diff --git a/examples/detector.py b/examples/detector.py
index b95ab71a..61868112 100644
--- a/examples/detector.py
+++ b/examples/detector.py
@@ -10,9 +10,9 @@ import darknet as dn
 import pdb
 
 dn.set_gpu(0)
-net = dn.load_net("cfg/tiny-yolo.cfg", "tiny-yolo.weights", 0)
-meta = dn.load_meta("cfg/coco.data")
-r = dn.detect(net, meta, "data/dog.jpg")
+net = dn.load_net("cfg/yolo-thor.cfg", "/home/pjreddie/backup/yolo-thor_final.weights", 0)
+meta = dn.load_meta("cfg/thor.data")
+r = dn.detect(net, meta, "data/bedroom.jpg")
 print r
 
 # And then down here you could detect a lot more images like:
diff --git a/examples/nightmare.c b/examples/nightmare.c
index 572396fe..71d38334 100644
--- a/examples/nightmare.c
+++ b/examples/nightmare.c
@@ -47,7 +47,7 @@ void optimize_picture(network *net, image orig, int max_layer, float scale, floa
 
 #ifdef GPU
     net->delta_gpu = cuda_make_array(delta.data, im.w*im.h*im.c);
-    cuda_push_array(net->input_gpu, im.data, net->inputs);
+    copy_cpu(net->inputs, im.data, 1, net->input, 1);
 
     forward_network_gpu(net);
     copy_gpu(last.outputs, last.output_gpu, 1, last.delta_gpu, 1);
@@ -62,7 +62,8 @@ void optimize_picture(network *net, image orig, int max_layer, float scale, floa
     cuda_free(net->delta_gpu);
     net->delta_gpu = 0;
 #else
-    net->input = im.data;
+    printf("\nnet: %d %d %d im: %d %d %d\n", net->w, net->h, net->inputs, im.w, im.h, im.c);
+    copy_cpu(net->inputs, im.data, 1, net->input, 1);
     net->delta = delta.data;
     forward_network(net);
     copy_cpu(last.outputs, last.output, 1, last.delta, 1);
@@ -308,8 +309,7 @@ void run_nightmare(int argc, char **argv)
     int reconstruct = find_arg(argc, argv, "-reconstruct");
     int smooth_size = find_int_arg(argc, argv, "-smooth", 1);
 
-    network *net = parse_network_cfg(cfg);
-    load_weights(net, weights);
+    network *net = load_network(cfg, weights, 0);
     char *cfgbase = basecfg(cfg);
     char *imbase = basecfg(input);
 
diff --git a/python/darknet.py b/python/darknet.py
index d0c6e961..398a2913 100644
--- a/python/darknet.py
+++ b/python/darknet.py
@@ -17,7 +17,6 @@ def c_array(ctype, values):
     arr[:] = values
     return arr
 
-
 class BOX(Structure):
     _fields_ = [("x", c_float),
                 ("y", c_float),
diff --git a/src/convolutional_kernels.cu b/src/convolutional_kernels.cu
index dd516fd3..56043e78 100644
--- a/src/convolutional_kernels.cu
+++ b/src/convolutional_kernels.cu
@@ -177,7 +177,7 @@ void backward_convolutional_layer_gpu(convolutional_layer l, network net)
     if(l.smooth){
         smooth_layer(l, 5, l.smooth);
     }
-    constrain_gpu(l.outputs*l.batch, 1, l.delta_gpu, 1);
+    //constrain_gpu(l.outputs*l.batch, 1, l.delta_gpu, 1);
     gradient_array_gpu(l.output_gpu, l.outputs*l.batch, l.activation, l.delta_gpu);
 
 
@@ -236,7 +236,7 @@ void backward_convolutional_layer_gpu(convolutional_layer l, network net)
             float *b = net.workspace;
             float *c = l.weight_updates_gpu + j*l.nweights/l.groups;
 
-            float *im = net.input+(i*l.groups + j)*l.c/l.groups*l.h*l.w;
+            float *im = net.input_gpu+(i*l.groups + j)*l.c/l.groups*l.h*l.w;
 
             im2col_gpu(im, l.c/l.groups, l.h, l.w,
                     l.size, l.stride, l.pad, b);
diff --git a/src/convolutional_layer.c b/src/convolutional_layer.c
index 86930b58..f197bcfe 100644
--- a/src/convolutional_layer.c
+++ b/src/convolutional_layer.c
@@ -150,24 +150,24 @@ void cudnn_convolutional_setup(layer *l)
             l->weightDesc,
             l->convDesc,
             l->dstTensorDesc,
-            CUDNN_CONVOLUTION_FWD_PREFER_FASTEST,
-            0,
+            CUDNN_CONVOLUTION_FWD_SPECIFY_WORKSPACE_LIMIT,
+            4000000000,
             &l->fw_algo);
     cudnnGetConvolutionBackwardDataAlgorithm(cudnn_handle(),
             l->weightDesc,
             l->ddstTensorDesc,
             l->convDesc,
             l->dsrcTensorDesc,
-            CUDNN_CONVOLUTION_BWD_DATA_PREFER_FASTEST,
-            0,
+            CUDNN_CONVOLUTION_BWD_DATA_SPECIFY_WORKSPACE_LIMIT,
+            4000000000,
             &l->bd_algo);
     cudnnGetConvolutionBackwardFilterAlgorithm(cudnn_handle(),
             l->srcTensorDesc,
             l->ddstTensorDesc,
             l->convDesc,
             l->dweightDesc,
-            CUDNN_CONVOLUTION_BWD_FILTER_PREFER_FASTEST,
-            0,
+            CUDNN_CONVOLUTION_BWD_FILTER_SPECIFY_WORKSPACE_LIMIT,
+            4000000000,
             &l->bf_algo);
 }
 #endif
diff --git a/src/network.c b/src/network.c
index 6425855d..1b4df6bc 100644
--- a/src/network.c
+++ b/src/network.c
@@ -389,6 +389,7 @@ int resize_network(network *net, int w, int h)
             error("Cannot resize this type of layer");
         }
         if(l.workspace_size > workspace_size) workspace_size = l.workspace_size;
+        if(l.workspace_size > 2000000000) assert(0);
         inputs = l.outputs;
         net->layers[i] = l;
         w = l.out_w;
diff --git a/src/parser.c b/src/parser.c
index 14914bc9..da7487b0 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -1110,7 +1110,7 @@ void load_weights_upto(network *net, char *filename, int start, int cutoff)
     fread(&major, sizeof(int), 1, fp);
     fread(&minor, sizeof(int), 1, fp);
     fread(&revision, sizeof(int), 1, fp);
-    if ((major*10 + minor) >= 2){
+    if ((major*10 + minor) >= 2 && major < 1000 && minor < 1000){
         fread(net->seen, sizeof(size_t), 1, fp);
     } else {
         int iseen = 0;