def output_max_patches(max_tracker, net, layer, idx_begin, idx_end, num_top, datadir, filelist, outdir, do_which,
layer_info):
do_maxes, do_deconv, do_deconv_norm, do_backprop, do_backprop_norm, do_info = do_which
assert do_maxes or do_deconv or do_deconv_norm or do_backprop or do_backprop_norm or do_info, 'nothing to do'
mt = max_tracker
rc = RegionComputer(layer_info)
image_filenames, image_labels = load_file_list(filelist)
print 'Loaded filenames and labels for %d files' % len(image_filenames)
print ' First file', os.path.join(datadir, image_filenames[0])
num_top_in_mt = mt.max_locs.shape[1]
assert num_top <= num_top_in_mt, 'Requested %d top images but MaxTracker contains only %d' % (
num_top, num_top_in_mt)
assert idx_end >= idx_begin, 'Range error'
size_ii, size_jj = get_max_data_extent(net, layer, rc, mt.is_conv)
data_size_ii, data_size_jj = net.blobs['data'].data.shape[2:4]
assert 0 < size_ii <= data_size_ii
assert 0 < size_jj <= data_size_jj
n_total_images = (idx_end - idx_begin) * num_top
for cc, channel_idx in enumerate(range(idx_begin, idx_end)):
unit_dir = os.path.join(outdir, layer, 'unit_%04d' % channel_idx)
mkdir_p(unit_dir)
if do_info:
info_filename = os.path.join(unit_dir, 'info.txt')
info_file = open(info_filename, 'w')
print >> info_file, '# is_conv val image_idx image_class i(if is_conv) j(if is_conv) filename'
# iterate through maxes from highest (at end) to lowest
for max_idx_0 in range(num_top):
max_idx = num_top_in_mt - 1 - max_idx_0
if mt.is_conv:
im_idx, im_class, ii, jj = mt.max_locs[channel_idx, max_idx]
else:
im_idx, im_class = mt.max_locs[channel_idx, max_idx]
recorded_val = mt.max_vals[channel_idx, max_idx]
filename = image_filenames[im_idx]
do_print = (max_idx_0 == 0)
if do_print:
print '%s Output file/image(s) %d/%d' % (datetime.now().ctime(), cc * num_top, n_total_images)
if mt.is_conv:
# Compute the focus area of the data layer
layer_indices = (ii, ii + 1, jj, jj + 1)
data_indices = rc.convert_region(layer, 'data', layer_indices, normalize_last=True)
data_ii_start, data_ii_end, data_jj_start, data_jj_end = data_indices
# why == 0. I think it's also possible for it to be < 0
# if we have padding in the first layer. such as VGG-16/19.
touching_imin = (data_ii_start <= 0)
touching_jmin = (data_jj_start <= 0)
# Compute how much of the data slice falls outside the actual data [0,max] range
ii_outside = size_ii - (data_ii_end - data_ii_start) # possibly 0
jj_outside = size_jj - (data_jj_end - data_jj_start) # possibly 0
# this should be true, since usually, the central unit (with extent size_ii, size_jj)
# should cover larger or equal region compared to all others, since there's less effect of padding.
assert ii_outside >= 0 and jj_outside >= 0
# if ii_outside (or jj_outside) is > 0,
# then that means more data got chopped off due to padding.
# if touching_imin, that means the chopping is due to close to left side
# if touching_jmin, chopping due to close to top.
# so we should pad those data there.
if touching_imin:
out_ii_start = ii_outside
out_ii_end = size_ii
else:
out_ii_start = 0
out_ii_end = size_ii - ii_outside
if touching_jmin:
out_jj_start = jj_outside
out_jj_end = size_jj
else:
out_jj_start = 0
out_jj_end = size_jj - jj_outside
else:
ii, jj = 0, 0
data_ii_start, out_ii_start, data_jj_start, out_jj_start = 0, 0, 0, 0
data_ii_end, out_ii_end, data_jj_end, out_jj_end = size_ii, size_ii, size_jj, size_jj
if do_info:
print >> info_file, 1 if mt.is_conv else 0, '%.6f' % mt.max_vals[channel_idx, max_idx],
if mt.is_conv:
print >> info_file, '%d %d %d %d' % tuple(mt.max_locs[channel_idx, max_idx]),
else:
print >> info_file, '%d %d' % tuple(mt.max_locs[channel_idx, max_idx]),
print >> info_file, filename
if not (do_maxes or do_deconv or do_deconv_norm or do_backprop or do_backprop_norm):
continue
with WithTimer('Load image', quiet=not do_print):
im = caffe.io.load_image(os.path.join(datadir, filename))
with WithTimer('Predict ', quiet=not do_print):
net.predict([im], oversample=False) # Just take center crop, same as in scan_images_for_maxes
if len(net.blobs[layer].data.shape) == 4:
reproduced_val = net.blobs[layer].data[0, channel_idx, ii, jj]
else:
reproduced_val = net.blobs[layer].data[0, channel_idx]
if abs(reproduced_val - recorded_val) > .1:
print 'Warning: recorded value %s is suspiciously different from reproduced value %s. Is the filelist the same?' % (
recorded_val, reproduced_val)
if do_maxes:
# grab image from data layer, not from im (to ensure preprocessing / center crop details match between image and deconv/backprop)
out_arr = np.zeros((3, size_ii, size_jj), dtype='float32')
out_arr[:, out_ii_start:out_ii_end, out_jj_start:out_jj_end] = net.blobs['data'].data[0, :,
data_ii_start:data_ii_end,
data_jj_start:data_jj_end]
with WithTimer('Save img ', quiet=not do_print):
save_caffe_image(out_arr, os.path.join(unit_dir, 'maxim_%03d.png' % max_idx_0),
autoscale=False, autoscale_center=0)
if do_deconv or do_deconv_norm:
diffs = net.blobs[layer].diff * 0
if len(diffs.shape) == 4:
diffs[0, channel_idx, ii, jj] = 1.0
else:
assert len(diffs.shape) == 2
diffs[0, channel_idx] = 1.0
with WithTimer('Deconv ', quiet=not do_print):
net.deconv_from_layer(layer, diffs)
out_arr = np.zeros((3, size_ii, size_jj), dtype='float32')
out_arr[:, out_ii_start:out_ii_end, out_jj_start:out_jj_end] = net.blobs['data'].diff[0, :,
data_ii_start:data_ii_end,
data_jj_start:data_jj_end]
if out_arr.max() == 0:
print 'Warning: Deconv out_arr in range', out_arr.min(), 'to', out_arr.max(), 'ensure force_backward: true in prototxt'
if do_deconv:
with WithTimer('Save img ', quiet=not do_print):
save_caffe_image(out_arr, os.path.join(unit_dir, 'deconv_%03d.png' % max_idx_0),
autoscale=False, autoscale_center=0)
if do_deconv_norm:
out_arr = np.linalg.norm(out_arr, axis=0)
with WithTimer('Save img ', quiet=not do_print):
save_caffe_image(out_arr, os.path.join(unit_dir, 'deconvnorm_%03d.png' % max_idx_0))
if do_backprop or do_backprop_norm:
diffs = net.blobs[layer].diff * 0
if len(diffs.shape) == 4:
diffs[0, channel_idx, ii, jj] = 1.0
else:
assert len(diffs.shape) == 2
diffs[0, channel_idx] = 1.0
with WithTimer('Backward ', quiet=not do_print):
net.backward_from_layer(layer, diffs)
out_arr = np.zeros((3, size_ii, size_jj), dtype='float32')
out_arr[:, out_ii_start:out_ii_end, out_jj_start:out_jj_end] = net.blobs['data'].diff[0, :,
data_ii_start:data_ii_end,
data_jj_start:data_jj_end]
if out_arr.max() == 0:
print 'Warning: Deconv out_arr in range', out_arr.min(), 'to', out_arr.max(), 'ensure force_backward: true in prototxt'
if do_backprop:
with WithTimer('Save img ', quiet=not do_print):
save_caffe_image(out_arr, os.path.join(unit_dir, 'backprop_%03d.png' % max_idx_0),
autoscale=False, autoscale_center=0)
if do_backprop_norm:
out_arr = np.linalg.norm(out_arr, axis=0)
with WithTimer('Save img ', quiet=not do_print):
save_caffe_image(out_arr, os.path.join(unit_dir, 'backpropnorm_%03d.png' % max_idx_0))
if do_info:
info_file.close()
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
'--model',
type=str,
default=
'/home/ubuntu/new/caffe/data/marketplace/googlenet/deploy.prototxt')
parser.add_argument(
'--weights',
type=str,
default=
'/home/ubuntu/new/caffe/data/marketplace/googlenet/snapshots/googlenet_train_quick_iter_5000.caffemodel'
)
parser.add_argument(
'--lmdb',
type=str,
default=
'/home/ubuntu/new/caffe/data/marketplace/images/marketplace_val_lmdb')
parser.add_argument(
'--mean',
type=str,
default=
'/home/ubuntu/new/caffe/data/marketplace/images/mean.binaryproto')
parser.add_argument('--layer', type=str, default='prob')
parser.add_argument('--channel', type=int, default=0)
args = parser.parse_args()
caffe.set_mode_gpu()
caffe.set_device(0)
reader = lmdb_reader(args.lmdb)
mean = read_mean(args.mean)
net = caffe.Net(args.model, args.weights, caffe.TEST)
try:
max_tracker = pickle.load(open('maxes.pkl', 'rb'))
except:
layers = map(str, net._blob_names)
is_conv = [False for ll in layers]
max_tracker = NetMaxTracker(layers=layers, is_conv=is_conv, n_top=10)
for idx, (i, image, label) in enumerate(reader):
print idx, i, label
caffe_in = preprocess_image(image, net, mean)
net.blobs['data'].data[...] = caffe_in
net.forward()
max_tracker.update(net, idx, label)
with open('maxes.pkl', 'wb') as f:
pickle.dump(max_tracker, f, -1)
reader = lmdb_reader(args.lmdb)
files = [i.split('_', 1)[1] for (i, _, _) in reader]
layer = args.layer
channel = args.channel
mt = max_tracker.max_trackers[layer]
rc = RegionComputer()
fig = plt.figure(figsize=(6, 6))
gs = gridspec.GridSpec(3, 3, wspace=0, hspace=0)
for i, im in enumerate(mt.max_locs[channel, -9:, 0]):
img = mpimg.imread('/home/ubuntu/new/caffe/data/marketplace/images/' +
files[im])
if mt.is_conv:
ii, jj = mt.max_locs[channel, i + 1, 2:]
layer_indices = (ii, ii + 1, jj, jj + 1)
data_indices = rc.convert_region(layer, 'data', layer_indices)
data_ii_start, data_ii_end, data_jj_start, data_jj_end = data_indices
img = img[data_ii_start:data_ii_end, data_jj_start:data_jj_end, :]
ax = plt.subplot(gs[i])
ax.set_xticks([])
ax.set_yticks([])
ax.imshow(img, aspect='auto')
fig.add_subplot(ax)
plt.tight_layout(pad=0)
plt.show()
def output_max_patches(max_tracker, net, layer, idx_begin, idx_end, num_top,
datadir, filelist, outdir, do_which):
do_maxes, do_deconv, do_deconv_norm, do_backprop, do_backprop_norm, do_info = do_which
assert do_maxes or do_deconv or do_deconv_norm or do_backprop or do_backprop_norm or do_info, 'nothing to do'
mt = max_tracker
rc = RegionComputer()
image_filenames, image_xmls, image_labels = load_file_list(filelist)
print('Loaded filenames and labels for %d files' % len(image_filenames))
print(' First file', os.path.join(datadir, image_filenames[0]))
num_top_in_mt = mt.max_locs.shape[1]
assert num_top <= num_top_in_mt, 'Requested %d top images but MaxTracker contains only %d' % (
num_top, num_top_in_mt)
assert idx_end >= idx_begin, 'Range error'
size_ii, size_jj = get_max_data_extent(net, layer, rc, mt.is_conv)
data_size_ii, data_size_jj = net.blobs['data'].data.shape[2:4]
n_total_images = (idx_end - idx_begin) * num_top
for cc, channel_idx in enumerate(range(idx_begin, idx_end)):
unit_dir = os.path.join(outdir, layer, 'unit_%04d' % channel_idx)
mkdir_p(unit_dir)
if do_info:
info_filename = os.path.join(unit_dir, 'info.txt')
info_file = open(info_filename, 'w')
info_file.write(
'# is_conv val image_idx image_class i(if is_conv) j(if is_conv) filename'
)
# iterate through maxes from highest (at end) to lowest
for max_idx_0 in range(num_top):
max_idx = num_top_in_mt - 1 - max_idx_0
if mt.is_conv:
im_idx, im_class, ii, jj = mt.max_locs[channel_idx, max_idx]
else:
im_idx, im_class = mt.max_locs[channel_idx, max_idx]
recorded_val = mt.max_vals[channel_idx, max_idx]
filename = image_filenames[im_idx]
roiname = image_xmls[im_idx]
do_print = (max_idx_0 == 0)
if do_print:
print('%s Output file/image(s) %d/%d' %
(datetime.now().ctime(), cc * num_top, n_total_images))
if mt.is_conv:
# Compute the focus area of the data layer
layer_indices = (ii, ii + 1, jj, jj + 1)
data_indices = rc.convert_region(layer, 'data', layer_indices)
data_ii_start, data_ii_end, data_jj_start, data_jj_end = data_indices
touching_imin = (data_ii_start == 0)
touching_jmin = (data_jj_start == 0)
# Compute how much of the data slice falls outside the actual data [0,max] range
ii_outside = size_ii - (data_ii_end - data_ii_start
) # possibly 0
jj_outside = size_jj - (data_jj_end - data_jj_start
) # possibly 0
if touching_imin:
out_ii_start = ii_outside
out_ii_end = size_ii
else:
out_ii_start = 0
out_ii_end = size_ii - ii_outside
if touching_jmin:
out_jj_start = jj_outside
out_jj_end = size_jj
else:
out_jj_start = 0
out_jj_end = size_jj - jj_outside
else:
ii, jj = 0, 0
data_ii_start, out_ii_start, data_jj_start, out_jj_start = 0, 0, 0, 0
data_ii_end, out_ii_end, data_jj_end, out_jj_end = size_ii, size_ii, size_jj, size_jj
if do_info:
info_file.write(str(1 if mt.is_conv else 0))
info_file.write('%.6f' % mt.max_vals[channel_idx, max_idx])
if mt.is_conv:
info_file.write('%d %d %d %d' %
tuple(mt.max_locs[channel_idx, max_idx]))
else:
info_file.write('%d %d' %
tuple(mt.max_locs[channel_idx, max_idx]))
info_file.write(filename)
if not (do_maxes or do_deconv or do_deconv_norm or do_backprop
or do_backprop_norm):
continue
with WithTimer('Load image & ROIs', quiet=not do_print):
im = load_image(os.path.join(datadir, filename))
_, _, rois = parse_roi_xml(os.path.join(datadir, roiname))
rois = np.array(rois)
with WithTimer('Predict ', quiet=not do_print):
net.blobs['data'].data[...] = im
net.blobs['rois'].reshape(1, *rois.shape)
net.blobs['rois'].data[...] = rois
net.forward()
if len(net.blobs[layer].data.shape) == 4:
reproduced_val = net.blobs[layer].data[0, channel_idx, ii, jj]
else:
reproduced_val = net.blobs[layer].data[0, channel_idx]
if abs(reproduced_val - recorded_val) > .1:
print(
'Warning: recorded value %s is suspiciously different from reproduced value %s. Is the filelist the same?'
% (recorded_val, reproduced_val))
if do_maxes:
#grab image from data layer, not from im (to ensure preprocessing / center crop details match between image and deconv/backprop)
out_arr = np.zeros((3, size_ii, size_jj), dtype='float32')
out_arr[:, out_ii_start:out_ii_end,
out_jj_start:out_jj_end] = net.blobs['data'].data[
0, :, data_ii_start:data_ii_end,
data_jj_start:data_jj_end]
with WithTimer('Save img ', quiet=not do_print):
save_caffe_image(out_arr,
os.path.join(unit_dir, 'maxim_%03d.png' %
max_idx_0),
autoscale=False,
autoscale_center=0)
if do_deconv or do_deconv_norm:
diffs = net.blobs[layer].diff * 0
if len(diffs.shape) == 4:
diffs[0, channel_idx, ii, jj] = 1.0
else:
diffs[0, channel_idx] = 1.0
with WithTimer('Deconv ', quiet=not do_print):
net.deconv_from_layer(layer, diffs)
out_arr = np.zeros((3, size_ii, size_jj), dtype='float32')
out_arr[:, out_ii_start:out_ii_end,
out_jj_start:out_jj_end] = net.blobs['data'].diff[
0, :, data_ii_start:data_ii_end,
data_jj_start:data_jj_end]
if out_arr.max() == 0:
print('Warning: Deconv out_arr in range', out_arr.min(),
'to', out_arr.max(),
'ensure force_backward: true in prototxt')
if do_deconv:
with WithTimer('Save img ', quiet=not do_print):
save_caffe_image(out_arr,
os.path.join(
unit_dir,
'deconv_%03d.png' % max_idx_0),
autoscale=False,
autoscale_center=0)
if do_deconv_norm:
out_arr = np.linalg.norm(out_arr, axis=0)
with WithTimer('Save img ', quiet=not do_print):
save_caffe_image(
out_arr,
os.path.join(unit_dir,
'deconvnorm_%03d.png' % max_idx_0))
if do_backprop or do_backprop_norm:
diffs = net.blobs[layer].diff * 0
diffs[0, channel_idx, ii, jj] = 1.0
with WithTimer('Backward ', quiet=not do_print):
net.backward_from_layer(layer, diffs)
out_arr = np.zeros((3, size_ii, size_jj), dtype='float32')
out_arr[:, out_ii_start:out_ii_end,
out_jj_start:out_jj_end] = net.blobs['data'].diff[
0, :, data_ii_start:data_ii_end,
data_jj_start:data_jj_end]
if out_arr.max() == 0:
print('Warning: Deconv out_arr in range', out_arr.min(),
'to', out_arr.max(),
'ensure force_backward: true in prototxt')
if do_backprop:
with WithTimer('Save img ', quiet=not do_print):
save_caffe_image(out_arr,
os.path.join(
unit_dir,
'backprop_%03d.png' % max_idx_0),
autoscale=False,
autoscale_center=0)
if do_backprop_norm:
out_arr = np.linalg.norm(out_arr, axis=0)
with WithTimer('Save img ', quiet=not do_print):
save_caffe_image(
out_arr,
os.path.join(unit_dir,
'backpropnorm_%03d.png' % max_idx_0))
if do_info:
info_file.close()
def output_max_patches(max_tracker, net, layer, idx_begin, idx_end, num_top, datadir, filelist, outdir, do_which):
do_maxes, do_deconv, do_deconv_norm, do_backprop, do_backprop_norm, do_info = do_which
assert do_maxes or do_deconv or do_deconv_norm or do_backprop or do_backprop_norm or do_info, 'nothing to do'
mt = max_tracker
rc = RegionComputer()
image_filenames, image_labels = load_file_list(filelist)
print 'Loaded filenames and labels for %d files' % len(image_filenames)
print ' First file', os.path.join(datadir, image_filenames[0])
num_top_in_mt = mt.max_locs.shape[1]
assert num_top <= num_top_in_mt, 'Requested %d top images but MaxTracker contains only %d' % (num_top, num_top_in_mt)
assert idx_end >= idx_begin, 'Range error'
size_ii, size_jj = get_max_data_extent(net, layer, rc, mt.is_conv)
data_size_ii, data_size_jj = net.blobs['data'].data.shape[2:4]
n_total_images = (idx_end-idx_begin) * num_top
for cc, channel_idx in enumerate(range(idx_begin, idx_end)):
unit_dir = os.path.join(outdir, layer, 'unit_%04d' % channel_idx)
mkdir_p(unit_dir)
if do_info:
info_filename = os.path.join(unit_dir, 'info.txt')
info_file = open(info_filename, 'w')
print >>info_file, '# is_conv val image_idx image_class i(if is_conv) j(if is_conv) filename'
# iterate through maxes from highest (at end) to lowest
for max_idx_0 in range(num_top):
max_idx = num_top_in_mt - 1 - max_idx_0
if mt.is_conv:
im_idx, im_class, ii, jj = mt.max_locs[channel_idx, max_idx]
else:
im_idx, im_class = mt.max_locs[channel_idx, max_idx]
recorded_val = mt.max_vals[channel_idx, max_idx]
filename = image_filenames[im_idx]
do_print = (max_idx_0 == 0)
if do_print:
print '%s Output file/image(s) %d/%d' % (datetime.now().ctime(), cc * num_top, n_total_images)
if mt.is_conv:
# Compute the focus area of the data layer
layer_indices = (ii,ii+1,jj,jj+1)
data_indices = rc.convert_region(layer, 'data', layer_indices)
data_ii_start,data_ii_end,data_jj_start,data_jj_end = data_indices
touching_imin = (data_ii_start == 0)
touching_jmin = (data_jj_start == 0)
# Compute how much of the data slice falls outside the actual data [0,max] range
ii_outside = size_ii - (data_ii_end - data_ii_start) # possibly 0
jj_outside = size_jj - (data_jj_end - data_jj_start) # possibly 0
if touching_imin:
out_ii_start = ii_outside
out_ii_end = size_ii
else:
out_ii_start = 0
out_ii_end = size_ii - ii_outside
if touching_jmin:
out_jj_start = jj_outside
out_jj_end = size_jj
else:
out_jj_start = 0
out_jj_end = size_jj - jj_outside
else:
ii,jj = 0,0
data_ii_start, out_ii_start, data_jj_start, out_jj_start = 0,0,0,0
data_ii_end, out_ii_end, data_jj_end, out_jj_end = size_ii, size_ii, size_jj, size_jj
if do_info:
print >>info_file, 1 if mt.is_conv else 0, '%.6f' % mt.max_vals[channel_idx, max_idx],
if mt.is_conv:
print >>info_file, '%d %d %d %d' % tuple(mt.max_locs[channel_idx, max_idx]),
else:
print >>info_file, '%d %d' % tuple(mt.max_locs[channel_idx, max_idx]),
print >>info_file, filename
if not (do_maxes or do_deconv or do_deconv_norm or do_backprop or do_backprop_norm):
continue
with WithTimer('Load image', quiet = not do_print):
im = caffe.io.load_image(os.path.join(datadir, filename))
with WithTimer('Predict ', quiet = not do_print):
net.predict([im], oversample = False) # Just take center crop, same as in scan_images_for_maxes
if len(net.blobs[layer].data.shape) == 4:
reproduced_val = net.blobs[layer].data[0,channel_idx,ii,jj]
else:
reproduced_val = net.blobs[layer].data[0,channel_idx]
if abs(reproduced_val - recorded_val) > .1:
print 'Warning: recorded value %s is suspiciously different from reproduced value %s. Is the filelist the same?' % (recorded_val, reproduced_val)
if do_maxes:
#grab image from data layer, not from im (to ensure preprocessing / center crop details match between image and deconv/backprop)
out_arr = np.zeros((3,size_ii,size_jj), dtype='float32')
out_arr[:, out_ii_start:out_ii_end, out_jj_start:out_jj_end] = net.blobs['data'].data[0,:,data_ii_start:data_ii_end,data_jj_start:data_jj_end]
with WithTimer('Save img ', quiet = not do_print):
save_caffe_image(out_arr, os.path.join(unit_dir, 'maxim_%03d.png' % max_idx_0),
autoscale = False, autoscale_center = 0)
if do_deconv or do_deconv_norm:
diffs = net.blobs[layer].diff * 0
if len(diffs.shape) == 4:
diffs[0,channel_idx,ii,jj] = 1.0
else:
diffs[0,channel_idx] = 1.0
with WithTimer('Deconv ', quiet = not do_print):
net.deconv_from_layer(layer, diffs)
out_arr = np.zeros((3,size_ii,size_jj), dtype='float32')
out_arr[:, out_ii_start:out_ii_end, out_jj_start:out_jj_end] = net.blobs['data'].diff[0,:,data_ii_start:data_ii_end,data_jj_start:data_jj_end]
if out_arr.max() == 0:
print 'Warning: Deconv out_arr in range', out_arr.min(), 'to', out_arr.max(), 'ensure force_backward: true in prototxt'
if do_deconv:
with WithTimer('Save img ', quiet = not do_print):
save_caffe_image(out_arr, os.path.join(unit_dir, 'deconv_%03d.png' % max_idx_0),
autoscale = False, autoscale_center = 0)
if do_deconv_norm:
out_arr = np.linalg.norm(out_arr, axis=0)
with WithTimer('Save img ', quiet = not do_print):
save_caffe_image(out_arr, os.path.join(unit_dir, 'deconvnorm_%03d.png' % max_idx_0))
if do_backprop or do_backprop_norm:
diffs = net.blobs[layer].diff * 0
diffs[0,channel_idx,ii,jj] = 1.0
with WithTimer('Backward ', quiet = not do_print):
net.backward_from_layer(layer, diffs)
out_arr = np.zeros((3,size_ii,size_jj), dtype='float32')
out_arr[:, out_ii_start:out_ii_end, out_jj_start:out_jj_end] = net.blobs['data'].diff[0,:,data_ii_start:data_ii_end,data_jj_start:data_jj_end]
if out_arr.max() == 0:
print 'Warning: Deconv out_arr in range', out_arr.min(), 'to', out_arr.max(), 'ensure force_backward: true in prototxt'
if do_backprop:
with WithTimer('Save img ', quiet = not do_print):
save_caffe_image(out_arr, os.path.join(unit_dir, 'backprop_%03d.png' % max_idx_0),
autoscale = False, autoscale_center = 0)
if do_backprop_norm:
out_arr = np.linalg.norm(out_arr, axis=0)
with WithTimer('Save img ', quiet = not do_print):
save_caffe_image(out_arr, os.path.join(unit_dir, 'backpropnorm_%03d.png' % max_idx_0))
if do_info:
info_file.close()