diff --git a/results/index.md b/results/index.md
index 96ce61c..58fd929 100644
--- a/results/index.md
+++ b/results/index.md
@@ -1,47 +1,85 @@
-# Your Name (id)
+# 楊皓崴 (0656706)
-#Project 5: Deep Classification
+#Project 1: Deep Classification
## Overview
The project is related to
-> quote
+> [ImageNet Classification with Deep Convolutional Neural Networks](https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks)
## Implementation
-1. One
- * item
- * item
-2. Two
+1. 前處理
+圖檔過大容易耗盡deepQ資源，故將長寬縮小24倍(45*80)
+整理成一般分類問題資料儲存之
-```
-Code highlights
-```
+```python
+ file = os.path.join(path4,"Image"+str(fileN)+".png")
+ pngfile = Image.open(file)
+ pngfile.thumbnail(size, Image.ANTIALIAS)
+ temp = np.asarray( pngfile, dtype="uint8" )
+```
+
+2. 模型結構
+ * conv layers (3*3 filter) *3
+ * fully connect *2
+
+```python
+ def alex_net(_X, _weights, _biases, _dropout):
+ _X = tf.reshape(_X, shape=[-1, 45, 80, 3])
+
+ conv1 = conv2d('conv1', _X, _weights['wc1'], _biases['bc1'])
+ pool1 = max_pool('pool1', conv1, k=2)
+ norm1 = norm('norm1', pool1, lsize=4)
+ norm1 = tf.nn.dropout(norm1, _dropout)
+
+ conv2 = conv2d('conv2', norm1, _weights['wc2'], _biases['bc2'])
+ pool2 = max_pool('pool2', conv2, k=2)
+ norm2 = norm('norm2', pool2, lsize=4)
+ norm2 = tf.nn.dropout(norm2, _dropout)
+
+ conv3 = conv2d('conv3', norm2, _weights['wc3'], _biases['bc3'])
+ pool3 = max_pool('pool3', conv3, k=2)
+ norm3 = norm('norm3', pool3, lsize=4)
+ norm3 = tf.nn.dropout(norm3, _dropout)
+
+ dense1 = tf.reshape(norm3, [-1, _weights['wd1'].get_shape().as_list()[0]])
+ dense1 = tf.nn.relu(tf.matmul(dense1, _weights['wd1']) + _biases['bd1'], name='fc1')
+
+ dense2 = tf.nn.relu(tf.matmul(dense1, _weights['wd2']) + _biases['bd2'], name='fc2')
+
+ out = tf.matmul(dense2, _weights['out']) + _biases['out']
+ return out
+```
## Installation
-* Other required packages.
-* How to compile from source?
+* Required packages.
+ * tensorflow
+ * numpy
+* How to compile from source?
+ * python preprocessing.py
+ * python process01.py / python process02.py
### Results
-
-
-
-
+process01.py
+ |
+
+process02.py
|
-
-
-
-
+
+ |
+
+
|
-
+嘗試增加conv層數，但沒有效果，猜測圖片縮小過多所致，但操作時間過久來不及嘗試其他尺寸..
diff --git a/results/output01.PNG b/results/output01.PNG
new file mode 100644
index 0000000..112564e
Binary files /dev/null and b/results/output01.PNG differ
diff --git a/results/output02.PNG b/results/output02.PNG
new file mode 100644
index 0000000..8511907
Binary files /dev/null and b/results/output02.PNG differ
diff --git a/results/preprocessing.py b/results/preprocessing.py
new file mode 100644
index 0000000..be6dafd
--- /dev/null
+++ b/results/preprocessing.py
@@ -0,0 +1,74 @@
+import numpy as np
+from PIL import Image
+import os
+
+path0 = "frames"
+testData = None
+trainData = None
+testLabel = None
+trainLabel = None
+size = 1920/24, 1080/24
+lr = None
+for train_test in os.listdir(path0):
+ path1 = os.path.join(path0, train_test)
+ for site in os.listdir(path1):
+ path2 = os.path.join(path1, site)
+ for num in os.listdir(path2):
+ path3 = os.path.join(path2, num)
+ for LR in os.listdir(path3):
+ if LR == "head":
+ continue
+ elif LR == "Lhand":
+ lr = "left"
+ else:
+ lr = "right"
+ path4 = os.path.join(path3, LR)
+ print(path4)
+
+ for fileN in range(1,len(os.listdir(path4))+1):
+ file = os.path.join(path4,"Image"+str(fileN)+".png")
+ pngfile = Image.open(file)
+ pngfile.thumbnail(size, Image.ANTIALIAS)
+ temp = np.asarray( pngfile, dtype="uint8" )
+ if train_test == "train":
+ if trainData is None:
+ trainData = temp.reshape([1,-1])
+ else:
+ trainData = np.concatenate([trainData,temp.reshape([1,-1])])
+ else:
+ if testData is None:
+ testData = temp.reshape([1,-1])
+ else:
+ testData = np.concatenate([testData,temp.reshape([1,-1])])
+
+ if train_test == "train":
+ lfile = os.path.join("labels", site, "obj_"+lr+num+".npy")
+ temp = np.load(lfile).astype(np.int8)
+ if trainLabel is None:
+ trainLabel = temp[:len(os.listdir(path4))]
+ else:
+ trainLabel = np.append(trainLabel, temp[:len(os.listdir(path4))])
+ print(trainData.shape, trainLabel.shape)
+ else:
+ if site == "lab":
+ lfile = os.path.join("labels", site, "obj_"+lr+str(int(num)+4)+".npy")
+ else:
+ lfile = os.path.join("labels", site, "obj_"+lr+str(int(num)+3)+".npy")
+ temp = np.load(lfile).astype(np.int8)
+ if testLabel is None:
+ testLabel = temp[:len(os.listdir(path4))]
+ else:
+ testLabel = np.append(testLabel, temp[:len(os.listdir(path4))])
+ print(testData.shape, testLabel.shape)
+
+b = np.zeros((testLabel.shape[0], 24))
+b[np.arange(testLabel.shape[0]), testLabel] = 1
+testLabel = b
+b = np.zeros((trainLabel.shape[0], 24))
+b[np.arange(trainLabel.shape[0]), trainLabel] = 1
+trainLabel = b
+print(testData.shape, trainData.shape, testLabel.shape, trainLabel.shape)
+np.save("testData",testData)
+np.save("trainData",trainData)
+np.save("testLabel",testLabel)
+np.save("trainLabel",trainLabel)
\ No newline at end of file
diff --git a/results/process01.py b/results/process01.py
new file mode 100644
index 0000000..c316c08
--- /dev/null
+++ b/results/process01.py
@@ -0,0 +1,122 @@
+import numpy as np
+import os
+import tensorflow as tf
+
+env = os.environ.get('GRAPE_DATASET_DIR')
+testData = np.load(os.path.join(env,"testData.npy"))
+trainData = np.load(os.path.join(env,"trainData.npy"))
+testLabel = np.load(os.path.join(env,"testLabel.npy"))
+trainLabel = np.load(os.path.join(env,"trainLabel.npy"))
+
+learning_rate = 0.001
+training_iters = 200
+
+n_input = 45*80*3
+n_classes = 24
+dropout = 0.8
+
+x = tf.placeholder(tf.float32, [None, n_input])
+y = tf.placeholder(tf.float32, [None, n_classes])
+keep_prob = tf.placeholder(tf.float32)
+
+def conv2d(name, l_input, w, b):
+ return tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(l_input, w, strides=[1, 1, 1, 1], padding='SAME'),b), name=name)
+
+def max_pool(name, l_input, k):
+ return tf.nn.max_pool(l_input, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME', name=name)
+
+def norm(name, l_input, lsize=4):
+ return tf.nn.lrn(l_input, lsize, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name=name)
+
+def alex_net(_X, _weights, _biases, _dropout):
+ _X = tf.reshape(_X, shape=[-1, 45, 80, 3])
+
+ conv1 = conv2d('conv1', _X, _weights['wc1'], _biases['bc1'])
+ pool1 = max_pool('pool1', conv1, k=2)
+ norm1 = norm('norm1', pool1, lsize=4)
+ norm1 = tf.nn.dropout(norm1, _dropout)
+
+ conv2 = conv2d('conv2', norm1, _weights['wc2'], _biases['bc2'])
+ pool2 = max_pool('pool2', conv2, k=2)
+ norm2 = norm('norm2', pool2, lsize=4)
+ norm2 = tf.nn.dropout(norm2, _dropout)
+
+ conv3 = conv2d('conv3', norm2, _weights['wc3'], _biases['bc3'])
+ pool3 = max_pool('pool3', conv3, k=2)
+ norm3 = norm('norm3', pool3, lsize=4)
+ norm3 = tf.nn.dropout(norm3, _dropout)
+
+ dense1 = tf.reshape(norm3, [-1, _weights['wd1'].get_shape().as_list()[0]])
+ dense1 = tf.nn.relu(tf.matmul(dense1, _weights['wd1']) + _biases['bd1'], name='fc1')
+
+ dense2 = tf.nn.relu(tf.matmul(dense1, _weights['wd2']) + _biases['bd2'], name='fc2')
+
+ out = tf.matmul(dense2, _weights['out']) + _biases['out']
+ return out
+
+weights = {
+ 'wc1': tf.Variable(tf.random_normal([3, 3, 3, 64])),
+ 'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128])),
+ 'wc3': tf.Variable(tf.random_normal([3, 3, 128, 256])),
+ 'wd1': tf.Variable(tf.random_normal([6*10*256, 1024])),
+ 'wd2': tf.Variable(tf.random_normal([1024, 1024])),
+ 'out': tf.Variable(tf.random_normal([1024, 24]))
+}
+biases = {
+ 'bc1': tf.Variable(tf.random_normal([64])),
+ 'bc2': tf.Variable(tf.random_normal([128])),
+ 'bc3': tf.Variable(tf.random_normal([256])),
+ 'bd1': tf.Variable(tf.random_normal([1024])),
+ 'bd2': tf.Variable(tf.random_normal([1024])),
+ 'out': tf.Variable(tf.random_normal([n_classes]))
+}
+
+pred = alex_net(x, weights, biases, keep_prob)
+
+cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=pred))
+optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
+
+correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
+accuracy = tf.reduce_sum(tf.cast(correct_pred, tf.float32))
+
+init = tf.global_variables_initializer()
+
+N = 200
+
+with tf.Session() as sess:
+ sess.run(init)
+ step = 1
+ # Keep training until reach max iterations
+ Ist = 0
+ Ien = Ist+N
+ while step < training_iters:
+ if Ien > trainData.shape[0]:
+ Ien = trainData.shape[0]
+ sess.run(optimizer, feed_dict={x: trainData[Ist:Ien], y: trainLabel[Ist:Ien], keep_prob: dropout})
+ Ist+=N
+ Ien+=N
+ if Ist > trainData.shape[0]:
+ Ist = 0
+ Ien = Ist+N
+ ist = 0
+ ien = ist+N
+ temp = 0
+ while ist < trainData.shape[0]:
+ if ien > trainData.shape[0]:
+ ien = trainData.shape[0]
+ temp += sess.run(accuracy, feed_dict={x: trainData[ist:ien], y: trainLabel[ist:ien], keep_prob: 1.})
+ ist+=N
+ ien+=N
+ acc = temp/trainData.shape[0]
+ ist = 0
+ ien = ist+N
+ temp = 0
+ while ist < testData.shape[0]:
+ if ien > testData.shape[0]:
+ ien = testData.shape[0]
+ temp += sess.run(accuracy, feed_dict={x: testData[ist:ien], y: testLabel[ist:ien], keep_prob: 1.})
+ ist+=N
+ ien+=N
+ v_acc = temp/testData.shape[0]
+ print('\nINFO:root:Epoch[%d] Train-accuracy=%f\nINFO:root:Epoch[%d] Validation-accuracy=%f' %(step, acc, step, v_acc))
+ step += 1
\ No newline at end of file
diff --git a/results/process02.py b/results/process02.py
new file mode 100644
index 0000000..1349b06
--- /dev/null
+++ b/results/process02.py
@@ -0,0 +1,130 @@
+import numpy as np
+import os
+import tensorflow as tf
+
+env = os.environ.get('GRAPE_DATASET_DIR')
+#env = ""
+testData = np.load(os.path.join(env,"testData.npy"))
+trainData = np.load(os.path.join(env,"trainData.npy"))
+testLabel = np.load(os.path.join(env,"testLabel.npy"))
+trainLabel = np.load(os.path.join(env,"trainLabel.npy"))
+
+learning_rate = 0.001
+training_iters = 20
+
+n_input = 45*80*3
+n_classes = 24
+dropout = 0.8
+
+x = tf.placeholder(tf.float32, [None, n_input])
+y = tf.placeholder(tf.float32, [None, n_classes])
+keep_prob = tf.placeholder(tf.float32)
+
+def conv2d(name, l_input, w, b):
+ return tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(l_input, w, strides=[1, 1, 1, 1], padding='SAME'),b), name=name)
+
+def max_pool(name, l_input, k):
+ return tf.nn.max_pool(l_input, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME', name=name)
+
+def norm(name, l_input, lsize=4):
+ return tf.nn.lrn(l_input, lsize, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name=name)
+
+def alex_net(_X, _weights, _biases, _dropout):
+ _X = tf.reshape(_X, shape=[-1, 45, 80, 3])
+
+ conv1 = conv2d('conv1', _X, _weights['wc1'], _biases['bc1'])
+ pool1 = max_pool('pool1', conv1, k=2)
+ norm1 = norm('norm1', pool1, lsize=4)
+ norm1 = tf.nn.dropout(norm1, _dropout)
+
+ conv2 = conv2d('conv2', norm1, _weights['wc2'], _biases['bc2'])
+ pool2 = max_pool('pool2', conv2, k=2)
+ norm2 = norm('norm2', pool2, lsize=4)
+ norm2 = tf.nn.dropout(norm2, _dropout)
+
+ conv3 = conv2d('conv3', norm2, _weights['wc3'], _biases['bc3'])
+ pool3 = max_pool('pool3', conv3, k=2)
+ norm3 = norm('norm3', pool3, lsize=4)
+ norm3 = tf.nn.dropout(norm3, _dropout)
+
+ conv4 = conv2d('conv4', norm3, _weights['wc4'], _biases['bc4'])
+ pool4 = max_pool('pool4', conv4, k=2)
+ norm4 = norm('norm4', pool4, lsize=4)
+ norm4 = tf.nn.dropout(norm4, _dropout)
+
+ dense1 = tf.reshape(norm4, [-1, _weights['wd1'].get_shape().as_list()[0]])
+ dense1 = tf.nn.relu(tf.matmul(dense1, _weights['wd1']) + _biases['bd1'], name='fc1')
+
+ dense2 = tf.nn.relu(tf.matmul(dense1, _weights['wd2']) + _biases['bd2'], name='fc2')
+
+ out = tf.matmul(dense2, _weights['out']) + _biases['out']
+ return out
+
+weights = {
+ 'wc1': tf.Variable(tf.random_normal([3, 3, 3, 64])),
+ 'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128])),
+ 'wc3': tf.Variable(tf.random_normal([3, 3, 128, 256])),
+ 'wc4': tf.Variable(tf.random_normal([3, 3, 256, 512])),
+ 'wd1': tf.Variable(tf.random_normal([3*5*512, 1024])),
+ 'wd2': tf.Variable(tf.random_normal([1024, 1024])),
+ 'out': tf.Variable(tf.random_normal([1024, 24]))
+}
+biases = {
+ 'bc1': tf.Variable(tf.random_normal([64])),
+ 'bc2': tf.Variable(tf.random_normal([128])),
+ 'bc3': tf.Variable(tf.random_normal([256])),
+ 'bc4': tf.Variable(tf.random_normal([512])),
+ 'bd1': tf.Variable(tf.random_normal([1024])),
+ 'bd2': tf.Variable(tf.random_normal([1024])),
+ 'out': tf.Variable(tf.random_normal([n_classes]))
+}
+
+pred = alex_net(x, weights, biases, keep_prob)
+
+cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=pred))
+optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
+
+correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
+accuracy = tf.reduce_sum(tf.cast(correct_pred, tf.float32))
+
+init = tf.global_variables_initializer()
+
+N = 256
+
+with tf.Session() as sess:
+ sess.run(init)
+ step = 1
+ # Keep training until reach max iterations
+ Ist = 0
+ Ien = Ist+N
+ while step < training_iters:
+ if Ien > trainData.shape[0]:
+ Ien = trainData.shape[0]
+ sess.run(optimizer, feed_dict={x: trainData[Ist:Ien], y: trainLabel[Ist:Ien], keep_prob: dropout})
+ Ist+=N
+ Ien+=N
+ if Ist > trainData.shape[0]:
+ Ist = 0
+ Ien = Ist+N
+ ist = 0
+ ien = ist+N
+ temp = 0
+ while ist < trainData.shape[0]:
+ if ien > trainData.shape[0]:
+ ien = trainData.shape[0]
+ temp += sess.run(accuracy, feed_dict={x: trainData[ist:ien], y: trainLabel[ist:ien], keep_prob: 1.})
+ ist+=N
+ ien+=N
+ acc = temp/trainData.shape[0]
+ ist = 0
+ ien = ist+N
+ temp = 0
+ while ist < testData.shape[0]:
+ if ien > testData.shape[0]:
+ ien = testData.shape[0]
+ temp += sess.run(accuracy, feed_dict={x: testData[ist:ien], y: testLabel[ist:ien], keep_prob: 1.})
+ ist+=N
+ ien+=N
+ v_acc = temp/testData.shape[0]
+ print('\nINFO:root:Epoch[%d] Train-accuracy=%f\nINFO:root:Epoch[%d] Validation-accuracy=%f' %(step, acc, step, v_acc))
+ step += 1
\ No newline at end of file