first commit

_init_paths.py

@@ -0,0 +1,15 @@
+import os.path as osp
+import sys
+
+def add_path(path):
+    if path not in sys.path:
+        sys.path.insert(0, path)
+
+this_dir = osp.dirname(__file__)
+
+# Add lib to PYTHONPATH
+lib_path = osp.join(this_dir, 'lib')
+add_path(lib_path)
+
+coco_path = osp.join(this_dir, 'data', 'coco', 'PythonAPI')
+add_path(coco_path)

cfgs/res101.yml

@@ -0,0 +1,18 @@
+EXP_DIR: res101
+TRAIN:
+  HAS_RPN: True
+  BBOX_NORMALIZE_TARGETS_PRECOMPUTED: True
+  RPN_POSITIVE_OVERLAP: 0.7
+  RPN_BATCHSIZE: 256
+  PROPOSAL_METHOD: gt
+  BG_THRESH_LO: 0.0
+  DISPLAY: 20
+  BATCH_SIZE: 128
+  WEIGHT_DECAY: 0.0001
+  DOUBLE_BIAS: False
+  LEARNING_RATE: 0.001
+TEST:
+  HAS_RPN: True
+POOLING_SIZE: 7
+POOLING_MODE: align
+CROP_RESIZE_WITH_MAX_POOL: False

cfgs/res101_ls.yml

@@ -0,0 +1,22 @@
+EXP_DIR: res101
+TRAIN:
+  HAS_RPN: True
+  BBOX_NORMALIZE_TARGETS_PRECOMPUTED: True
+  RPN_POSITIVE_OVERLAP: 0.7
+  RPN_BATCHSIZE: 256
+  PROPOSAL_METHOD: gt
+  BG_THRESH_LO: 0.0
+  DISPLAY: 20
+  BATCH_SIZE: 128
+  WEIGHT_DECAY: 0.0001
+  SCALES: [800]
+  DOUBLE_BIAS: False
+  LEARNING_RATE: 0.001
+TEST:
+  HAS_RPN: True
+  SCALES: [800]
+  MAX_SIZE: 1200
+  RPN_POST_NMS_TOP_N: 1000
+POOLING_SIZE: 7
+POOLING_MODE: align
+CROP_RESIZE_WITH_MAX_POOL: False

cfgs/res50.yml

@@ -0,0 +1,17 @@
+EXP_DIR: res50
+TRAIN:
+  HAS_RPN: True
+  # IMS_PER_BATCH: 1
+  BBOX_NORMALIZE_TARGETS_PRECOMPUTED: True
+  RPN_POSITIVE_OVERLAP: 0.7
+  RPN_BATCHSIZE: 256
+  PROPOSAL_METHOD: gt
+  BG_THRESH_LO: 0.0
+  DISPLAY: 20
+  BATCH_SIZE: 128
+  WEIGHT_DECAY: 0.0001
+  DOUBLE_BIAS: False
+  SNAPSHOT_PREFIX: res50_faster_rcnn
+TEST:
+  HAS_RPN: True
+POOLING_MODE: align

cfgs/res50_1.yml

@@ -0,0 +1,19 @@
+EXP_DIR: res50
+TRAIN:
+  HAS_RPN: True
+  # IMS_PER_BATCH: 1
+  BBOX_NORMALIZE_TARGETS_PRECOMPUTED: True
+  RPN_POSITIVE_OVERLAP: 0.7
+  RPN_BATCHSIZE: 256
+  PROPOSAL_METHOD: gt
+  BG_THRESH_LO: 0.0
+  DISPLAY: 20
+  BATCH_SIZE: 128
+  WEIGHT_DECAY: 0.0001
+  DOUBLE_BIAS: False
+  SNAPSHOT_PREFIX: res50_faster_rcnn
+TEST:
+  HAS_RPN: True
+POOLING_MODE: align
+train_categories: [2]
+test_categories: [2]

cfgs/res50_2.yml

@@ -0,0 +1,19 @@
+EXP_DIR: res50
+TRAIN:
+  HAS_RPN: True
+  # IMS_PER_BATCH: 1
+  BBOX_NORMALIZE_TARGETS_PRECOMPUTED: True
+  RPN_POSITIVE_OVERLAP: 0.7
+  RPN_BATCHSIZE: 256
+  PROPOSAL_METHOD: gt
+  BG_THRESH_LO: 0.0
+  DISPLAY: 20
+  BATCH_SIZE: 128
+  WEIGHT_DECAY: 0.0001
+  DOUBLE_BIAS: False
+  SNAPSHOT_PREFIX: res50_faster_rcnn
+TEST:
+  HAS_RPN: True
+POOLING_MODE: align
+train_categories: [2]
+test_categories: [2]

cfgs/res50_3.yml

@@ -0,0 +1,19 @@
+EXP_DIR: res50
+TRAIN:
+  HAS_RPN: True
+  # IMS_PER_BATCH: 1
+  BBOX_NORMALIZE_TARGETS_PRECOMPUTED: True
+  RPN_POSITIVE_OVERLAP: 0.7
+  RPN_BATCHSIZE: 256
+  PROPOSAL_METHOD: gt
+  BG_THRESH_LO: 0.0
+  DISPLAY: 20
+  BATCH_SIZE: 128
+  WEIGHT_DECAY: 0.0001
+  DOUBLE_BIAS: False
+  SNAPSHOT_PREFIX: res50_faster_rcnn
+TEST:
+  HAS_RPN: True
+POOLING_MODE: align
+train_categories: [3]
+test_categories: [3]

cfgs/res50_4.yml

@@ -0,0 +1,19 @@
+EXP_DIR: res50
+TRAIN:
+  HAS_RPN: True
+  # IMS_PER_BATCH: 1
+  BBOX_NORMALIZE_TARGETS_PRECOMPUTED: True
+  RPN_POSITIVE_OVERLAP: 0.7
+  RPN_BATCHSIZE: 256
+  PROPOSAL_METHOD: gt
+  BG_THRESH_LO: 0.0
+  DISPLAY: 20
+  BATCH_SIZE: 128
+  WEIGHT_DECAY: 0.0001
+  DOUBLE_BIAS: False
+  SNAPSHOT_PREFIX: res50_faster_rcnn
+TEST:
+  HAS_RPN: True
+POOLING_MODE: align
+train_categories: [0]
+test_categories: [0]

cfgs/res50_ls.yml

@@ -0,0 +1,18 @@
+EXP_DIR: res50
+TRAIN:
+  HAS_RPN: True
+  BBOX_NORMALIZE_TARGETS_PRECOMPUTED: True
+  RPN_POSITIVE_OVERLAP: 0.7
+  RPN_BATCHSIZE: 256
+  PROPOSAL_METHOD: gt
+  BG_THRESH_LO: 0.0
+  DISPLAY: 20
+  BATCH_SIZE: 256
+  WEIGHT_DECAY: 0.0001
+  DOUBLE_BIAS: False
+  LEARNING_RATE: 0.001
+TEST:
+  HAS_RPN: True
+POOLING_SIZE: 7
+POOLING_MODE: align
+CROP_RESIZE_WITH_MAX_POOL: False

cfgs/vgg16.yml

@@ -0,0 +1,14 @@
+EXP_DIR: vgg16
+TRAIN:
+  HAS_RPN: True
+  BBOX_NORMALIZE_TARGETS_PRECOMPUTED: True
+  RPN_POSITIVE_OVERLAP: 0.7
+  RPN_BATCHSIZE: 256
+  PROPOSAL_METHOD: gt
+  BG_THRESH_LO: 0.0
+  BATCH_SIZE: 256
+  LEARNING_RATE: 0.01
+TEST:
+  HAS_RPN: True
+POOLING_MODE: align
+CROP_RESIZE_WITH_MAX_POOL: False

check_image.py

@@ -0,0 +1 @@
+import 

cls_utils.py

@@ -0,0 +1,124 @@
+'''Some helper functions for PyTorch, including:
+    - get_mean_and_std: calculate the mean and std value of dataset.
+    - msr_init: net parameter initialization.
+    - progress_bar: progress bar mimic xlua.progress.
+'''
+import os
+import sys
+import time
+import math
+
+import torch.nn as nn
+import torch.nn.init as init
+
+
+def get_mean_and_std(dataset):
+    '''Compute the mean and std value of dataset.'''
+    dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=2)
+    mean = torch.zeros(3)
+    std = torch.zeros(3)
+    print('==> Computing mean and std..')
+    for inputs, targets in dataloader:
+        for i in range(3):
+            mean[i] += inputs[:,i,:,:].mean()
+            std[i] += inputs[:,i,:,:].std()
+    mean.div_(len(dataset))
+    std.div_(len(dataset))
+    return mean, std
+
+def init_params(net):
+    '''Init layer parameters.'''
+    for m in net.modules():
+        if isinstance(m, nn.Conv2d):
+            init.kaiming_normal(m.weight, mode='fan_out')
+            if m.bias:
+                init.constant(m.bias, 0)
+        elif isinstance(m, nn.BatchNorm2d):
+            init.constant(m.weight, 1)
+            init.constant(m.bias, 0)
+        elif isinstance(m, nn.Linear):
+            init.normal(m.weight, std=1e-3)
+            if m.bias:
+                init.constant(m.bias, 0)
+
+
+_, term_width = os.popen('stty size', 'r').read().split()
+term_width = int(term_width)
+
+TOTAL_BAR_LENGTH = 65.
+last_time = time.time()
+begin_time = last_time
+def progress_bar(current, total, msg=None):
+    global last_time, begin_time
+    if current == 0:
+        begin_time = time.time()  # Reset for new bar.
+
+    cur_len = int(TOTAL_BAR_LENGTH*current/total)
+    rest_len = int(TOTAL_BAR_LENGTH - cur_len) - 1
+
+    sys.stdout.write(' [')
+    for i in range(cur_len):
+        sys.stdout.write('=')
+    sys.stdout.write('>')
+    for i in range(rest_len):
+        sys.stdout.write('.')
+    sys.stdout.write(']')
+
+    cur_time = time.time()
+    step_time = cur_time - last_time
+    last_time = cur_time
+    tot_time = cur_time - begin_time
+
+    L = []
+    L.append('  Step: %s' % format_time(step_time))
+    L.append(' | Tot: %s' % format_time(tot_time))
+    if msg:
+        L.append(' | ' + msg)
+
+    msg = ''.join(L)
+    sys.stdout.write(msg)
+    for i in range(term_width-int(TOTAL_BAR_LENGTH)-len(msg)-3):
+        sys.stdout.write(' ')
+
+    # Go back to the center of the bar.
+    for i in range(term_width-int(TOTAL_BAR_LENGTH/2)+2):
+        sys.stdout.write('\b')
+    sys.stdout.write(' %d/%d ' % (current+1, total))
+
+    if current < total-1:
+        sys.stdout.write('\r')
+    else:
+        sys.stdout.write('\n')
+    sys.stdout.flush()
+
+def format_time(seconds):
+    days = int(seconds / 3600/24)
+    seconds = seconds - days*3600*24
+    hours = int(seconds / 3600)
+    seconds = seconds - hours*3600
+    minutes = int(seconds / 60)
+    seconds = seconds - minutes*60
+    secondsf = int(seconds)
+    seconds = seconds - secondsf
+    millis = int(seconds*1000)
+
+    f = ''
+    i = 1
+    if days > 0:
+        f += str(days) + 'D'
+        i += 1
+    if hours > 0 and i <= 2:
+        f += str(hours) + 'h'
+        i += 1
+    if minutes > 0 and i <= 2:
+        f += str(minutes) + 'm'
+        i += 1
+    if secondsf > 0 and i <= 2:
+        f += str(secondsf) + 's'
+        i += 1
+    if millis > 0 and i <= 2:
+        f += str(millis) + 'ms'
+        i += 1
+    if f == '':
+        f = '0ms'
+    return f