Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

dataset.py #3

Open
wants to merge 8 commits into
base: master
Choose a base branch
from
Open

dataset.py #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
449374d
Created using Colaboratory
Kevin1732 Jun 10, 2021
7a83484
Created using Colaboratory
Kevin1732 Jun 14, 2021
c6f0570
Created using Colaboratory
Kevin1732 Jun 14, 2021
7f1a655
Created using Colaboratory
Kevin1732 Jun 14, 2021
abe7e0b
Delete Copy_of_3D_pose_warping_task1.ipynb
Kevin1732 Jun 27, 2021
c9f6f37
Delete Copy_of_3D_pose_warping_task1_updated_.ipynb
Kevin1732 Jun 27, 2021
3c81bce
Delete Copy_of_3D_pose_warping_task1_updated.ipynb
Kevin1732 Jun 27, 2021
3014f53
Add files via upload
Kevin1732 Jun 27, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
185 changes: 183 additions & 2 deletions Task1/3D_pose_warping_task1.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -81,13 +81,194 @@
{
"cell_type": "code",
"metadata": {
"id": "RKInCk4WTo2r"
"id": "07WvlRnwjVcO"
},
"source": [
"# Add code cells in this section"
"# I am trying using keras \n",
"\n",
"import tensorflow as tf\n",
"\n",
"from tensorflow.keras import datasets, layers, models\n",
"import matplotlib.pyplot as plt\n",
"\n",
"(train_images, train_labels), (test_images, test_labels) = datasets.cifar10.load_data()\n",
"\n",
"# Normalize pixel values to be between 0 and 1\n",
"train_images, test_images = train_images / 255.0, test_images / 255.0\n",
"\n",
"model = models.Sequential()\n",
"model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))\n",
"#model.add(layers.MaxPooling2D((2, 2)))\n",
"model.add(layers.Conv2D(32, (3, 3), activation='relu'))\n",
"model.add(layers.MaxPooling2D((2, 2)))\n",
"model.add(layers.Dropout(0.25))\n",
"\n",
"model.add(layers.Conv2D(64, (3, 3), activation='relu'))\n",
"#model.add(layers.MaxPooling2D((2, 2)))\n",
"model.add(layers.Conv2D(64, (3, 3), activation='relu'))\n",
"model.add(layers.MaxPooling2D((2, 2)))\n",
"model.add(layers.Dropout(0.25))\n",
"\n",
"model.add(layers.Flatten())\n",
"model.add(layers.Dense(512, activation='relu'))\n",
"model.add(layers.Dense(10), activation=' softmax')\n",
"\n",
"model.summary()\n",
"\n",
"model.compile(optimizer='adam',\n",
" loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),\n",
" metrics=['accuracy'])\n",
"\n",
"history = model.fit(train_images, train_labels, epochs=10, \n",
" validation_data=(test_images, test_labels))\n",
"\n",
"plt.plot(history.history['accuracy'], label='accuracy')\n",
"plt.plot(history.history['val_accuracy'], label = 'val_accuracy')\n",
"plt.xlabel('Epoch')\n",
"plt.ylabel('Accuracy')\n",
"plt.ylim([0.5, 1])\n",
"plt.legend(loc='lower right')\n",
"\n",
"test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2)\n",
"print(test_acc)"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "RKInCk4WTo2r",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 370
},
"outputId": "78661b63-663a-4409-edb2-708eb21db5fb"
},
"source": [
"# Add code cells in this section\n",
"%tensorflow_version 1.x\n",
"import tensorflow as tf\n",
"import numpy as np\n",
"from keras.datasets import cifar10\n",
"#from tensorflow.examples.tutorials.mnist import input_data\n",
"# load dataset\n",
"(trainX, trainY), (testX, testY) = cifar10.load_data()\n",
"\n",
"batch_size = 128\n",
"test_size = 256\n",
"\n",
"def init_weights(shape):\n",
" return tf.Variable(tf.random_normal(shape, stddev=0.01))\n",
"\n",
"def model(X, w, w2, w3, w4, w5, w6, w_o, p_keep_conv, p_keep_hidden):\n",
" l1 = tf.nn.relu(tf.nn.conv2d(X, w, # l1a shape=(?, 28, 28, 32)\n",
" strides=[1, 1, 1, 1], padding='SAME'))\n",
" #l1 = tf.nn.max_pool(l1a, ksize=[1, 2, 2, 1], # l1 shape=(?, 28, 28, 32)\n",
" #strides=[1, 2, 2, 1], padding='SAME')\n",
" l1 = tf.nn.dropout(l1, p_keep_conv)\n",
"\n",
" l2a = tf.nn.relu(tf.nn.conv2d(l1, w2, # l2a shape=(?, 28, 28, 64)\n",
" strides=[1, 1, 1, 1], padding='SAME'))\n",
" l2 = tf.nn.max_pool(l2a, ksize=[1, 2, 2, 1], # l2 shape=(?, 14, 14, 64)\n",
" strides=[1, 2, 2, 1], padding='SAME')\n",
" l2 = tf.nn.dropout(l2, p_keep_conv)\n",
"\n",
" l3 = tf.nn.relu(tf.nn.conv2d(l2, w3, # l3a shape=(?, 7, 7, 128)\n",
" strides=[1, 1, 1, 1], padding='SAME'))\n",
" #l3 = tf.nn.max_pool(l3a, ksize=[1, 2, 2, 1], # l3 shape=(?, 7, 7, 128)\n",
" #strides=[1, 2, 2, 1], padding='SAME')\n",
" l3 = tf.nn.dropout(l3, p_keep_conv)\n",
"\n",
" l4a = tf.nn.relu(tf.nn.conv2d(l3, w4, # l4a shape=(?, 7, 7, 256)\n",
" strides=[1, 1, 1, 1], padding='SAME'))\n",
" l4 = tf.nn.max_pool(l4a, ksize=[1, 2, 2, 1], # l4 shape=(?, 4, 4, 256)\n",
" strides=[1, 2, 2, 1], padding='SAME')\n",
" l4 = tf.nn.dropout(l4, p_keep_conv)\n",
"\n",
" l5 = tf.nn.relu(tf.nn.conv2d(l4, w5, # l5a shape=(?, 4, 4, 512)\n",
" strides=[1, 1, 1, 1], padding='SAME'))\n",
" #l5 = tf.nn.max_pool(l5a, ksize=[1, 2, 2, 1], # l5 shape=(?, 4, 4, 512)\n",
" #strides=[1, 2, 2, 1], padding='SAME')\n",
" l5 = tf.nn.dropout(l5, p_keep_conv)\n",
"\n",
"\n",
"\n",
" l5 = tf.reshape(l5, [-1, w6.get_shape().as_list()[0]]) # reshape to (?, 512*4*4)\n",
" l5 = tf.nn.dropout(l5, p_keep_conv)\n",
"\n",
" l6 = tf.nn.relu(tf.matmul(l5, w6))\n",
" l6 = tf.nn.dropout(l6, p_keep_hidden)\n",
"\n",
" pyx = tf.matmul(l6, w_o)\n",
" return pyx\n",
"\n",
"# load dataset\n",
"(trainX_c, trainY), (testX_c, testY) = cifar10.load_data()\n",
"\n",
"#trainX = np.mean(trainX_c, axis=2)\n",
"#testX = np.mean(testX_c, axis=2)\n",
"# Normalize pixel values to be between 0 and 1\n",
"trainX, testX = trainX / 255.0, testX / 255.0\n",
"\n",
"X = tf.placeholder(\"float\", [None, 28, 28, 1])\n",
"Y = tf.placeholder(\"float\", [None, 10])\n",
"\n",
"w = init_weights([3, 3, 1, 32]) # 3x3x1 conv, 32 outputs\n",
"w2 = init_weights([3, 3, 32, 64]) # 3x3x32 conv, 64 outputs\n",
"w3 = init_weights([3, 3, 64, 128]) # 3x3x32 conv, 128 outputs\n",
"w4 = init_weights([3, 3, 128, 256]) # 3x3x32 conv, 256 outputs\n",
"w5 = init_weights([3, 3, 256, 512]) # 3x3x32 conv, 512 outputs\n",
"w6 = init_weights([512 * 4 * 4, 625]) # FC 512 * 4 * 4 inputs, 625 outputs\n",
"w_o = init_weights([625, 10]) # FC 625 inputs, 10 outputs (labels)\n",
"\n",
"p_keep_conv = tf.placeholder(\"float\")\n",
"p_keep_hidden = tf.placeholder(\"float\")\n",
"py_x = model(X, w, w2, w3, w4, w5, w6, w_o, p_keep_conv, p_keep_hidden)\n",
"\n",
"cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y))\n",
"train_op = tf.train.RMSPropOptimizer(0.001, 0.9).minimize(cost)\n",
"predict_op = tf.argmax(py_x, 1)\n",
"\n",
"\n",
"# Launch the graph in a session\n",
"with tf.Session() as sess:\n",
" # you need to initialize all variables\n",
" tf.global_variables_initializer().run()\n",
"\n",
" for i in range(100):\n",
" training_batch = zip(range(0, len(trainX), batch_size),\n",
" range(batch_size, len(trainX)+1, batch_size))\n",
" for start, end in training_batch:\n",
" sess.run(train_op, feed_dict={X: trainX[start:end], Y: trainY[start:end],\n",
" p_keep_conv: 0.8, p_keep_hidden: 0.5})\n",
"\n",
" test_indices = np.arange(len(testX)) # Get A Test Batch\n",
" np.random.shuffle(test_indices)\n",
" test_indices = test_indices[0:test_size]\n",
"\n",
" print(i, np.mean(np.argmax(testY[test_indices], axis=1) ==\n",
" sess.run(predict_op, feed_dict={X: testX[test_indices],\n",
" Y: testY[test_indices],\n",
" p_keep_conv: 1.0,\n",
" p_keep_hidden: 1.0})))"
],
"execution_count": 9,
"outputs": [
{
"output_type": "error",
"ename": "ValueError",
"evalue": "ignored",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-9-17e3f741ceed>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 94\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mstart\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mend\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mtraining_batch\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 95\u001b[0m sess.run(train_op, feed_dict={X: trainX[start:end], Y: trainY[start:end],\n\u001b[0;32m---> 96\u001b[0;31m p_keep_conv: 0.8, p_keep_hidden: 0.5})\n\u001b[0m\u001b[1;32m 97\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 98\u001b[0m \u001b[0mtest_indices\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtestX\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# Get A Test Batch\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/tensorflow-1.15.2/python3.7/tensorflow_core/python/client/session.py\u001b[0m in \u001b[0;36mrun\u001b[0;34m(self, fetches, feed_dict, options, run_metadata)\u001b[0m\n\u001b[1;32m 954\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 955\u001b[0m result = self._run(None, fetches, feed_dict, options_ptr,\n\u001b[0;32m--> 956\u001b[0;31m run_metadata_ptr)\n\u001b[0m\u001b[1;32m 957\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mrun_metadata\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 958\u001b[0m \u001b[0mproto_data\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf_session\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTF_GetBuffer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrun_metadata_ptr\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/tensorflow-1.15.2/python3.7/tensorflow_core/python/client/session.py\u001b[0m in \u001b[0;36m_run\u001b[0;34m(self, handle, fetches, feed_dict, options, run_metadata)\u001b[0m\n\u001b[1;32m 1154\u001b[0m \u001b[0;34m'Cannot feed value of shape %r for Tensor %r, '\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1155\u001b[0m \u001b[0;34m'which has shape %r'\u001b[0m \u001b[0;34m%\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1156\u001b[0;31m (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))\n\u001b[0m\u001b[1;32m 1157\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgraph\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mis_feedable\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msubfeed_t\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1158\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Tensor %s may not be fed.'\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0msubfeed_t\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mValueError\u001b[0m: Cannot feed value of shape (128, 32, 3) for Tensor 'Placeholder_24:0', which has shape '(?, 28, 28, 1)'"
]
}
]
}
]
}
86 changes: 86 additions & 0 deletions dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,86 @@
import numpy as np
import tensorflow as tf
import pickle
import matplotlib.pyplot as plt
from matplotlib import image
import glob
import os
from PIL import Image
from numpy import asarray
import PIL
import pathlib
import tensorflow_datasets as tfds
# import tensorflow.keras.datasets.cifar10 as cf


!unzip '/content/drive/MyDrive/DeepFashion/In-shop Clothes Retrieval Benchmark/Img/img.zip'

infile = open('/content/drive/MyDrive/poses_fashion3d.pkl','rb')
poses = pickle.load(infile)



#Function For Converting image into numpy array

def img_to_tensor (path):
# load the image
image = Image.open(path)
# convert image to numpy array
data = asarray(image)
# print(type(data))
# # summarize shape
# print(data.shape)

# # create Pillow image
# image2 = Image.fromarray(data)
# print(type(image2))

# # summarize image details
# print(image2.mode)
# print(image2.size)
data.reshape(256,256,3)
return data



data = {}
for n in poses:
for i in poses[n]:
#data_men[i] = {}
for j in poses[n][i]:
#data_men[i][j]={}
for k in poses[n][i][j]:
#data_men[i][j][k]={}
for l in poses[n][i][j][k]:
path = '/content/img/'+n+'/'+i+'/'+j+'/'+k+'_'+l+'.jpg'
x = img_to_tensor(path)
data.update({path : x})



data_pose={}
for n in poses:
for i in poses[n]:
for j in poses[n][i]:
for k in poses[n][i][j]:
for l in poses[n][i][j][k]:
#for m in poses[n][i][j][k][l]:
path = '/content/img/'+n+'/'+i+'/'+j+'/'+k+'_'+l+'.jpg'
data_pose.update({path : poses[n][i][j][k][l]})



joint_order=['neck', 'nose', 'lsho', 'lelb', 'lwri', 'lhip', 'lkne', 'lank', 'rsho', 'relb', 'rwri', 'rhip', 'rkne', 'rank', 'leye', 'lear', 'reye', 'rear', 'pelv']

def give_name_to_keypoints(array, joint_order):
res = {}
for i, name in enumerate(joint_order):
res[name] = array[i]
return res


data_with_joints={}
for path,image in data.items():
array=data_pose.get(path)
data_with_joints[path]=give_name_to_keypoints(data_pose.get(path), joint_order)