HarisIqbal88 / PlotNeuralNet

Latex code for making neural networks diagrams
MIT License
21.54k stars 2.83k forks source link

I want to draw my architecture, what should I do? #153

Open Viet0904 opened 4 months ago

Viet0904 commented 4 months ago

NUM_CLASSES = 8

model = models.Sequential( [ layers.Conv2D(32, (3, 3), input_shape=(224, 224, 3)), layers.BatchNormalization(), layers.Activation("relu"), layers.MaxPooling2D((2, 2)), layers.Conv2D(64, (3, 3)), layers.BatchNormalization(), layers.Activation("relu"), layers.MaxPooling2D((2, 2)), layers.Conv2D(128, (3, 3)), layers.BatchNormalization(), layers.Activation("relu"), layers.MaxPooling2D((2, 2)), layers.Flatten(), layers.Dense(512), layers.BatchNormalization(), layers.Activation("relu"), layers.Dropout(0.5), layers.Dense(NUM_CLASSES, activation="softmax"), ] ) Above is my architecture. Tôi đã thay thử

defined your arch

arch = [ to_head(".."), to_cor(), to_begin(), to_Conv( "conv1", 224, 32, offset="(0,0,0)", to="(0,0,0)", height=40, depth=40, width=2 ), to_Pool("pool1", offset="(0,0,0)", to="(conv1-east)"), to_Conv( "conv2", 196, 64, offset="(2,0,0)", to="(pool1-east)", height=40, depth=40, width=2, ), to_Pool("pool2", offset="(0,0,0)", to="(conv2-east)", height=36, depth=36, width=1), to_Conv( "conv3", 168, 128, offset="(2,0,0)", to="(pool2-east)", height=36, depth=36, width=2, ), to_Pool("pool3", offset="(0,0,0)", to="(conv3-east)", height=32, depth=32, width=1), to_Conv( "flatten", 16, 1, offset="(2,0,0)", to="(pool3-east)", height=1, depth=1, width=2, ), to_Dense( "dense1", 512, offset="(2,0,0)", to="(flatten-east)", height=64, depth=64, width=2, ), to_Dropout("dropout1", "(1,0,0)", "(dense1-east)", caption="Dropout"), to_SoftMax("softmax", 8, "(1,0,0)", "(dropout1-east)", caption="Softmax"), to_end(), ] and it doesn't seem right. Someone please help me