Skip to content

Commit

Permalink
fix: Correct mean normalization channel order
Browse files Browse the repository at this point in the history 
The order of the mean normalization values was BGR when it should have been RGB for this implementation. Fixed now.
  • Loading branch information
@pierluigiferrari
pierluigiferrari committed Jan 18, 2018
1 parent 9509bb9 commit d183dd9
Show file tree
Hide file tree
Showing 6 changed files with 32 additions and 35 deletions.
2 changes: 1 addition & 1 deletion keras_ssd300.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,7 @@ def ssd_300(image_size,
variances=[0.1, 0.1, 0.2, 0.2],
coords='centroids',
normalize_coords=False,
subtract_mean=[104, 117, 123],
subtract_mean=[123, 117, 104],
divide_by_stddev=None,
swap_channels=True,
return_predictor_sizes=False):
Expand Down
2 changes: 1 addition & 1 deletion keras_ssd512.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ def ssd_512(image_size,
variances=[0.1, 0.1, 0.2, 0.2],
coords='centroids',
normalize_coords=False,
subtract_mean=[104, 117, 123],
subtract_mean=[123, 117, 104],
divide_by_stddev=None,
swap_channels=True,
return_predictor_sizes=False):
Expand Down
52 changes: 24 additions & 28 deletions ssd300_evaluation_COCO.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -18,9 +18,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"metadata": {},
"outputs": [],
"source": [
"from keras import backend as K\n",
Expand Down Expand Up @@ -83,9 +81,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"metadata": {},
"outputs": [],
"source": [
"# 1: Build the Keras model\n",
Expand All @@ -109,7 +105,7 @@
" variances=[0.1, 0.1, 0.2, 0.2],\n",
" coords='centroids',\n",
" normalize_coords=True,\n",
" subtract_mean=[104, 117, 123],\n",
" subtract_mean=[123, 117, 104],\n",
" swap_channels=True)\n",
"\n",
"# 2: Load the trained weights into the model.\n",
Expand Down Expand Up @@ -210,7 +206,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 6,
"metadata": {
"collapsed": true
},
Expand All @@ -223,15 +219,15 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of images in the evaluation dataset: 5000\n",
"Producing results file: 100%|██████████| 250/250 [15:02<00:00, 3.79s/it]\n",
"Producing results file: 100%|██████████| 250/250 [17:07<00:00, 4.29s/it]\n",
"Prediction results saved in 'detections_val2017_ssd300_results.json'\n"
]
}
Expand Down Expand Up @@ -263,19 +259,19 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"loading annotations into memory...\n",
"Done (t=0.54s)\n",
"Done (t=0.41s)\n",
"creating index...\n",
"index created!\n",
"Loading and preparing results...\n",
"DONE (t=5.32s)\n",
"DONE (t=5.34s)\n",
"creating index...\n",
"index created!\n"
]
Expand All @@ -289,7 +285,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 9,
"metadata": {},
"outputs": [
{
Expand All @@ -298,21 +294,21 @@
"text": [
"Running per image evaluation...\n",
"Evaluate annotation type *bbox*\n",
"DONE (t=68.27s).\n",
"DONE (t=69.19s).\n",
"Accumulating evaluation results...\n",
"DONE (t=10.48s).\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.241\n",
" Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.415\n",
" Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.247\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.057\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.257\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.405\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.229\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.335\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.356\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.097\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.395\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.568\n"
"DONE (t=14.10s).\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.247\n",
" Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.424\n",
" Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.253\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.059\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.264\n",
" Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.414\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.232\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.341\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.362\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.102\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.401\n",
" Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.577\n"
]
}
],
Expand Down
2 changes: 1 addition & 1 deletion ssd300_inference.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -95,7 +95,7 @@
" variances=[0.1, 0.1, 0.2, 0.2],\n",
" coords='centroids',\n",
" normalize_coords=True,\n",
" subtract_mean=[104, 117, 123],\n",
" subtract_mean=[123, 117, 104],\n",
" swap_channels=True)\n",
"\n",
"# 2: Load the trained weights into the model.\n",
Expand Down
7 changes: 4 additions & 3 deletions ssd300_training.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -76,10 +76,11 @@
"img_height = 300 # Height of the input images\n",
"img_width = 300 # Width of the input images\n",
"img_channels = 3 # Number of color channels of the input images\n",
"subtract_mean = [104, 117, 123] # The per-channel mean of the images in the dataset\n",
"subtract_mean = [123, 117, 104] # The per-channel mean of the images in the dataset\n",
"swap_channels = True # The color channel order in the original SSD is BGR\n",
"n_classes = 20 # Number of positive classes, e.g. 20 for Pascal VOC, 80 for MS COCO\n",
"scales = [0.1, 0.2, 0.37, 0.54, 0.71, 0.88, 1.05] # The anchor box scaling factors used in the original SSD300 for the Pascal VOC datasets, the factors for the MS COCO dataset are smaller, namely [0.07, 0.15, 0.33, 0.51, 0.69, 0.87, 1.05]\n",
"scales_voc = [0.1, 0.2, 0.37, 0.54, 0.71, 0.88, 1.05] # The anchor box scaling factors used in the original SSD300 for the Pascal VOC datasets\n",
"scales_coco = [0.07, 0.15, 0.33, 0.51, 0.69, 0.87, 1.05] # The anchor box scaling factors used in the original SSD300 for the MS COCO datasets\n",
"aspect_ratios = [[1.0, 2.0, 0.5],\n",
" [1.0, 2.0, 0.5, 3.0, 1.0/3.0],\n",
" [1.0, 2.0, 0.5, 3.0, 1.0/3.0],\n",
Expand Down Expand Up @@ -137,7 +138,7 @@
"model = ssd_300(image_size=(img_height, img_width, img_channels),\n",
" n_classes=n_classes,\n",
" l2_regularization=0.0005,\n",
" scales=scales,\n",
" scales=scales_voc,\n",
" aspect_ratios_per_layer=aspect_ratios,\n",
" two_boxes_for_ar1=two_boxes_for_ar1,\n",
" steps=steps,\n",
Expand Down
2 changes: 1 addition & 1 deletion ssd512_inference.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,7 @@
" variances=[0.1, 0.1, 0.2, 0.2],\n",
" coords='centroids',\n",
" normalize_coords=True,\n",
" subtract_mean=[104, 117, 123],\n",
" subtract_mean=[123, 117, 104],\n",
" swap_channels=True)\n",
"\n",
"# 2: Load the trained weights into the model.\n",
Expand Down

0 comments on commit d183dd9

Please sign in to comment.