up

Author: geraldb

README.md

@@ -106,4 +106,45 @@ To eval(uate) the trained model use:
 
 
 
-That's it.
+That's it.
+
+
+
+## Bonus - AlexNet (Anno 2012) - From 61,706 Weights to 61,100,840
+
+
+The award-winning AlexNet is basically a LeNet5 scaled up 1000x and
+introduces relu activation, dropout layers, and more to the world (of deep neural networks).
+The summary of the model reads:
+
+
+```
+----------------------------------------------------------------
+        Layer (type)               Output Shape         Param #
+================================================================
+            Conv2d-1           [-1, 64, 55, 55]          23,296
+              ReLU-2           [-1, 64, 55, 55]               0
+         MaxPool2d-3           [-1, 64, 27, 27]               0
+            Conv2d-4          [-1, 192, 27, 27]         307,392
+              ReLU-5          [-1, 192, 27, 27]               0
+         MaxPool2d-6          [-1, 192, 13, 13]               0
+            Conv2d-7          [-1, 384, 13, 13]         663,936
+              ReLU-8          [-1, 384, 13, 13]               0
+            Conv2d-9          [-1, 256, 13, 13]         884,992
+             ReLU-10          [-1, 256, 13, 13]               0
+           Conv2d-11          [-1, 256, 13, 13]         590,080
+             ReLU-12          [-1, 256, 13, 13]               0
+        MaxPool2d-13            [-1, 256, 6, 6]               0
+AdaptiveAvgPool2d-14            [-1, 256, 6, 6]               0
+          Dropout-15                 [-1, 9216]               0
+           Linear-16                 [-1, 4096]      37,752,832
+             ReLU-17                 [-1, 4096]               0
+          Dropout-18                 [-1, 4096]               0
+           Linear-19                 [-1, 4096]      16,781,312
+             ReLU-20                 [-1, 4096]               0
+           Linear-21                 [-1, 1000]       4,097,000
+================================================================
+Total params: 61,100,840
+```
+
+

alexnet/SUMMARY.md

@@ -0,0 +1,82 @@
+# Summary
+
+to generate - try
+
+    $ python ./models.py
+
+resulting in:
+
+## AlexNet  input_size=(3, 224, 224)
+
+```
+AlexNet(
+  (features): Sequential(
+    (0): Conv2d(3, 64, kernel_size=(11, 11), stride=(4, 4), padding=(2, 2))
+    (1): ReLU(inplace=True)
+    (2): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
+    (3): Conv2d(64, 192, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
+    (4): ReLU(inplace=True)
+    (5): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
+    (6): Conv2d(192, 384, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (7): ReLU(inplace=True)
+    (8): Conv2d(384, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (9): ReLU(inplace=True)
+    (10): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
+    (11): ReLU(inplace=True)
+    (12): MaxPool2d(kernel_size=3, stride=2, padding=0, dilation=1, ceil_mode=False)
+  )
+  (avgpool): AdaptiveAvgPool2d(output_size=(6, 6))
+  (classifier): Sequential(
+    (0): Dropout(p=0.5, inplace=False)
+    (1): Linear(in_features=9216, out_features=4096, bias=True)
+    (2): ReLU(inplace=True)
+    (3): Dropout(p=0.5, inplace=False)
+    (4): Linear(in_features=4096, out_features=4096, bias=True)
+    (5): ReLU(inplace=True)
+    (6): Linear(in_features=4096, out_features=1000, bias=True)
+  )
+)
+
+Total number of trainable model parameters: 61100840
+about  231.27 MBs, 237746.46 KBs
+
+----------------------------------------------------------------
+        Layer (type)               Output Shape         Param #
+================================================================
+            Conv2d-1           [-1, 64, 55, 55]          23,296
+              ReLU-2           [-1, 64, 55, 55]               0
+         MaxPool2d-3           [-1, 64, 27, 27]               0
+            Conv2d-4          [-1, 192, 27, 27]         307,392
+              ReLU-5          [-1, 192, 27, 27]               0
+         MaxPool2d-6          [-1, 192, 13, 13]               0
+            Conv2d-7          [-1, 384, 13, 13]         663,936
+              ReLU-8          [-1, 384, 13, 13]               0
+            Conv2d-9          [-1, 256, 13, 13]         884,992
+             ReLU-10          [-1, 256, 13, 13]               0
+           Conv2d-11          [-1, 256, 13, 13]         590,080
+             ReLU-12          [-1, 256, 13, 13]               0
+        MaxPool2d-13            [-1, 256, 6, 6]               0
+AdaptiveAvgPool2d-14            [-1, 256, 6, 6]               0
+          Dropout-15                 [-1, 9216]               0
+           Linear-16                 [-1, 4096]      37,752,832
+             ReLU-17                 [-1, 4096]               0
+          Dropout-18                 [-1, 4096]               0
+           Linear-19                 [-1, 4096]      16,781,312
+             ReLU-20                 [-1, 4096]               0
+           Linear-21                 [-1, 1000]       4,097,000
+================================================================
+Total params: 61,100,840
+Trainable params: 61,100,840
+Non-trainable params: 0
+----------------------------------------------------------------
+Input size (MB): 0.57
+Forward/backward pass size (MB): 8.38
+Params size (MB): 233.08
+Estimated Total Size (MB): 242.03
+----------------------------------------------------------------
+```
+
+
+
+
+

alexnet/eval.py

@@ -0,0 +1,82 @@
+import torch
+from torchvision import transforms
+from PIL import Image
+
+
+### local imports
+from model import model
+
+
+
+path = './files/coffee.jpg'
+# path = './files/cat.jpg'
+# path = './files/stephansdom.jpg'
+
+
+img = Image.open( path )
+
+
+transform = transforms.Compose([
+  transforms.Resize(256),
+  transforms.CenterCrop(224),   # 224x224
+  transforms.ToTensor(),
+  transforms.Normalize(
+      mean=[0.485, 0.456, 0.406],
+      std=[0.229, 0.224, 0.225])])
+
+img_tensor = transform(img)
+batch = torch.unsqueeze(img_tensor, dim=0)
+
+
+model.eval()
+y = model(batch)
+
+y_max, index = torch.max(y,dim=1)
+
+with open('./files/imagenet_class_labels.txt') as f:
+  classes = [line.strip() for line in f.readlines()]
+
+prob = torch.nn.functional.softmax(y, dim=1)[0]
+print( classes[index[0]], prob[index[0]].item())
+print()
+#=> 967: 'espresso', 0.8799548745155334
+
+y_sort, indices = torch.sort(y, descending=True)
+for idx in indices[0][:5]:
+  print(classes[idx], prob[idx].item())
+#=> 967: 'espresso',     0.8799548745155334
+#   968: 'cup',          0.07688959687948227
+#   504: 'coffee mug',   0.038615722209215164
+#   925: 'consomme',     0.0035129631869494915
+#   960: 'chocolate sauce, chocolate syrup', 0.0005007769796065986
+
+
+print( "bye" )
+
+
+"""
+try with
+
+    path = './files/cat.jpg'
+
+resulting in
+
+    283: 'Persian cat',       0.31462812423706055
+    552: 'feather boa, boa',  0.21569392085075378
+    285: 'Egyptian cat',      0.17547936737537384
+    281: 'tabby, tabby cat',  0.03902266174554825
+    262: 'Brabancon griffon', 0.031412456184625626
+
+or with
+
+    path = './files/stephansdom.jpg'
+
+resulting in
+
+    497: 'church, church building', 0.4236260652542114
+    698: 'palace',                  0.2292090207338333
+    663: 'monastery',               0.1675940901041031
+    442: 'bell cote, bell cot',     0.03244597092270851
+    483: 'castle',                  0.024614153429865837
+"""
+