:19,740 ‫Then 64 filters. 6 00:00:19,920 --> 00:00:21,480 ‫Then 128 filters. 7 00:00:21,810 --> 00:00:23,880 ‫Then again, 128 filters. 8 00:00:25,780 --> 00:00:28,660 ‫And after each of this con layer, we will. 9 00:00:29,080 --> 00:00:31,080 ‫We are also applying pooling layer. 10 00:00:33,370 --> 00:00:37,840 ‫And as always, the activation function is the RELU for all these layers. 11 00:00:39,430 --> 00:00:43,630 ‫And after that, this time, we are also applying dropout layer. 12 00:00:46,080 --> 00:00:55,650 ‫So what this layer will do is it will deactivate 50 percent of neurons during each epoch. 13 00:00:56,490 --> 00:01:01,170 ‫It will randomly pick 50 percent of our neurons and it will deactivate them. 14 00:01:01,770 --> 00:01:08,190 ‫And we will be training model with the remaining 50 percent of neurons during each epoch. 15 00:01:08,910 --> 00:01:15,860 ‫So for each epoch, we are activating randomly 50 percent of our total neurons. 16 00:01:17,720 --> 00:01:24,780 ‫We are using dropout here because dropout is a very effective layer to avoid overfitting in our model 17 00:01:24,780 --> 00:01:24,990 ‫. 18 00:01:28,290 --> 00:01:30,710 ‫So this is our a model architecture. 19 00:01:32,390 --> 00:01:34,670 ‫Now, the next step is to compile 20 00:01:35,660 --> 00:01:38,650 ‫For lost function, we will be using binary cross entropy. 21 00:01:39,050 --> 00:01:41,030 ‫Since we have two different classes. 22 00:01:42,640 --> 00:01:50,860 ‫If you remember earlier in mnist, we had 10 different classes and there we were using sparce categorical 23 00:01:51,250 --> 00:01:52,100 ‫Cross entropy. 24 00:01:52,750 --> 00:01:59,040 ‫But here, since we have one the two classes, we are using binary Cross entropy for optimizer 25 00:01:59,050 --> 00:01:59,260 ‫. 26 00:01:59,410 --> 00:02:03,820 ‫We are using rms prop with learning rate of zero point zero zero one. 27 00:02:05,120 --> 00:02:10,390 ‫And since this is a classification problem, we are calculating accuracy metrics as well. 28 00:02:13,590 --> 00:02:16,140 ‫The next step is to train our model. 29 00:02:17,830 --> 00:02:26,390 ‫Since we are taking our data from train generator, we have to use fit generator to fit our model. 30 00:02:26,530 --> 00:02:31,240 ‫So we'll be using model dot fit generator, then train generator 31 00:02:32,270 --> 00:02:39,370 ‫This the data generator, which will continuously generate data in the batches of 32 images. 32 00:02:41,120 --> 00:02:44,950 ‫And then here we are using steps per Epoch as hundred. 33 00:02:46,970 --> 00:02:51,510 ‫Earlier in our last model, we were using a batch size of 20 steps. 34 00:02:51,680 --> 00:02:57,120 ‫Per Epoch as hundred because we only had 2000 images 35 00:02:57,140 --> 00:02:58,550 ‫For training purposes. 36 00:02:59,420 --> 00:03:07,880 ‫But this time, since we are randomly generating images from this transformation, we can use more than 37 00:03:08,160 --> 00:03:09,680 ‫2000 images as well. 38 00:03:10,370 --> 00:03:16,060 ‫This time we are using a batch size of 32 and steps per epoch as hundred. 39 00:03:16,770 --> 00:03:22,850 ‫So overall, in each epoch we are feeding around three thousand two hundred images. 40 00:03:25,270 --> 00:03:28,780 ‫The number of epochs this time is hundred. 41 00:03:30,240 --> 00:03:36,450 ‫And similarly, we will use validation generator to get the validation data. 42 00:03:39,090 --> 00:03:46,050 ‫Now, since we are running this four hundred epochs, if you are using a system with less than 16 43 00:03:46,050 --> 00:03:52,050 ‫Gb of RAM and without any graphics card, it may take up to one and half to two hours to create 44 00:03:52,050 --> 00:03:52,580 ‫this model. 45 00:03:55,020 --> 00:04:01,980 ‫That's why I have already train this model and I have the data of over hundred epochs here. 46 00:04:04,230 --> 00:04:13,740 ‫You can see that our validation accuracy is increasing with each epoch and at around ninety two hundred 47 00:04:13,820 --> 00:04:14,110 ‫Epoch 48 00:04:14,160 --> 00:04:20,340 ‫We are getting a validation accuracy between 82 to 84 percent and. 49 00:04:21,440 --> 00:04:25,650 ‫A training accuracy of around 84 to 85 percent 50 00:04:26,940 --> 00:04:35,190 ‫So if you compare in our last model, we were getting training accuracy of around 95 to 98 percent 51 00:04:36,000 --> 00:04:41,140 ‫and a significantly lower validation accuracy of our own 79 percent. 52 00:04:42,690 --> 00:04:49,460 ‫In this model, we are getting almost same validation and our training accuracy of around 84 percent. 53 00:04:51,370 --> 00:05:00,070 ‫So you can say that with our image pre processing and creating dummy images we have treated over fitting 54 00:05:00,160 --> 00:05:00,910 ‫in our model 55 00:05:03,660 --> 00:05:11,220 ‫After running this, you can save your model by model dot save method and lets just create this graph 56 00:05:12,150 --> 00:05:18,150 ‫to see how our validation accuracy and training accuracy are changing with each epoch. 57 00:05:20,160 --> 00:05:23,280 ‫So this orange and red lines are for accuracy. 58 00:05:24,240 --> 00:05:28,950 ‫This orange line is for training accuracy and red line is for validation accuracy. 59 00:05:30,510 --> 00:05:36,600 ‫You can see here that the validation accuracy is more than 80 percent as well as the training. 60 00:05:36,600 --> 00:05:38,760 ‫Accuracy is also more than 80 percent. 61 00:05:40,320 --> 00:05:42,560 ‫And both are moving together. 62 00:05:42,720 --> 00:05:45,420 ‫So there are no evidence of overfitting. 63 00:05:45,660 --> 00:05:46,890 ‫In our model 64 00:05:48,690 --> 00:05:50,670 ‫And this is still increasing. 65 00:05:51,090 --> 00:06:00,930 ‫So if you run it for, say, 40 or 50 more epochs, the validation accuracy may reach around 85, 86 66 00:06:00,930 --> 00:06:01,820 ‫percent as well. 67 00:06:03,760 --> 00:06:05,230 ‫So that's all for this video. 68 00:06:06,310 --> 00:06:14,620 ‫We see that by augmenting our initial dataset, by applying sheer rotation, width shift, height, shift 69 00:06:15,120 --> 00:06:15,910 ‫And flips 70 00:06:16,480 --> 00:06:24,590 ‫We can treat overfitting fitting in our data and we can get a higher valuation accuracy from our model. 71 00:06:25,180 --> 00:06:25,630 ‫Thank you.